CN106774887A - A kind of non-contact gesture identifying device and recognition methods - Google Patents
A kind of non-contact gesture identifying device and recognition methods Download PDFInfo
- Publication number
- CN106774887A CN106774887A CN201611158133.7A CN201611158133A CN106774887A CN 106774887 A CN106774887 A CN 106774887A CN 201611158133 A CN201611158133 A CN 201611158133A CN 106774887 A CN106774887 A CN 106774887A
- Authority
- CN
- China
- Prior art keywords
- data
- threshold value
- value
- gesture
- 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.)
- Pending
Links
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
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a kind of non-contact gesture identifying device and recognition methods, the device is made up of sensor unit, control module and controlled unit, wherein, the sensor unit includes a plurality of (sensors, the sensor is range sensor, and the range sensor is in array arrangement.The present invention goes to seek the non-contact gesture identifying system application of low cost using Distance-sensing, so, on the one hand meets low cost, the requirement of low-power consumption；On the other hand some simple non-contact gesture interactions can be realized, can be met completely under common simple interaction scenarios.
Description
Technical field
The invention belongs to technical field of hand gesture recognition, more particularly to a kind of contactless gesture identifying device and identification side
Method.
Background technology
In computer science, gesture identification is the technology that human gesture is recognized by mathematical algorithm.Gesture is known
The motion of the parts of body of people is not can come from, but generally refers to the motion of face and hand.It is generally used for smart mobile phone and intelligence
In energy glasses, panel computer.
Current Non-contact gesture identification technology is broadly divided into following three class:
1) the two-dimensional static hand-type identification based on mode-matching technique.This mode is mainly to be come by mode identification technology
Realize.
2) the two-dimentional Gesture Recognition based on microcomputerized visual algorithm.This mode is mainly by the picture processing of microcomputer
Technology.
3) the three-dimension gesture identification technology based on stronger computer vision algorithms make.This mode is relied primarily at picture
The technologies such as reason, computer vision algorithms make, machine learning.
Although the above method is in actual applications than wide, due to being currently based on the hardware requirement of picture Processing Technique
It is higher, the factor such as sensor costliness, it is difficult to promote in many low cost application scenarios.
As patent application 201510796509.6 discloses a kind of gesture identification for virtual reality display output equipment
Method and virtual reality display output equipment, recognition methods include：The first video is obtained from the first camera, from second camera
Obtain the second video；On the first plane information of hand figure in the first video first is isolated from first video flat
Face gesture, isolates the second plane hand on the second plane information of hand figure in the second video from second video
Gesture；First plane information and second plane information are converted to by spatial information, generation bag using binocular imaging mode
Include the space gesture of the spatial information；Obtain the corresponding execute instruction of the space gesture；Perform the execute instruction.The Shen
The identification of three-dimension gesture please be completed using common camera.
The content of the invention
Based on this, therefore primary mesh of the invention be to provide a kind of non-contact gesture identifying device and recognition methods,
The device and method goes to seek the non-contact gesture identifying system application of low cost by using Distance-sensing, so on the one hand
Meet low cost, the requirement of low-power consumption；On the other hand some simple non-contact gesture interactions can be realized, common
Can meet completely under simple interaction scenarios.
Be that a kind of non-contact gesture identifying device and recognition methods are provided another mesh of the invention, the device and
Method improves the other accuracy of non-contact gesture hand based on distance, stability and practicality, and realizes easy, low cost
It is honest and clean.
To achieve the above object, the technical scheme is that：
A kind of non-contact gesture identifying device, it is characterised in that the device is by sensor unit, control module and is controlled
Unit is constituted, wherein, the sensor unit includes a plurality of sensors, and the sensor is range sensor, and described
Range sensor is arranged in array.
Further, the vertically disposed range sensor of plural number row in the sensor unit, described often to arrange vertically disposed
The distance between range sensor is equal, and distance is D between adjacent two rows range sensor, the contrast of threshold values is carried out accordingly and is sentenced
It is disconnected.
The control module is made up of microcontroller and transmission command module, and microprocessor excitation range sensor is obtained and rung
After answering, read to obtain gesture command after response carries out relevant treatment, be sent out finally by command module is sent, by controlled single
Unit receives respective beacon, does respective response.
Based on this, non-contact gesture recognition methods of the invention is realized by above-mentioned gesture identifying device.The method
Including：
101st, set an activation threshold value (threshold values 1), the threshold value be with apart from the relevant physical quantity of size；Setting one
Individual secondary threshold (threshold values 2), the threshold value is used to abandon random disturbances；
102nd, the adjust the distance data-signal of sensor of microcontroller is changed, and obtains the distance number of each sensor
Value；
103rd, detect successively and by all range sensor range informations, if acquisition information meets activation threshold value requirement bar
Part, then it is assumed that be correct trigger signal, into Digital Signal Processing flow；
104th, according to given activation threshold value, valid data are gone out using threshold decision method preliminary screening, is deposited respectively, remembered
The corresponding data value of the last valid data, data value will subtract each other and then be contrasted with secondary threshold twice, if greater than
Secondary threshold values, then it is assumed that this data invalid, abandons invalid data, waits a new pen data to arrive, until confirming to meet two
The valid data of level threshold values；
105th, after obtaining valid data, the buffer that queue length is N is deposited into, queuing data is then obtained respectively
With lose one or more maximums and minimum value ask it to be averagely assigned to valid data again.So it is achieved that initial data
Processing, this step can further shield some random data；
106th, a distance threshold is set by user and is referred to as TH1 (threshold value 3), the position that the threshold value is used to embody data is special
Property；By the judgement to threshold value TH1, and definition status FLAG, GestureFlag, LeftCount, RightCount,
GestureDetc, the position and direction for carrying out opponent are accurately positioned, to judge left cunning, right cunning, left click and right click hand
Gesture.
The physical features such as distance, the time of gesture data that the method analysis is answered based on distance perspective, utilization state machine mode,
The multiple cross such as the directional characteristic according to data verify that raising is based on the other accuracy of non-contact gesture hand, the stabilization of distance
Property and practicality.
In the step 105, buffer has multiple, and the valid data for obtaining every time are stored in corresponding slow according to its position
Storage.
Further, it is X1 and X2 with two adjacent sensors data in the step 106, and X1 represents left sensor
Data, X2 represents the right sensing data；The judgement step of gesture is：
1061st, the new data group for obtaining, is respectively present in X1 and X2；
1062nd, X1 and X2 and threshold value TH1 are compared respectively, and will be greater than the value of the X1 or X2 of threshold value TH1 and be set to
New threshold value TH1；
Specifically, in step 1062, compare the size of X1 and threshold value TH1 (threshold value 3), next step then performed less than TH1,
More than or equal to the value of X1 then is set into TH1；
Compare the size of X2 and threshold value TH1, next step is then performed less than threshold value TH1, more than or equal to then setting the threshold value of X2
It is set to TH1；
1063rd, X1 and X2 is contrasted with new threshold values TH1 again, and is detected FLAG flag bits accordingly, judged gesture；
Further, in 1063 step, while judging whether that X1 is less than threshold value TH1, X2 is also equal to TH1；If X1 is small
X2 is equal to TH1 while threshold value TH1, then the value for going to detect whether FLAG flag bits again is RIGHT；If the value of FLAG is
RIGHT, then illustrate to detect left skating gesture, the value for resetting GestureFlag is LeftShift, and is set
GestureDetc is true, and this explanation is correctly detecting gesture.And gesture is responded herein to arrive action that this does, and is such as sent out
Control command is sent, terminates the refreshing of this data flow.
Further, in 1063 step, judge whether X1 less than TH1 and X2 is equal to TH1；If X1 less than TH1 and
X2 is equal to TH1, and the value of FLAG is LEFT, is not that then setting FLAG is LEFT, is then to set LeftCount from adding once, ties
Shu Benci data flows refresh.
Further, in 1063 step, rejudge whether X2 be less than threshold value TH1 while, X1 is also equal to TH1；Such as
X1 is equal to TH1 while fruit X2 is less than threshold value TH1, then detect whether that the value for meeting FLAG is LEFT, if true, then explanation inspection
Right skating gesture is measured, right sliding related command, end loop is performed.The RightCount++ if the value of FLAG is for RIGHT is that is, right
Variable is carried out from adding once, not for FLAG values are then set to RIGHT by RIGHT, terminates the refreshing of this data flow.
Further, in 1063 step, if it find that TH1 is more than X2 more than X1 and TH1, if very then
The value of LeftCount, RightCount is emptied, and FLAG values are set to NONE, and GestureDetc values are set to FALSE；
Otherwise continue flow, judge GestureDetc whether be it is true, it is then that the value of LeftCount, RightCount is clear if true
Sky, and FLAG values are set to NONE, GestureDetc values are set to FALSE；Otherwise continue to determine whether to meet
LeftCount is more than TH2 (threshold value of threshold value 4, i.e., the 4th), if it is satisfied, then explanation detects left click gesture, responds left click hand
Gesture relevant action, then terminates this Refresh Data.
Further, continue to determine whether to meet RightCount more than TH2；If very then explanation detects right click hand
Gesture, should perform related command here, then terminate this refreshing；The value of LeftCount, RightCount is emptied, and handle
FLAG values are set to NONE, and GestureDetc values are set to FALSE.
The threshold values 1, threshold values 2, threshold values 3, threshold values 4 can be according to the actual demand sets itselfs of user.
The present invention goes to seek the non-contact gesture identifying system application of low cost using Distance-sensing, so, on the one hand
Meet low cost, the requirement of low-power consumption；On the other hand some simple non-contact gesture interactions can be realized, common
Can meet completely under simple interaction scenarios.
The present invention realizes the definition and identification and application of the gestures such as left cunning, right cunning using a kind of new algorithm simultaneously.
Brief description of the drawings
Fig. 1 is the structural representation that the present invention is implemented.
Fig. 2 is the structural representation that the present invention implements sensor unit.
Fig. 3 is the specific configuration figure that the present invention implements a kind of sensor unit.
Fig. 4 is the schematic diagram that the present invention implements gesture judgement.
Fig. 5 is the control flow chart that the present invention is implemented.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
As shown in figure 1, be that the present invention realizes the structure chart of non-contact gesture identifying device, shown in figure, this is non-to connect
Touch gesture identifying device 100 is made up of sensor unit 101, control module 102 and control module 103.
Wherein, with reference to shown in Fig. 2, Fig. 3, sensor cell array formula arrangement, sensor unit has and 101 has sensor array
106 and sensor group 107 constitute.Distance is D (cm) between two neighboring sensing.
Control module 102 is made up of microcontroller 104 and transmission command module 105.Microprocessor encourages range sensor
Obtain after response, read to obtain gesture command after response carries out relevant treatment, finally by transmission command module 105 to outgoing
Send, respective beacon is received by controlled module, do respective response.
For the ease of statement, only the detection of an analysis two of which adjacent ultrasonic wave sensor gets data herein, three and its
More than can be by that analogy.So for this possesses three arrays of ultrasonic device, we firstly the need of immobilising device,
Closely easily cause space tracking factor for disturbing and considering gesture motion etc. very much due to what two ultrasonic sensors were leaned on.Make
It is reference, the distance between two neighboring sensor is set to D cm.As shown in Figure 2 and Figure 3.Architectural characteristic determines collection
Some position characteristics for the range data for arriving.
As Fig. 4 shows.When two sensor tops are mobile therefrom for hand, in fact, for relative certain reference point.Distance
D1 and d2 are changes simultaneously.And after selected reference point, 2 points of change dependences can be derived mutually.
Its data is represented with X1 and X2 respectively.Work as X1>=TH0 (threshold value 1) and X2>During=TH0, significant figure is just considered
According to.Here preliminary screening goes out valid data, is stored in X1 and X2 respectively.Remember last time X1 and X2 value be respectively X1 ' and
X2 ', if X1-X1 '>TH0 ' (threshold value 2) or X2-X2 '>TH0 ', then it is assumed that this data invalid.Invalid data is abandoned, etc.
Treat that a new pen data arrives.
After obtaining X1 and X2, it is assumed that it is the buffer Q1 and Q2 of N to set queue length, each data X1 and X2 will
It falls in lines respectively.One or more maximums and minimum value in queue are abandoned, the sum of queuing data is then obtained respectively, ask it
Averagely X1 and X2 is assigned to again.So it is achieved that further anti-random disturbances filtering process.
As Fig. 5 shows, the identification of gesture is realized by following steps.This is the core algorithm flow of this method.With two
Adjacent sensors data are X1 and X2, and X1 represents left sensor data, and X2 represents the right sensing data.
201st, the new data group for obtaining, is respectively present in X1 and X2.
202nd, compare the size of X1 and threshold value TH1 (threshold value 3), step 204 is then jumped to less than TH1.
203rd, installing for X1 is set to TH1.This is equivalent to the value for having reset X1.
204th, compare the size of X2 and threshold value TH1, step 206 is then jumped to less than threshold value TH1.
205th, the threshold value of X2 is set to TH1.This is equivalent to the value for having reset X2.
206th, while judging whether that X1 is less than threshold value TH1, X2 is also equal to TH1；If X2 while X1 is less than threshold value TH1
Equal to TH1, step 208 is otherwise skipped to, then the value for going to detect whether FLAG flag bits again is RIGHT.If the value of FLAG is
RIGHT, then illustrate to detect left skating gesture, the value for resetting GestureFlag is LeftShift.And set
GestureDetc is true, and this explanation is correctly detecting gesture.And gesture is responded herein to arrive action that this does, and is such as sent out
Control command is sent, terminates the refreshing of this data flow.
207th, judge whether X1 less than TH1 and X2 is equal to TH1.If X1 is equal to the value of TH1 and FLAG less than TH1 and X2
It is LEFT, is not that FLAG is then set for LEFT, be that LeftCount is then set from adding once, terminates the refreshing of this data flow.Otherwise
Skip to step 208.
208th, rejudge whether X2 be less than threshold value TH1 while, X1 is also equal to TH1；If X2 is same less than threshold value TH1
When X1 be equal to TH1, otherwise skip to step 213.It is to detect whether that the value for meeting FLAG is RIGHT, if true, illustrates detection
Right skating gesture is arrived, corresponding right sliding order has been performed, has terminated this circulation.If the value of FLAG is RIGHT, RightCount+
+, i.e., variable is carried out adding once certainly.FLAG values are otherwise set to RIGHT.Terminate the refreshing of this data flow.
209th, this explanation detects right skating gesture, and the value for now needing to put GestureFlag is RightShift, and will
GestureDetc traffic sign placements are True and then the value of FLAG are set into NONE.The treatment of right skating gesture should now be ordered
Or code is placed on this and sentences and facilitates real-time response to act.Then this Refresh Data is terminated.
210th, continue to judge, if it find that TH1 is more than X1 and TH1 is more than X2.If very then going to step 213.It is no
Then continue flow.
211st, now need to judge whether GestureDetc is true, step 13 is then gone to if true.Otherwise continue to judge
Whether LeftCount is met more than TH2 (threshold value 4).If it is satisfied, then explanation detects left click gesture, response is needed exist for left
Hitter's gesture relevant action.Then this Refresh Data is terminated.Otherwise continue flow.
212nd, continue to determine whether to meet RightCount more than TH2.If very then explanation detects right click gesture, this
In should perform related command.Then this refreshing is terminated.Go to step 213.
213rd, the value of LeftCount, RightCount is emptied, and FLAG values is set to NONE, GestureDetc
Value is set to FALSE.
In order to improve the accuracy and more gestures of gesture identification.This algorithm applies also for multiple range sensor arrays
Situation.For multiple sensor arrays, only it need to two-by-two be processed.
The present invention goes to seek the non-contact gesture identifying system application of low cost using Distance-sensing, so, on the one hand
Meet low cost, the requirement of low-power consumption；On the other hand some simple non-contact gesture interactions can be realized, common
Can meet completely under simple interaction scenarios.
Presently preferred embodiments of the present invention is the foregoing is only, is not intended to limit the invention, it is all in essence of the invention
Any modification, equivalent and improvement made within god and principle etc., should be included within the scope of the present invention.
Claims (10)
1. a kind of non-contact gesture identifying device, it is characterised in that the device is by sensor unit, control module and controlled single
Unit's composition, wherein, the sensor unit includes a plurality of sensors, and the sensor is range sensor, and it is described away from
Arranged in array from sensor.
2. non-contact gesture identifying device as claimed in claim 1, it is characterised in that plural number row in the sensor unit
Vertically disposed range sensor, the distance between the vertically disposed range sensor of often arranging is equal, adjacent two array pitch from
Distance is D between sensor, and the contrast and judgement of threshold values are carried out accordingly.
3. non-contact gesture identifying device as claimed in claim 1, it is characterised in that the control module is by microcontroller
Constituted with command module is sent, microprocessor excitation range sensor is obtained after response, read to be obtained after response carries out relevant treatment
To gesture command, order is sent out finally by command module is sent, respective beacon is received by controlled unit, do corresponding sound
Should.
4. a kind of non-contact gesture recognition methods, it is characterised in that the method includes：
101st, set an activation threshold value, the threshold value be with apart from the relevant physical quantity of size；One secondary threshold of setting,
The threshold value is used to abandon random disturbances；
102nd, the adjust the distance data-signal of sensor of microcontroller is changed, and obtains the distance values of each sensor；
103rd, detect successively and by all range sensor range informations, if acquisition information meets activation threshold value requirement condition,
Correct trigger signal is considered, into Digital Signal Processing flow；
104th, according to given activation threshold value, valid data are gone out using threshold decision method preliminary screening, is deposited respectively, memory upper
The corresponding data value of the secondary valid data, data value will subtract each other and then be contrasted with secondary threshold, if greater than secondary twice
Threshold values, then it is assumed that this data invalid, abandons invalid data, waits a new pen data to arrive, until confirmation meets secondary valve
The valid data of value；
105th, after obtaining valid data, the buffer that queue length is N is deposited into, the sum of queuing data is then obtained respectively,
Lose one or more maximums and minimum value asks it to be averagely assigned to valid data again.So it is achieved that adding for initial data
Work, this step can further shield some random data；
106th, a distance threshold is set by user and is referred to as TH1, the threshold value is used to embody the position characteristic of data；By to threshold value
The judgement of TH1, and definition status FLAG, GestureFlag, LeftCount, RightCount, GestureDetc, carry out opponent
Position and direction accurately positioned, to judge left cunning, right cunning, left click and right click gesture.
5. non-contact gesture recognition methods as claimed in claim 4, it is characterised in that in the step 106, with two phases
As a example by adjacent sensing data is X1 and X2, and X1 represents left sensor data, X2 represents on the right of sensing data；Gesture is sentenced
Disconnected step is：
1061st, the new data group for obtaining, is respectively present in X1 and X2；
1062nd, X1 and X2 and threshold value TH1 are compared respectively, and will be greater than the value of the X1 or X2 of threshold value TH1 and be set to new threshold
Value TH1；
1063rd, X1 and X2 is contrasted with new threshold values TH1 again, and is detected FLAG flag bits accordingly, judged gesture.
6. non-contact gesture recognition methods as claimed in claim 5, it is characterised in that in step 1062, compare X1 and threshold value
The size of TH1 (threshold value 3), next step is then performed less than TH1, more than or equal to the value of X1 then is set into TH1；
Compare the size of X2 and threshold value TH1, next step is then performed less than threshold value TH1, more than or equal to being then set to the threshold value of X2
TH1。
7. non-contact gesture recognition methods as claimed in claim 6, it is characterised in that in 1063 step, judge whether X1
While less than threshold value TH1, X2 is also equal to TH1；If X2 is equal to TH1 while X1 is less than threshold value TH1, then go the detection to be again
The value of no FLAG flag bits is RIGHT；If the value of FLAG is RIGHT, then illustrate to detect left skating gesture, reset
The value of GestureFlag is LeftShift, and sets GestureDetc for true, and this explanation is correctly detecting gesture.And
And gesture is responded herein arrive the action that this does, control command is such as sent, terminate the refreshing of this data flow.
8. non-contact gesture recognition methods as claimed in claim 7, it is characterised in that in 1063 step, rejudging is
While no X2 is less than threshold value TH1, X1 is also equal to TH1；If X1 is equal to TH1 while X2 is less than threshold value TH1, detect whether
The value of FLAG is met for LEFT, if true, then illustrates to detect right skating gesture, perform related command, terminate flow；If
The value of FLAG is LEFT then RightCount++, i.e., variable is carried out, from adding once, FLAG values otherwise being set into RIGHT, is terminated
This data flow refreshes.
9. non-contact gesture recognition methods as claimed in claim 8, it is characterised in that in 1063 step, if it find that
TH1 is more than X2 more than X1 and TH1, if very then emptying the value of LeftCount, RightCount, and FLAG values is set
NONE is set to, GestureDetc values are set to FALSE；Otherwise continue flow, judge whether GestureDetc is true, if
For true then empties the value of LeftCount, RightCount, and FLAG values are set to NONE, GestureDetc values are set
It is set to FALSE；Otherwise continue to determine whether to meet LeftCount more than TH2, if it is satisfied, then explanation detects left click gesture,
Response left click gesture relevant action, then terminates this Refresh Data.
10. non-contact gesture recognition methods as claimed in claim 9, it is characterised in that continue to determine whether to meet
RightCount is more than TH2；If very then explanation detects right click gesture, related command should be performed here, then terminate
This refreshes；The value of LeftCount, RightCount is emptied, and FLAG values are set to NONE, GestureDetc values
It is set to FALSE.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611158133.7A CN106774887A (en) | 2016-12-15 | 2016-12-15 | A kind of non-contact gesture identifying device and recognition methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611158133.7A CN106774887A (en) | 2016-12-15 | 2016-12-15 | A kind of non-contact gesture identifying device and recognition methods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106774887A true CN106774887A (en) | 2017-05-31 |
Family
ID=58888302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611158133.7A Pending CN106774887A (en) | 2016-12-15 | 2016-12-15 | A kind of non-contact gesture identifying device and recognition methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106774887A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107131823A (en) * | 2017-06-03 | 2017-09-05 | 芯海科技（深圳）股份有限公司 | A kind of piezoresistive transducer mobile terminal calibrating installation and method |
| CN108549480A (en) * | 2018-03-28 | 2018-09-18 | 北京经纬恒润科技有限公司 | A kind of triggering judgment method and device based on multi-channel data |
| CN109508124A (en) * | 2018-11-13 | 2019-03-22 | 苏州大学 | Versatility non-contact gesture identification device based on metal surface |
| CN109539354A (en) * | 2018-12-28 | 2019-03-29 | 九阳股份有限公司 | A kind of gesture identification control method identifying accurate range hood and range hood |
| CN109710116A (en) * | 2018-08-23 | 2019-05-03 | 华东师范大学 | A kind of non-contact gesture state recognition system and recognition methods |
| CN112363613A (en) * | 2020-09-25 | 2021-02-12 | 惠州市德赛西威汽车电子股份有限公司 | Infrared sliding gesture induction recognition method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6094188A (en) * | 1990-11-30 | 2000-07-25 | Sun Microsystems, Inc. | Radio frequency tracking system |
| CN102339154A (en) * | 2010-07-16 | 2012-02-01 | 谊达光电科技股份有限公司 | Gesture detection method for proximity induction |
| CN102410846A (en) * | 2010-08-04 | 2012-04-11 | St微电子(鲁塞)有限公司 | A method of detecting an object with a proximity sensor |
| CN103543834A (en) * | 2013-11-05 | 2014-01-29 | 上海电机学院 | Gesture recognition device and method |
| CN204028810U (en) * | 2014-07-07 | 2014-12-17 | 长沙维汉信息科技有限公司 | A kind of vehicle-carrying music player of Non-contact gesture manipulation |
| CN104391578A (en) * | 2014-12-05 | 2015-03-04 | 重庆蓝岸通讯技术有限公司 | Real-time gesture control method of three-dimensional images |
| CN105094298A (en) * | 2014-05-13 | 2015-11-25 | 华为技术有限公司 | Terminal and terminal based gesture recognition method |
| US20160357260A1 (en) * | 2015-06-03 | 2016-12-08 | Stmicroelectronics (Research & Development) Limited | Distance independent gesture detection |
-
2016
- 2016-12-15 CN CN201611158133.7A patent/CN106774887A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6094188A (en) * | 1990-11-30 | 2000-07-25 | Sun Microsystems, Inc. | Radio frequency tracking system |
| CN102339154A (en) * | 2010-07-16 | 2012-02-01 | 谊达光电科技股份有限公司 | Gesture detection method for proximity induction |
| CN102410846A (en) * | 2010-08-04 | 2012-04-11 | St微电子(鲁塞)有限公司 | A method of detecting an object with a proximity sensor |
| CN103543834A (en) * | 2013-11-05 | 2014-01-29 | 上海电机学院 | Gesture recognition device and method |
| CN105094298A (en) * | 2014-05-13 | 2015-11-25 | 华为技术有限公司 | Terminal and terminal based gesture recognition method |
| CN204028810U (en) * | 2014-07-07 | 2014-12-17 | 长沙维汉信息科技有限公司 | A kind of vehicle-carrying music player of Non-contact gesture manipulation |
| CN104391578A (en) * | 2014-12-05 | 2015-03-04 | 重庆蓝岸通讯技术有限公司 | Real-time gesture control method of three-dimensional images |
| US20160357260A1 (en) * | 2015-06-03 | 2016-12-08 | Stmicroelectronics (Research & Development) Limited | Distance independent gesture detection |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107131823A (en) * | 2017-06-03 | 2017-09-05 | 芯海科技（深圳）股份有限公司 | A kind of piezoresistive transducer mobile terminal calibrating installation and method |
| CN108549480A (en) * | 2018-03-28 | 2018-09-18 | 北京经纬恒润科技有限公司 | A kind of triggering judgment method and device based on multi-channel data |
| CN109710116A (en) * | 2018-08-23 | 2019-05-03 | 华东师范大学 | A kind of non-contact gesture state recognition system and recognition methods |
| CN109710116B (en) * | 2018-08-23 | 2021-12-07 | 华东师范大学 | Non-contact gesture state recognition system and recognition method |
| CN109508124A (en) * | 2018-11-13 | 2019-03-22 | 苏州大学 | Versatility non-contact gesture identification device based on metal surface |
| CN109539354A (en) * | 2018-12-28 | 2019-03-29 | 九阳股份有限公司 | A kind of gesture identification control method identifying accurate range hood and range hood |
| CN112363613A (en) * | 2020-09-25 | 2021-02-12 | 惠州市德赛西威汽车电子股份有限公司 | Infrared sliding gesture induction recognition method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106774887A (en) | A kind of non-contact gesture identifying device and recognition methods | |
| CN105893827B (en) | A kind of applicative notifications message inspection method and terminal | |
| Fukunari et al. | An efficient cycle time model for autonomous vehicle storage and retrieval systems | |
| EP3514724B1 (en) | Depth map-based heuristic finger detection method | |
| CN103109244B (en) | For object tracking and the method and apparatus of identification | |
| CN107486863B (en) | Robot active interaction method based on perception | |
| CN106650688A (en) | Eye feature detection method, device and recognition system based on convolutional neural network | |
| CN100550039C (en) | A kind of image characteristic points positioning method and device | |
| CN106104434A (en) | Touch panel device is used to determine user's handedness and orientation | |
| Sung et al. | Data fusion of multi-sensor for IOT precise measurement based on improved PSO algorithms | |
| JP6178506B2 (en) | Information processing system and information processing method | |
| CN109345553A (en) | A kind of palm and its critical point detection method, apparatus and terminal device | |
| CN107545252A (en) | Face identification method and device in video based on multi-pose Face model | |
| CN110348412A (en) | A kind of key independent positioning method, device, electronic equipment and storage medium | |
| CN109664309A (en) | A kind of clean method, apparatus of intelligent robot and robot | |
| CN108205646A (en) | A kind of hand gestures detection method and device | |
| CN108898612A (en) | Multi-object tracking method based on the enhancing study of multiple agent depth | |
| CN105278846B (en) | Control the method and its mobile terminal in mobile terminal screen direction | |
| CN110274607A (en) | Intelligent paths planning method, device and computer readable storage medium | |
| CN102364419B (en) | Camera type touch control method and system thereof | |
| WO2012059595A1 (en) | Touch detection | |
| CN103049747A (en) | Method for re-identifying human body images by utilization skin color | |
| CN104766100A (en) | Infrared small target image background predicting method and device based on machine learning | |
| Tong et al. | A fine-grained channel state information-based deep learning system for dynamic gesture recognition | |
| CN113591629A (en) | Finger three-mode fusion recognition method, system, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |