CN104142730B - A kind of method that gesture tracking result is mapped to mouse event - Google Patents
A kind of method that gesture tracking result is mapped to mouse event Download PDFInfo
- Publication number
- CN104142730B CN104142730B CN201410318600.2A CN201410318600A CN104142730B CN 104142730 B CN104142730 B CN 104142730B CN 201410318600 A CN201410318600 A CN 201410318600A CN 104142730 B CN104142730 B CN 104142730B
- Authority
- CN
- China
- Prior art keywords
- mouse
- mapped
- tracking result
- mapping
- algorithm
- 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.)
- Active
Links
Landscapes
- Image Analysis (AREA)
- Position Input By Displaying (AREA)
Abstract
The present invention discloses a kind of method that gesture tracking result is mapped to mouse event, and the gesture tracking result of physical space is mapped into the movement of mouse, realizes the accurate smooth control to mouse in operating system.The method comprises the following steps：(1) arithmetic speed to the track algorithm under different use platforms carries out Time alignment；(2) according to people with camera apart from self adaptation apart from regular；(3) threshold value and parameter setting；(4) shake is distinguished to tracking result and moves slowly at situation；(5) being mapped the staff in image by mapping function turns into mouse event；(6) rate smoothing treatment is carried out to mouse movement process；(7) the mouse point of two frames mapping is filled up by the way of interframe interpolation, interpolation is shown.The present invention is not only restricted to track algorithm, tracking result effectively can be mapped as into mouse event, and the algorithm bad for tracking effect, can repair final mapping result by mouse event, improves algorithm availability in practice.
Description
Technical field
The present invention relates to computer vision tracking and field of human-computer interaction, and in particular to a kind of hand based on computer vision
Gesture tracking is mapped to mouse calibration method.
Background technology
With the development of computer vision technique, gesture identification and tracking technique are increasingly mature, and its Related product is also gradually
Industrialization is moved towards from scientific research, society is come into as actual property commodity.Human-computer interaction technology is by based on computer vision
The key that gesture identification and tracking technique are contacted with machine.Staff is carried out by certain mapping algorithm to the cursor in computer
Manipulation, realizes movement and the control to operating system that light is marked in operation interface.
2D gesture tracking algorithms of today still suffer from certain limitation, due to the presence of noise during tracking, with
Track result is inevitably generated different degrees of shake, meanwhile, in interaction, the friendly and comfort level of user mutual
Also the key factor that interactive map algorithm considers is turned into.Therefore, to the applicability of generic gesture track algorithm, algorithm is improved
Robustness is accustomed to as mapping algorithm development trend in human-computer interaction technology with mankind's natural interaction is met.
The content of the invention
Of the invention aiming at overcomes the shortcomings of that existing gesture mapping cursor algorithm exists in actual applications, there is provided
A kind of method that natural, harmonious, efficient gesture tracking result is mapped to mouse event, concrete technical scheme is as follows.
A kind of method that gesture tracking result is mapped to mouse event, comprises the following steps：
Time alignment is carried out to current gesture tracking algorithm；
Row distance is entered to the tracking result of current gesture tracking algorithm regular；
Distinguish shake and move slowly at situation；
Hand tracking result is mapped as mouse event；
Smoothing processing is done to Mouse Scroll；
Fill up the mouse point of two frames mapping.
It is described Time alignment is carried out to current gesture tracking algorithm to be specifically wherein in one embodiment：To gesture with
Track result is multiplied by a coefficient compared with standard testing platform inter frame temporal so that the same speed of staff in physical world
Same Mouse Scroll can be mapped as in different interframe process times.
Wherein in one embodiment, the tracking result to current gesture tracking algorithm enters the regular specific bag of row distance
Include following steps：A () utilizes
The size of tracking box in tracking result, calculates the distance between staff and camera；
B () is adaptively adjusted the human hand movement speed calculated in drawing.
Wherein in one embodiment, the differentiation is shaken and moves slowly at situation and specifically includes following steps：
A () accumulated history trace point is obtained to average filter point；
B () compares current trace point with this filtering point, differentiation is moved slowly at and shaken；
C () shielding shake, amplification is moved slowly at.
Wherein in one embodiment, the specific mapping scheme bag that hand tracking result is mapped to mouse event
Include：Using piecewise function, will be regular after the different mapping multiplying powers of human hand movement speed correspondence.
It is described smoothing processing is done to Mouse Scroll to specifically include wherein in one embodiment：To the mouse of current mapping
The Mouse Scroll that speed is obtained with former frame does weighted sum, it is to avoid the display speed of mouse is being interacted visually during tracking
Undergo mutation.
Wherein in one embodiment, it is described fill up two frames mapping mouse point be specifically：In two frame algorithm process times
It is interior filled up by the way of interframe linear interpolation two frames mapping mouse point, insert mouse point number regarding specific algorithm process when
Between depending on, so as to avoid some algorithm process time it is long cause mouse beat situation.
Further optimize, the above method also includes：According to the movement tendency of user, the transverse and longitudinal mapping rail of the mouse that standardizes
Mark.
A kind of gesture tracking result of the present invention is mapped to the method for mouse event compared with prior art, has the following advantages that
And technique effect：
(1) inventive algorithm complexity is low, and the resource for consuming in actual applications is few.
(2) present invention is not only restricted to specific track algorithm, with universality.
(3) present invention can overcome the disadvantages that track algorithm deficiency in itself to a certain extent, improve track algorithm in practice
Robustness.
(4) present invention can be provided the user and naturally interact body-sensing with computer, and operation sense is strong.
Brief description of the drawings
Fig. 1 is the method flow diagram that gesture tracking result of the present invention is mapped to mouse event.
Fig. 2 is the imaging schematic diagram that different user uses distance.
Fig. 3 is motion state classification chart.
Fig. 4 is mapping function of the present invention.
Fig. 5 is the present invention comparative result figure apart from mapping method conventional with one of them.
Specific embodiment
Specific implementation method of the invention is described further below in conjunction with accompanying drawing, but implementation of the invention and protection are not
It is limited to this, needs specification, below every not specified symbol, step or process, is that those skilled in the art can
Realized with reference to prior art.
As shown in figure 1, the method that gesture tracking result of the present invention is mapped to mouse event includes following flow.
(1) Time alignment is carried out to current gesture tracking algorithm, one is multiplied by gesture tracking result and is put down with standard testing
The coefficient that platform inter frame temporal compares so that the same speed of staff can in different interframe process times in physical world
Same Mouse Scroll is mapped as, Time alignment method is as follows：
2 Euclidean distances (pixel count) d/ inter frame temporals t (ms) of gesture speed v=interframe
It is T ms that algorithm integrally takes in standard testing platform, determines mapping range steady, v1, v2, is selected at this
More excellent test parameter in test platform.When being run under other platforms, these parameters are processed by Time alignment so that thing
The same speed of staff can be mapped as same cursor speed in different interframe process times in the reason world.Implementation
To be multiplied by a coefficient compared with standard testing platform inter frame temporal.
(2) done apart from regular, using the big of tracking box in tracking result (204,205) with the distance of camera according to user
It is small, as shown in Fig. 2 the distance between staff area S and staff 201 and different distance camera 203 L is calculated, it is flat in test
Standard staff area S on platformstandard(mapping is corresponding when more excellent), staff 201 and the normal pitch demarcated between camera 202
From LstandardThe zoom factor F for obtaining the human hand movement speed that current algorithm is calculated is compared, it is adaptive using zoom factor
Answer the human hand movement speed calculated in ground adjustment drawing.
(3) distinguish shake and move slowly at situation, Fig. 3 includes jitter points 302 and moves slowly at a little 303, by adding up
25 trace points of history are averaged and obtain medium filtering point 301, and current trace point is compared with this filtering point, rather than
Compare with the point of previous frame.So as to reduce shake 304, amplification moves slowly at 305, as shown in Figure 3.
(4) hand tracking result is mapped to the mapping scheme of mouse event, using piecewise function, will be regular after staff
The different mapping multiplying power of movement velocity correspondence.Mapping scheme of the present invention is as shown in Figure 4.Transverse axis is algorithm keeps track in figure
The movement velocity of the staff for obtaining, the longitudinal axis is mapping multiplying power (movement velocity of the multiplying power k=Mouse Scroll/staff to be mapped).
Different threshold speed v1, v2, the v3 of setting, mapping function is piecewise nonlinear function, including exponential function, logarithmic function, its
The value of middle α is needed according to the actual mapping multiplying power to be reached adjustment.
(5) in order to reduce the mutation that tracking of the algorithm to staff is likely to result in speed, the present invention does flat to Mouse Scroll
Sliding treatment, does weighted sum, it is to avoid mouse during tracking to the Mouse Scroll that the Mouse Scroll of current mapping is obtained with former frame
Target display speed is visually undergone mutation in interaction, and formula is as follows：
Mapping speed+0.5* the present frames of the speed of mapping=0.5* previous frames do not have the mapping speed before filtering
(6) the mouse point of two frames mapping is filled up by the way of interframe linear interpolation within two frame algorithm process times, is inserted
Enter the number of mouse point depending on specific algorithm process time, some algorithm process time is long to cause mouse to be beated so as to avoid
Situation.
Hereinafter only it is only for example：Use in specific track algorithm, mesh is made with average drifting (mean shift) algorithm
As a example by mark track algorithm, using hand as tracking target, by mapping method of the invention and the distance phase for more commonly using at present
The tracking result being respectively acting on to mapping method, realizes that gesture roaming is mapped as the function of mouse movement.In order to effective ratio compared with
Two kinds of mapping methods, using same section of test video as input, the hand of user is at the uniform velocity laterally roamed in video.It is extracted in respectively
Absolute displacement of the mouse on screen, depicts in same coordinate system under two kinds of mapping methods, as shown in figure 5, solid line
It is the mapping result of method proposed by the invention, dotted line is the mapping result for tracking Relative Maps method, calculates two kinds of mapping sides
Method variance on the y axis can be obtained, and the conventional variance apart from mapping method is approximately equal to 21.9447, and variance of the invention is about
11.9944.It can thus be seen that mapping method of the invention is relatively stable, Path balance is shaken smaller.
Specific embodiment of the invention is these are only, protection scope of the present invention is not limited with this；Do not violating this hair
Any replacement made on the basis of bright design and improvement, belong to protection scope of the present invention.
Claims (6)
1. a kind of method that gesture tracking result is mapped to mouse event, it is characterised in that comprise the following steps：
（1）Time alignment is carried out to current gesture tracking algorithm；It is described that to carry out Time alignment to current gesture tracking algorithm specific
It is：A coefficient compared with standard testing platform inter frame temporal is multiplied by gesture tracking result so that people in physical world
The same speed of hand can be mapped as same Mouse Scroll in different interframe process times；
（2）Row distance is entered to the tracking result of current gesture tracking algorithm regular；It is described to be specifically apart from regular：According to user with
The distance of camera is done apart from regular, using the size of tracking box in tracking result, calculates the distance between staff and camera,
It is adaptively adjusted the human hand movement speed calculated in picture；
（3）Distinguish shake and move slowly at situation；
（4）Hand tracking result is mapped as mouse event；
（5）Smoothing processing is done to Mouse Scroll；
（6）Fill up the mouse point of two frames mapping.
2. the method that a kind of gesture tracking result as claimed in claim 1 is mapped to mouse event, it is characterised in that the area
Divide shake and move slowly at situation and be specifically：Accumulated history trace point obtains average filter point, by current trace point and this
Filter point to compare, differentiation is moved slowly at and shaken, and shields shake, and amplification is moved slowly at.
3. the method that a kind of gesture tracking result as claimed in claim 1 is mapped to mouse event, it is characterised in that step（4）
Using piecewise function, will be regular after the different mapping multiplying powers of human hand movement speed correspondence.
4. the method that a kind of gesture tracking result as claimed in claim 1 is mapped to mouse event, it is characterised in that step（5）
In, weighted sum is done to the Mouse Scroll that the Mouse Scroll of current mapping is obtained with former frame, it is to avoid mouse during tracking
Display speed is visually undergone mutation in interaction.
5. the method that a kind of gesture tracking result as claimed in claim 1 is mapped to mouse event, it is characterised in that step（6）
The mouse point of two frames mapping is filled up by the way of interframe linear interpolation within two frame algorithm process times, the individual of mouse point is inserted
It is several the process time of specific gesture tracking algorithm to be determined according to the efficiency of chip or the hardware condition of computer, so as to keep away
Exempt from the long situation for causing mouse to be beated of some algorithm process time.
6. the method that a kind of gesture tracking result as claimed in claim 1 is mapped to mouse event, it is characterised in that according to
The movement tendency at family, the transverse and longitudinal mapping trajectories of the mouse that standardizes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410318600.2A CN104142730B (en) | 2014-07-04 | 2014-07-04 | A kind of method that gesture tracking result is mapped to mouse event |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410318600.2A CN104142730B (en) | 2014-07-04 | 2014-07-04 | A kind of method that gesture tracking result is mapped to mouse event |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104142730A CN104142730A (en) | 2014-11-12 |
| CN104142730B true CN104142730B (en) | 2017-06-06 |
Family
ID=51851932
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410318600.2A Active CN104142730B (en) | 2014-07-04 | 2014-07-04 | A kind of method that gesture tracking result is mapped to mouse event |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104142730B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104793744A (en) * | 2015-04-16 | 2015-07-22 | 天脉聚源(北京)传媒科技有限公司 | Gesture operation method and device |
| CN111330243A (en) * | 2018-12-18 | 2020-06-26 | 上海赢赞数字科技有限公司 | Rock climbing wall somatosensory interaction method, control system and interaction system |
| CN112394811B (en) | 2019-08-19 | 2023-12-08 | 华为技术有限公司 | Interaction method of air-separation gestures and electronic equipment |
| CN112671972A (en) * | 2020-12-21 | 2021-04-16 | 四川长虹电器股份有限公司 | Method for controlling movement of large-screen television mouse by mobile phone |
| CN114840126B (en) * | 2022-05-23 | 2024-01-23 | 北京字跳网络技术有限公司 | Object control method, device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102707802A (en) * | 2012-05-09 | 2012-10-03 | 华南理工大学 | Method for controlling speed of mapping of gesture movement to interface |
| CN103324281A (en) * | 2013-04-18 | 2013-09-25 | 苏州易乐展示系统工程有限公司 | Filtering method of non-contact interactive display system |
| CN103324277A (en) * | 2012-03-22 | 2013-09-25 | 扬州永利宁科技有限公司 | Touch free user input recognition |
| CN103400118A (en) * | 2013-07-30 | 2013-11-20 | 华南理工大学 | Gesture control method capable of adaptively adjusting mapping relation |
| CN103488294A (en) * | 2013-09-12 | 2014-01-01 | 华南理工大学 | Non-contact gesture control mapping adjustment method based on user interactive habits |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9448633B2 (en) * | 2011-10-01 | 2016-09-20 | Oracle International Corporation | Moving a display object within a display frame using a discrete gesture |
-
2014
- 2014-07-04 CN CN201410318600.2A patent/CN104142730B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103324277A (en) * | 2012-03-22 | 2013-09-25 | 扬州永利宁科技有限公司 | Touch free user input recognition |
| CN102707802A (en) * | 2012-05-09 | 2012-10-03 | 华南理工大学 | Method for controlling speed of mapping of gesture movement to interface |
| CN103324281A (en) * | 2013-04-18 | 2013-09-25 | 苏州易乐展示系统工程有限公司 | Filtering method of non-contact interactive display system |
| CN103400118A (en) * | 2013-07-30 | 2013-11-20 | 华南理工大学 | Gesture control method capable of adaptively adjusting mapping relation |
| CN103488294A (en) * | 2013-09-12 | 2014-01-01 | 华南理工大学 | Non-contact gesture control mapping adjustment method based on user interactive habits |
Non-Patent Citations (1)
| Title |
|---|
| A survey of 3D object selection techniques for virtual environments;Argelaguet F Andujar C;《Computers & Graphics》;20131230;第27卷(第2013期);第121-136页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104142730A (en) | 2014-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104142730B (en) | A kind of method that gesture tracking result is mapped to mouse event | |
| CN109711304B (en) | Face feature point positioning method and device | |
| KR101830804B1 (en) | Digital image stabilization method with adaptive filtering | |
| US9218653B2 (en) | Method and apparatus for dynamic range enhancement of an image | |
| US12125173B2 (en) | Video denoising method and device, and computer readable storage medium | |
| US20090022396A1 (en) | Image processing device, image processing method, image processing system, program, storage medium, and integrated circuit | |
| WO2021189173A1 (en) | Methods and systems for hand gesture-based control of a device | |
| US9961321B2 (en) | Image processing device and image processing method having function for reconstructing multi-aspect images, and recording medium | |
| WO2017058362A1 (en) | Systems and methods for performing automatic zoom | |
| CN105611116B (en) | A kind of global motion vector method of estimation and monitor video digital image stabilization method and device | |
| CN104980626A (en) | Method And Apparatus For Reducing Noise Of Image | |
| WO2016107962A1 (en) | Improving focus in image and video capture using depth maps | |
| CN101877130A (en) | Moving target tracking method based on particle filter under complex scene | |
| JP5014274B2 (en) | Image processing apparatus, image processing method, image processing system, program, recording medium, and integrated circuit | |
| KR20150146045A (en) | Apparatus and method for image defogging | |
| CN105574817A (en) | Image anti-aliasing method and apparatus | |
| KR20160103902A (en) | Image processing apparatus, image processing method, and image processing program | |
| TWI465984B (en) | Method and control apparatus for determining control output in control domain | |
| CN109859138B (en) | Infrared image enhancement method based on human visual characteristics | |
| WO2021184356A1 (en) | Methods and systems for hand gesture-based control of a device | |
| EP3313077A1 (en) | A method and apparatus for controlling a degree of compression of a digital image | |
| TW201435807A (en) | Method, apparatus, and non-transitory computer readable medium for enhancing image contrast | |
| CN103258318A (en) | Method and system for image noise reduction processing | |
| US9736456B1 (en) | Two dimensional to three dimensional video conversion | |
| CN104063845B (en) | Enhance the method and device and non-transitory computer-readable media of image contrast |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |