CN109217891A - A kind of individual combat handset type communication device - Google Patents
A kind of individual combat handset type communication device Download PDFInfo
- Publication number
- CN109217891A CN109217891A CN201811305670.9A CN201811305670A CN109217891A CN 109217891 A CN109217891 A CN 109217891A CN 201811305670 A CN201811305670 A CN 201811305670A CN 109217891 A CN109217891 A CN 109217891A
- Authority
- CN
- China
- Prior art keywords
- waveform
- data
- module
- sign language
- sensor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B1/00—Details of transmission systems, not covered by a single one of groups H04B3/00 - H04B13/00; Details of transmission systems not characterised by the medium used for transmission
- H04B1/38—Transceivers, i.e. devices in which transmitter and receiver form a structural unit and in which at least one part is used for functions of transmitting and receiving
- H04B1/3827—Portable transceivers
- H04B1/385—Transceivers carried on the body, e.g. in helmets
-
- 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
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B1/00—Details of transmission systems, not covered by a single one of groups H04B3/00 - H04B13/00; Details of transmission systems not characterised by the medium used for transmission
- H04B1/38—Transceivers, i.e. devices in which transmitter and receiver form a structural unit and in which at least one part is used for functions of transmitting and receiving
- H04B1/3827—Portable transceivers
- H04B1/385—Transceivers carried on the body, e.g. in helmets
- H04B2001/3861—Transceivers carried on the body, e.g. in helmets carried in a hand or on fingers
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The present invention relates to Test and control fields, more particularly to a kind of individual combat handset type communication device, the present invention solves the Sign Language Recognition technology based on data glove, with one group of continuous gesture motion (track of variation and gesture motion including finger), as research object.For static sign language, the meaning that it can be expressed is more abundant and accurate.In the complex situation of operation condition, when can not carry out manual communication due to cooperation team member directly facing face and not can be carried out speech exchange, it can not accomplish that the coordinated of unification and the movement of battle plan be easy to cause practical operation team member injured or even sacrifices.When operation team member encounters, operation condition directly facing face can not carry out manual communication and while not can be carried out speech exchange can use the communication device and smoothly complete interim battle plan and formulates and the collaboration of tactical operation, guarantee that the life security of operation team member simultaneously smoothly completes task.
Description
Technical field
The present invention relates to Test and control fields, and in particular to a kind of individual combat handset type communication device.
Background technique
Individual combat communication device has very important effect in fight, is mutually to cooperate between individual soldier, mutually
The basis of cooperation.When executing minor operation, individual combat communication device is particularly important.Complicated combat duty can not be only
It is completed by single, the cooperation of operation team directly determines the implementation of task.The division of labor of the Team Member in task often cannot
It is fully validated before task execution, it needs constantly to be adjusted in task progress.And each time in task implementation procedure
The coherence request etc. of the assurance of node, each individual soldier's action requires that individual soldier must keep continual communication in task.
Individual combat communication modes common at present have following several:
1. gesture communicates: being linked up by simple gesture and team member.Advantage be without individually equipment communication device, can be with
Reduce individual soldier's weight bearing.It, in most cases can not be straight between individual soldier when task execution the disadvantage is that due to the uncertainty of operational environment
Meet visual team member, and the not applicable distance of such mode farther out in the case of communication, or even be easy to cause misunderstanding.
2. radio voice communicates: carrying out speech communication by radio signal.Advantage is to communicate directly, conveniently.Disadvantage
Be by execute task environment it is more demanding, be easy to give away one's position in pole stationary ring border, in pole, noisy environment can not carry out effective ditch
It is logical.
Radio code communication: it is communicated after being encoded by radio signal to assignment instructions.Advantage is that Content of communciation can be with
Encryption, is not easy to crack.The disadvantage is that such equipment usually requires larger volume, need individual soldier in the instruction for being completed at the same time complexity of fighting
Input, and radio voice signal is easy to be intercepted and captured and cracked by enemy.
Summary of the invention
In view of the deficiencies of the prior art, the invention discloses a kind of individual combat handset type communication device, the present invention is opposite
It is communicated in traditional gesture, there is stronger concealment, without can visually carry out instruction transmission.It, can relative to speech communication
It is affected to avoid the execution made a sound to task, and avoids exposing players' positions.It can simplify relative to communicating with code telegram
The process of instruction input allows individual soldier to complete the transmission of instruction within the shortest time.
The present invention is achieved by the following technical programs:
A kind of individual combat handset type communication device, including system function module, Sign Language Recognition module and communication module；Its
Be characterized in that: the system function module includes system power supply module, middle control module, identification module and memory module；Hand
Language identification module includes curvature acquisition, acceleration acquisition and gyroscope；Communication module includes data acquisition module, data transmitting
Module and data reception module；When wearer makes different gestures, Sign Language Recognition module detects digital flexion degree, palm movement
Acceleration and angular speed, middle control module call preset corpus in memory module according to detection data, pass through data acquisition module
Block is encoded, and the data after coding are transmitted to teammate by data transmission module, and data reception module is standby, when receiving team
Pass through data acquisition module block decoding when friendly information；Result notifies wearer by middle control module after decoding.
Preferably, after individual soldier's wearable device, system power supply module starting, lithium battery is powered to each unit module, middle control mould
Block is powered after starting, and notice each unit module is started to work, and starts to work after identification module starting, and detection wearer refers to
Line determines identity.
Preferably, the curvature acquisition is curvature sensor, and gloves have a curvature sensing on each finger
Device can collect the voltage of 5 groups of variations, and hand during exercise three directions of XYZ axis acceleration and angular speed this 6
Group data, form 11 groups of data altogether, carry out characteristic point acquisition by 11 groups of data to each standard gesture for needing to use and compile
Code, is stored in SD card, as sign language database.
Preferably, as combatant, sensor acquires hand in the characteristic point and SD of sign language during wearing gloves are talked
Data carry out related coefficient calculating in language data, and finding out the maximum data of related coefficient can determine that sign language looks like, and send out in time
Give cooperation personnel.
Preferably, angular velocity of satellite motion of the gyroscope acquisition hand on the axis of three, space is converted to space by quaternary number
Angle utilizes displacement of the double integral acquisition hand of accelerometer on the axis of three, space.
A kind of method of gesture Waveform Matching, the method use Sign Language Recognition module, it is characterised in that: the method packet
Include following steps:
S1 collects the waveform of consecutive variations on time shaft by sensor；
S2 carries out waveform analysis for each sensor and obtains the corresponding waveform of each sensor, establishes the wave of sensor
Shape library；
S3 establishes waveform coding comparison library to sign language according to the corresponding waveform sensor of different sign languages；
S4 carries out the matching of data waveform according to the waveform library in S2.
Preferably, the waveform library, which needs to need to have gloves in advance, demonstrates store-through storage to SD card for the sign language used
In, the format of storage is the data information of waveform and the sensor serial number of waveform and waveform serial number；It is read after sign language arrives
Sensor information is taken, Waveform Matching is carried out, the corresponding waveform signal of output is matched to, is not matched to, the output wave of sensor
Shape number zero, wherein 0 is no shape information；Finally obtain the encoded information being made of 11 numbers.
Preferably, the matched method of the data waveform are as follows: it is assumed that two signals are respectively x (t), y (t), can choose
When multiple a makes a*y (t) go to approach x (t)；Error energy is indicated with the integral square in the time domain of x (t)-a*y (t)；Times
Number a's selects it has to be ensured that energy error can be made minimum, by asking extreme value that can learn when a is x (t) * y function derivation
(t) it can satisfy condition when integral ratio in the integral of time domain and y (t) * y (t) in time domain, error energy with this condition
It is the smallest under possible all conditions.
Preferably, the dependency number for defining x (t) and y (t) is Pxy, square is relative error energy with 1 difference, that is, is missed
The ratio of poor energy and x (t) * x (t) in time-domain integration, wherein xy can be used to characterize the similarity degree of two waveforms；
The equation about Pxy is solved, molecule is integral of x (t) the * y (t) in time domain；It is divided into respective square of two signals
In the square root of the product of time-domain integration.It can mathematically prove that the mould of molecule is less than denominator namely the mould of dependency number Pxy will not
Greater than 1；
Due to for the signal of finite energy, energy be it is determining, the size of related coefficient Pxy is only by x (t) * y
(t) integral is determined；If two completely dissimilar its amplitude value of waveform and current moment is mutually indepedent, independently of each other out
, x (t) * y (t)=0, integral result is also 0, so similarity is worst when related coefficient is 0, i.e., it is uncorrelated；Work as correlation
Coefficient is 1, then error energy is 0, illustrates that this two signals similarity is fine, be it is linear relevant, two signal waveforms it is similar
Property.
Preferably, it is characterised in that: need to return standard gesture waveform acquisition before the correlation analysis for doing two waveforms
Come as document format data, then in practice operation by under the waveform recording talked also as data file, according to
Correlation function concept, bidding quasi wave graphic data be A [i], i ∈ [0,10], practice operation in by the waveform talked be B [i], i
∈[0,10]；
Integral approach is carried out to two groups of data in central control system approximately to be integrated in such a way that discrete point takes sum:
α +=A [i] * B [i]；// to the integral of A [i] * B [i]
β +=A [i] * A [i]；// to the integral of A [i] * A [i]
γ +=B [i] * B [i]；// to the integral of B [i] * B [i]
P=α/(sqrt (β * γ))；// related coefficient calculates.
The invention has the benefit that
The present invention solves the Sign Language Recognition technology based on data glove, with one group of continuous gesture motion (including finger
The track of variation and gesture motion), as research object.For static sign language, the meaning that it can be expressed is richer
It is rich and accurate.
In the complex situation of operation condition, since cooperation team member can not carry out manual communication directly facing face
(distance farther out or since barrier blocks) and when not can be carried out speech exchange, it can not accomplish the unification and movement of battle plan
Coordinated be easy to cause practical operation team member injured or even sacrifices.
When operation team member encounters operation condition manual communication can not be carried out (apart from farther out or due to barrier directly facing face
Block) and while not can be carried out speech exchange can use the communication device and smoothly complete interim battle plan and formulate and tactical operation
Collaboration, guarantee operation team member life security simultaneously smoothly complete task.
It is communicated relative to traditional gesture, there is stronger concealment, without can visually carry out instruction transmission.Relative to
Speech communication can affect to avoid the execution made a sound to task, and avoid exposing players' positions.It is logical relative to password
News can simplify the process of instruction input, and individual soldier is allow to complete the transmission of instruction within the shortest time.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is integral module schematic diagram of the invention；
Fig. 2 is circuit theory schematic diagram of the present invention；
Fig. 3 is the resistance signal conversion circuit of curvature sensor of the present invention；
Fig. 4 is gesture waveform acquisition schematic diagram of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Embodiment 1
A kind of individual combat handset type communication device as shown in Figure 1, including system function module, Sign Language Recognition module and
Communication module；The system function module includes system power supply module, middle control module, identification module and memory module；Hand
Language identification module includes curvature acquisition, acceleration acquisition and gyroscope；Communication module includes data acquisition module, data transmitting
Module and data reception module；When wearer makes different gestures, Sign Language Recognition module detects digital flexion degree, palm movement
Acceleration and angular speed, middle control module call preset corpus in memory module according to detection data, pass through data acquisition module
Block is encoded, and the data after coding are transmitted to teammate by data transmission module, and data reception module is standby, when receiving team
Pass through data acquisition module block decoding when friendly information；Result notifies wearer by middle control module after decoding.
After individual soldier's wearable device, system power supply module starting, lithium battery is powered to each unit module, and middle control module energization is opened
After dynamic, notice each unit module is started to work, and is started to work after identification module starting, is detected wearer fingerprint, determines
Identity.
Curvature acquisition is curvature sensor, and gloves have a curvature sensor on each finger, can acquire
To the voltage of 5 groups of variations, in addition hand is during exercise in this 6 groups of data of the acceleration and angular speed in three directions of XYZ axis, total group
At 11 groups of data, characteristic point acquisition coding is carried out by 11 groups of data to each standard gesture for needing to use, is stored in SD
In card, as sign language database.
When sign language data in combatant sensor acquires sign language during wearing gloves are talked characteristic point and SD
Middle data carry out related coefficient calculating, and finding out the maximum data of related coefficient can determine that sign language looks like, and be timely transmitted to assist
Same combatant.
Gyroscope acquires angular velocity of satellite motion of the hand on the axis of three, space and is converted to Space Angle by quaternary number, utilizes acceleration
Displacement of the double integral acquisition hand of degree meter on the axis of three, space.
Wherein gesture identification is mainly formed by image recognition, static gesture identification and dynamic hand gesture recognition etc. are several.Due to
Equipment provided by the invention is mainly used in individual combat environment, and image recognition technology is not suitable for application environment, and static
For gesture identification due to identifiable sign language limited amount, application value is lower.Dynamic Sign Language Recognition can be fully contemplated by existing
The general sign language gesture having may be implemented richer to exchange with accurate.
The resistance signal of curvature sensor can be converted to voltage signal using circuit shown in Fig. 3, the circuit output
Voltage signal Vout, which is connected on the ADC pin of middle control MCU, can collect the voltage signal, and analog signal is become feasible to locate
The digital signal of reason.
Hand activities are very flexibly complicated but can be divided into the movement of the bending and hand of finger in space.Do not consider finger
Bending hand can be regarded as to rigid body, the movement of rigid body in space can be divided into Fixed-point Motion of A and translation.Therefore it can use
Gyroscope acquires angular velocity of satellite motion of the hand on the axis of three, space and is converted to Space Angle by quaternary number, utilizes the two of accelerometer
Multiple integral acquires displacement of the hand on the axis of three, space.Test proves that the program can more accurately acquire it is in one's hands in sky
Between middle motion information, and real-time is good.The bending of finger uses curvature sensor, and curvature sensor is that have variable resistance
Composition, its resistance value changes as its curvature changes.Finger can be more accurately collected using curvature sensor
Bending information.It is as shown in Figure 4 that it acquires information.
In order to measure digital flexion degree, using 2.2 " bending sensor module of Flex can be understood to strain
Piece: the working principle of resistance strain gage is made based on strain effect, i.e. the effect of conductor or semiconductor material in external force
When lower generation mechanically deform, resistance value changes accordingly, and the working principle of bending sensor cans be compared to a potentiometer, leads to
Curvature is crossed to change resistance value size.
Current sensor bending can be obtained in the output voltage values that operational amplifier is read by Chip Microcomputer A/D acquisition channel
Degree, and then obtain digital flexion situation.It is digital flexion judgement service using this numerical value.
Acceleration transducer is a kind of electronic equipment that can measure acceleration.Acceleration is exactly when object is in accelerator
In act on the power on object, like terrestrial gravitation, that is, gravity.Its definition is: can experience acceleration and be converted into
The sensor of usable output signal.Wherein the principle of linear accelerometer is principle of inertia, that is, the balance of power,
A (acceleration)=F (inertia force)/M (quality)
Only needing to measure F can.How F is measured? going to balance this power with electromagnetic force can.It can be obtained by
F corresponds to the relationship of electric current.It only needs to go to demarcate this proportionality coefficient just with experiment.
Gyroscope is with the moment of momentum sensitivity shell relative inertness space of high-speed rotator around being orthogonal to one of the axis of rotation
Or the angular movement detection device of two axis.The also referred to as gyro of said function is played using angular movement detection device made of other principles
Instrument.It has a wide range of applications in every field such as science, technology, military affairs.Such as: gyro compass, orientation indicator, shell
Overturning, rotation of gyro etc..
Finger is during bending along with the rotation and movement of entire hand, and the signal is by JY901 (9 axis attitude angles
Sensor) module acquisition, integrate in this module can accelerometer and gyroscope, can acquire simultaneously when hand is during exercise in XYZ
The acceleration and angular speed in three directions of axis, and in module also this 6 directly can be exported by serial ports with microprocessor
Data.The two cooperates to acquire hand space angle, they together constitute the measuring unit of a 6DOF.
HMM algorithm is at present using than wide in Activity recognition.It is a kind of processing method of effective time varying signal,
The correction to the time is implied, and provides study mechanism and recognition capability, but the method needs to provide a large amount of training pattern
And it carries out testing the parameter that must just obtain in model.Based on this, we propose the side of Waveform Matching according to the characteristics of acquisition data
Method.
It can regard the waveform of consecutive variations on time shaft, different gesture sign languages as by the collected information of sensor
Corresponding corresponding data waveform.When the bending information of hand available five fingers when doing sign language, the angle of three spatial axes
The shape information of the displacement information of information and three spatial axes totally 11 sensors.One hand can in selection GBT/24435-2009
The sign language of expression carries out multiple test, obtains the shape information of corresponding 11 sensors of each gesture sign language.For each
A sensor carries out waveform analysis, such as the curvature information of middle finger, obtains the shape information of middle finger in all sign languages and will not
Same waveform is classified and is encoded according to its feature.It can be obtained by the corresponding waveform of each sensor in this way, establish and pass
The waveform library of sensor.And waveform coding comparison library is established to sign language according to the corresponding waveform sensor of different sign languages.
Gesture waveform library is the core of whole system, more convenient in order to upgrade later, and gesture waveform library needs in advance need to
It has gloves on and the sign language used is demonstrated into store-through storage into SD card, the format of storage is the data information and waveform of waveform
Sensor serial number and waveform serial number.Sensor information is read after sign language arrives, Waveform Matching is carried out, is matched to output phase
The waveform signal answered, is not matched to, the output waveform number zero of sensor, wherein 0 is no shape information.Finally obtain one by
The encoded information of 11 number compositions.
Data format such as 11,12,13,14,15,16,17,18,19,20,21#1 r n.Comma separates each waveform
Value, be easy distinguish, be conducive to carry out Waveform Matching, r n be gesture coding between separator, for separating different hands
Gesture, number represents sign language sequence after No. #, and each sign language is numbered.
The similarity of two waveforms is measured in the matching of data waveform.Since the waveform actually generated is not only simple
Just, cosine waveform, and the irregular waveform often containing relatively abundant frequency distribution, and the electricity in device components itself and the external world
Magnetic disturbance inevitably introduces interference noise again, and the differentiation of itself and the fitting degree for being pre-designed waveform is just analyzed for us
Increase difficulty.In addition, actual waveform and being pre-designed between waveform often there is the difference in timing, the change of phase is same
Also the fitting for being unfavorable for signal differentiates.It is proposed using higher mathematics and the related knowledge of signal and system aspects to the problem
Solution.
In signal and this subject of system, correlation is a kind of important side that characteristics of signals is described in the time domain
Method.Since the power spectrum function of its communication is a pair of of Fourier transform, often it is utilized to analyze random letter in signal analysis
Number Power Spectrum Distribution so that many people can associate the calculating of power spectrum signal once mentioning correlation, but related right
The analysis for determining signal is also to have certain application.Since relevant concept is introduced to study the statistical property of random signal
, then theoretically we can also be applied to two determining signals (our collected signal waveforms and one
A theoretical waveform) similitude research on.
Compare the similarity degrees of two waveforms conceptive will also start with from relevant, it is assumed that two signals are respectively x (t), y
(t), it can choose when multiple a makes a*y (t) go to approach x (t).We can borrow error energy to measure this to waveform this again
Similarity degree, specific method in higher mathematics be used to discriminant function between orthogonality method it is substantially similar: error energy x
(t) integral square in the time domain of-a*y (t) indicates；Multiple a's selects it has to be ensured that energy error can be made minimum,
By to function derivation ask extreme value can learn when a be x (t) * y (t) time domain integral and y (t) * y (t) time domain integral
It can satisfy condition when ratio, error energy with this condition is the smallest under possible all conditions.Define x (t) and y (t)
Dependency number be Pxy, square be relative error energy, i.e. error energy and x (t) * x (t) in time-domain integration with 1 difference
Ratio.Wherein, xy can be used to characterize the similarity degree of two waveforms.The equation about Pxy is solved, molecule is x (t) * y
(t) in the integral of time domain；It is divided into the square root of respective square of the two signals product in time-domain integration.It can mathematically prove point
The mould of son is less than denominator namely the mould of dependency number Pxy is not more than 1.Since for the signal of finite energy, energy is true
Fixed, the size of related coefficient Pxy is only determined by the integral of x (t) * y (t).If its amplitude of the waveform of two complete dissmilarities
Value and out current moment be it is mutually indepedent, independently of each other, x (t) * y (t)=0, integral result is also 0, so working as phase relation
Similarity is worst when number is 0, i.e., uncorrelated.When related coefficient is 1, then error energy is 0, illustrates this two signals similarity very
It is good, it is linear relevant.Therefore using related coefficient as a kind of degree of the similitude (or linear correlation) of two signal waveforms
Amount be entirely have theoretical foundation, it is reasonable.
It is needed before the correlation analysis for doing two waveforms by standard gesture waveform acquisition back as document format data
(such as 11,12,13,14,15,16,17,18,19,20,21#1 r n), then the waveform recording that will talk in practice operation
Get off also as data file, according to correlation function concept, being marked with quasi wave graphic data is A [i], (i ∈ [0,10]), practice operation
It is middle by the waveform talked be B [i], (i ∈ [0,10]).
Integral approach is carried out to two groups of data in central control system approximately to be integrated in such a way that discrete point takes sum:
α +=A [i] * B [i]；// to the integral of A [i] * B [i]
β +=A [i] * A [i]；// to the integral of A [i] * A [i]
γ +=B [i] * B [i]；// to the integral of B [i] * B [i]
P=α/(sqrt (β * γ))；// related coefficient calculates.
When sign language data in combatant sensor acquires sign language during wearing gloves are talked characteristic point and SD
Middle data carry out related coefficient calculating, are found out and the highest data of related coefficient in database, energy by calculating related coefficient
Determine that gloves user gets meaning representated by sign language and is timely transmitted to cooperation personnel.
Related coefficient algorithm calculating is relatively simple, and the speed of service is very fast in single-chip microcontroller, can satisfy requirement of real-time.
The workflow of whole system on the whole as shown in Figure 2 are as follows: each gloves need 5 this sensors, the biography
Sensor is similar to variable resistance, and different curvature corresponds to different resistance, by curvature sensor access digital flexion degree letter
Number Acquisition Circuit, the circuit form (each curvature sensor corresponds to two-way operational amplifier) by 10 operational amplifiers, should
The corresponding resistance of the different bending degree of each finger is converted to voltage signal by circuit, and it is single which is directly accessed middle control
ADC acquires this voltage signal inside piece machine, converts bit digital quantity.This completes the acquisitions of digital flexion degree signal.
Finger is during bending along with the rotation and movement of entire hand simultaneously, and the signal is by JY901 (9 axis postures
Angular transducer) module acquisition, integrate in this module can accelerometer and gyroscope, can acquire simultaneously when hand exists during exercise
The acceleration and angular speed in three directions of XYZ axis, and in module also with microprocessor can directly by serial ports export this 6
A data.The two cooperates to acquire hand space angle, they together constitute the measuring unit of a 6DOF.
Gloves have a curvature sensor on each finger, can collect the voltage of 5 groups of variations, in addition hand exists
In this 6 groups of data of the acceleration and angular speed in three directions of XYZ axis when movement, 11 groups of data are formed altogether, by each needs
11 groups of data of the standard gesture used carry out characteristic point acquisition coding, are stored in SD card, as sign language database.As
Data carry out phase to war personnel in sign language data in the characteristic point of sensor acquisition sign language and SD during wearing gloves are talked
Relationship number calculates, and finding out the maximum data of related coefficient can determine that sign language looks like, and be sent in time by wireless sending module
Give cooperation personnel.
In curvature sensor resistance-voltage conversion circuit due to the sensor resistance variation range be 45K Ω~
125K Ω makes output electricity so R2 resistance selection should take the median i.e. 80K Ω of R1 change in resistance range or so resistance value preferable
Press the linearity preferable, convenient for measurement.Impedance buffer on curvature sensor is single side operational amplifier, with these sensors
It is used together, because the Low-bias Current of operational amplifier reduces the error due to caused by source impedance, and curvature sensor
As divider.It is recommended that operational amplifier be LM358 or LM324.
JY901 (9 axis attitude angle sensor) module, inside modules are integrated with attitude algorithm device, cooperate dynamic Kalman
Filtering algorithm is capable of the current pose of accurate output module in a dynamic environment, and attitude measurement accuracy is 0.05 degree static, dynamically
0.1 degree, stability is high, and performance is even better than the inclinator of certain professions！And it can also be straight with microprocessor in module
It connected serial ports and exports this 6 data.Middle control MCU directly passes through the acceleration and angular speed data that serial ports reads the module.
Since the characteristic of accelerometer and angular speed flowmeter sensor needs using preceding carry out primary calibration, meter calibrating is added to use
In the zero bias of removal accelerometer.Sensor can all have different degrees of zero offset error when leaving the factory, need to be calibrated manually
Afterwards, measurement just can be accurate.The calibration only need to keep after powering palm level wait can self calibration complete, can normally make
With.
If sensor does not carry out calibration may will lead to individual Sign Language Recognition inaccuracy in use, influence to make
With.
Experimental data: utilizing three-axis gyroscope, 3-axis acceleration and one be located at the curvature sensor at thumb into
Row parameters simulation:
Simulation process:
1. getting sign language according to specified gesture.
2. single-chip microcontroller reads curvature sensor and the current initial data of gyroscope, acceleration transducer.
3. a pair data are handled, it is translated into the data for being easy to express and analyze.
4. sending treated data to computer host computer by serial ports.
5. allowing host computer to save transmitted data in real time and data being converted into intuitive lines waveform diagram.
6. being analyzed by gesture sign language actual act and the comparison of waveform diagram and data.
7. last end obtains gesture sign language parameter.
The data form (period 4750-4780) of observation simulation for the first time:
The variation tendency that can observe each curve has reacted hand in the tendency:
State → edge-on and such a process of digital flexion state of the state that level is stretched → edge-on.Period is numerically
Gradual change given full expression to this process.Wherein:
Z axis from by horizontal gravity to it is edge-on when to the axis gravity reduce, 700 can be down to from the axle acceleration from 2000
It being verified, and X-axis is because receive the gravity that Z axis " transfer " comes at this time, X-axis acceleration of gravity drops to absolutely-
1800 (because of X-axis negative direction stress, acceleration reversely increases), but hand is rotated by roll angle, is cared for roll angle and is increased from 28
Add to 663 (2.8 degree to 66.3 degree).The analyzing examples of above section sufficiently demonstrate data analysis to gesture model determine can
Row.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to the foregoing embodiments
Invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each implementation
Technical solution documented by example is modified or equivalent replacement of some of the technical features；And these modification or
Replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of individual combat handset type communication device, including system function module, Sign Language Recognition module and communication module；It is special
Sign is: the system function module includes system power supply module, middle control module, identification module and memory module；Sign language
Identification module includes curvature acquisition, acceleration acquisition and gyroscope；Communication module includes data acquisition module, data transmitting mould
Block and data reception module；When wearer makes different gestures, Sign Language Recognition module detects digital flexion degree, palm movement adds
Speed and angular speed, middle control module call preset corpus in memory module according to detection data, pass through data acquisition module
It is encoded, the data after coding are transmitted to teammate by data transmission module, and data reception module is standby, when receiving teammate
Pass through data acquisition module block decoding when information；Result notifies wearer by middle control module after decoding.
2. individual combat handset type communication device according to claim 1, it is characterised in that: after individual soldier's wearable device, be
Power supply module of uniting starts, and lithium battery gives each unit module to power, and middle control module is powered after starting, and notice each unit module starts work
Make, starts to work after identification module starting, detect wearer fingerprint, determine identity.
3. individual combat handset type communication device according to claim 1, it is characterised in that: the curvature acquisition is curved
Curvature sensor, gloves have a curvature sensor on each finger, can collect the voltage of 5 groups of variations, in addition
Hand in this 6 groups of data of the acceleration and angular speed in three directions of XYZ axis, forms 11 groups of data, by each during exercise altogether
11 groups of data of the standard gesture for needing to use carry out characteristic point acquisition coding, are stored in SD card, as sign language database.
4. individual combat handset type communication device according to claim 3, it is characterised in that: when combatant is wearing hand
Sensor acquires data progress related coefficient calculating in sign language data in the characteristic point and SD of sign language during set is talked, and finds out
The maximum data of related coefficient can determine that sign language looks like, and be timely transmitted to cooperation personnel.
5. individual combat handset type communication device according to claim 1, it is characterised in that: the gyroscope acquisition hand exists
Angular velocity of satellite motion on the axis of three, space is converted to Space Angle by quaternary number, is existed using the double integral acquisition hand of accelerometer
Displacement on the axis of three, space.
6. a kind of method of gesture Waveform Matching, the method uses Sign Language Recognition module, it is characterised in that: the method includes
Following steps:
S1 collects the waveform of consecutive variations on time shaft by sensor；
S2 carries out waveform analysis for each sensor and obtains the corresponding waveform of each sensor, establishes the waveform of sensor
Library；
S3 establishes waveform coding comparison library to sign language according to the corresponding waveform sensor of different sign languages；
S4 carries out the matching of data waveform according to the waveform library in S2.
7. the method for gesture Waveform Matching according to claim 6, it is characterised in that: the waveform library needs in advance need to
It has gloves on and the sign language used is demonstrated into store-through storage into SD card, the format of storage is the data information and waveform of waveform
Sensor serial number and waveform serial number；Sensor information is read after sign language arrives, Waveform Matching is carried out, is matched to output phase
The waveform signal answered, is not matched to, the output waveform number zero of sensor, wherein 0 is no shape information；Finally obtain one by
The encoded information of 11 number compositions.
8. the method for gesture Waveform Matching according to claim 6, it is characterised in that: the matched side of the data waveform
Method are as follows: it is assumed that two signals are respectively x (t), y (t), can choose when multiple a makes a*y (t) go to approach x (t)；Error energy x
(t) integral square in the time domain of-a*y (t) indicates；Multiple a's selects it has to be ensured that energy error can be made minimum,
By to function derivation ask extreme value can learn when a be x (t) * y (t) time domain integral and y (t) * y (t) time domain integral
It can satisfy condition when ratio, error energy with this condition is the smallest under possible all conditions.
9. the method for gesture Waveform Matching according to claim 8, it is characterised in that: define the dependency number of x (t) and y (t)
Square be relative error energy with 1 difference for Pxy, i.e., error energy and x (t) * x (t) time-domain integration ratio,
In, xy can be used to characterize the similarity degree of two waveforms；
The equation about Pxy is solved, molecule is integral of x (t) the * y (t) in time domain；Be divided into respective square of two signals when
The square root of the product of volume integration.It can mathematically prove that the mould of molecule is less than denominator namely the mould of dependency number Pxy is not more than
1；
Due to for the signal of finite energy, energy be it is determining, the size of related coefficient Pxy is only by x (t) * y's (t)
Integral is determined；If two completely dissimilar its amplitude value of waveform and current moment is mutually indepedent, independently of each other, x out
(t) * y (t)=0, integral result are also 0, so similarity is worst when related coefficient is 0, i.e., it is uncorrelated；Work as related coefficient
It is 1, then error energy is 0, illustrates that this two signals similarity is fine, is linear relevant, the similitude of two signal waveforms.
10. the method for gesture Waveform Matching according to claim 8, it is characterised in that: in the correlation for doing two waveforms point
It is needed before analysis by standard gesture waveform acquisition back as document format data, the wave that then will be talked in practice operation
Shape is recorded also as data file, and according to correlation function concept, being marked with quasi wave graphic data is A [i], i ∈ [0,10], practice
In operation by the waveform talked be B [i], i ∈ [0,10]；
Integral approach is carried out to two groups of data in central control system approximately to be integrated in such a way that discrete point takes sum:
α +=A [i] * B [i]；// to the integral of A [i] * B [i]
β +=A [i] * A [i]；// to the integral of A [i] * A [i]
γ +=B [i] * B [i]；// to the integral of B [i] * B [i]
P=α/(sqrt (β * γ))；// related coefficient calculates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811305670.9A CN109217891B (en) | 2018-11-05 | 2018-11-05 | Hand-wearing type communication device for individual combat |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811305670.9A CN109217891B (en) | 2018-11-05 | 2018-11-05 | Hand-wearing type communication device for individual combat |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109217891A true CN109217891A (en) | 2019-01-15 |
| CN109217891B CN109217891B (en) | 2021-04-09 |
Family
ID=64994391
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811305670.9A Expired - Fee Related CN109217891B (en) | 2018-11-05 | 2018-11-05 | Hand-wearing type communication device for individual combat |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109217891B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103578329A (en) * | 2013-10-25 | 2014-02-12 | 西安理工大学 | Intelligent sign language interpretation device and usage method thereof |
| CN104434119A (en) * | 2013-09-20 | 2015-03-25 | 卡西欧计算机株式会社 | Body information obtaining device and body information obtaining method |
| CN204791666U (en) * | 2015-05-13 | 2015-11-18 | 郑州大学 | Portable intelligent sign language interpreter device |
| CN107544072A (en) * | 2017-08-15 | 2018-01-05 | 北京理工大学 | A kind of precision distance measurement system and method for preset waveform matching |
-
2018
- 2018-11-05 CN CN201811305670.9A patent/CN109217891B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104434119A (en) * | 2013-09-20 | 2015-03-25 | 卡西欧计算机株式会社 | Body information obtaining device and body information obtaining method |
| CN103578329A (en) * | 2013-10-25 | 2014-02-12 | 西安理工大学 | Intelligent sign language interpretation device and usage method thereof |
| CN204791666U (en) * | 2015-05-13 | 2015-11-18 | 郑州大学 | Portable intelligent sign language interpreter device |
| CN107544072A (en) * | 2017-08-15 | 2018-01-05 | 北京理工大学 | A kind of precision distance measurement system and method for preset waveform matching |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109217891B (en) | 2021-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105102928B (en) | Inertial device, methods and procedures | |
| CN104780217B (en) | Detect method, system and the client of user job efficiency | |
| CN106527738A (en) | Multi-information somatosensory interaction glove system and method for virtual reality system | |
| Kunze et al. | Can magnetic field sensors replace gyroscopes in wearable sensing applications? | |
| CN103690148B (en) | A kind of exercise coordination capacity simple detection system | |
| CN105575219A (en) | Intelligent glove | |
| CN106174813A (en) | A kind of Intelligent glove | |
| Fang et al. | Development of a wearable device for motion capturing based on magnetic and inertial measurement units | |
| CN109011506B (en) | Training action recognition method | |
| CN108279773B (en) | Data glove based on MARG sensor and magnetic field positioning technology | |
| Choi et al. | Development of a low-cost wearable sensing glove with multiple inertial sensors and a light and fast orientation estimation algorithm | |
| CN109737941A (en) | A kind of human action method for catching | |
| CN111506199A (en) | Kinect-based high-precision unmarked whole-body motion tracking system | |
| US10424224B2 (en) | Glove for use in collecting data for sign language recognition | |
| CN115919250A (en) | Human dynamic joint angle measuring system | |
| Chunsheng et al. | Human gait feature data analysis and person identification based on IMU | |
| CN109217891A (en) | A kind of individual combat handset type communication device | |
| CN210091521U (en) | Percussion training auxiliary device | |
| CN206270980U (en) | A kind of motion capture gloves for gesture identification | |
| Xingjun | Application of Motion Sensor Fusion in Special Competitive Sports | |
| Xia et al. | Real-time recognition of human daily motion with smartphone sensor | |
| CN107443356B (en) | It is a kind of can real-time display robot form system and method | |
| Shi et al. | Data glove design and virtual hand simulation based on single-chip microcomputer | |
| CN206390909U (en) | A kind of detection means of piano playing hand | |
| CN206401997U (en) | A kind of Hand gesture detection device based on wireless power mode |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210409 Termination date: 20211105 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |