CN105677024B - A kind of eye moves detecting and tracking method, apparatus and application thereof - Google Patents
A kind of eye moves detecting and tracking method, apparatus and application thereof Download PDFInfo
- Publication number
- CN105677024B CN105677024B CN201511028928.1A CN201511028928A CN105677024B CN 105677024 B CN105677024 B CN 105677024B CN 201511028928 A CN201511028928 A CN 201511028928A CN 105677024 B CN105677024 B CN 105677024B
- Authority
- CN
- China
- Prior art keywords
- eyeball
- target rectangle
- hash codes
- frame
- image
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/013—Eye tracking input arrangements
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30041—Eye; Retina; Ophthalmic
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)
- Image Analysis (AREA)
Abstract
This application discloses a kind of eyes to move detecting and tracking method, apparatus and application thereof, wherein the described method includes：Capture may include the consecutive image sequence of eyeball；Detection positioning candidate's eyeball target rectangle in the imaging picture of described image sequence；It goes unless Ins location and the eyeball target rectangle tracked；Hash codes calculation procedure scans whole image in a frame of described image sequence and calculates the Hash codes of each scanning window；Comparison step compares the Hamming distance of the Hash codes of calculating and the Hash codes of the eyeball target rectangle of tracking, and the scanning window of wherein Hamming distance minimum is the eyeball target position of present frame；The next frame eyeball target rectangle to be tracked is updated with the eyeball target rectangle of present frame, repeats Hash codes calculation procedure and comparison step until obtaining the eyeball target rectangle coordinate sequence of N two field pictures；The angle of eyeball movement is calculated according to the coordinate sequence.The application can realize oculomotor accurate detect and track.
Description
Technical field
This application involves electric digital data processing field more particularly to a kind of positions for detecting positioning eyeball in image
And it analyzes and detects that the eye of the movement locus of eyeball within a certain period of time moves detecting and tracking method and/or device.The application also relates to
And foregoing eye move detecting and tracking method for control application such as player application operation purposes.
Background technology
It is the development of the information technology and information industry of representative and application to mankind society using multimedia in current information-intensive society
The influence and effect that can be generated are more and more apparent, more and more important.Multimedia development and application have greatly promoted all multiplexings
Industry interpenetrating and developing rapidly, and the work structuring and life style of entire human society has been altered in steps.It can not overstate
It opens ground and says that the formation and development of multimedia industry will not only cause the revolution of computer industry, will also influence human society
A huge change occurs.
Multimedia player integrates audio, video playing, audio play part realize broadcasting, pause, a upper head,
Next, the functions such as volume adjustment, synchronous lyrics are shown, play mode selects.Functional, user interaction is friendly.Video is broadcast
Part is put in addition to general control function is realized, also supports the functions such as the switching of different video aspect ratio.It is most of at present
The cellphone multimedia player independent operating in Android or iOS system mostly.
Most cellphone multimedia player controls the temporary of audio and video mostly in a manner that finger moves screen sliding at present
Stop, play, F.F., retrogressing, the functions such as switching are, it is necessary to which user has with mobile terminal directly contacts, it is impossible to liberate both hands.With
In the case of family wearing gloves or both hands inconvenience, the mode of this touch screen type control multimedia just seems not friendly enough
Good, collaborative is poor, influences user experience.Meanwhile prolonged contact action can damage mobile phone screen, influence beauty.It is worth note
Meaning, if touch-screen mobile phone screen is broken, the mobile phones such as similar apple, Meizu cannot use.
Samsung once released a Note3 mobile phones, added smart screen, and this functionality is taken the photograph by the way that machine is preposition
It is main to realize as head eye intelligent identification technology：Intelligent dormancy is opened, and tool bar shows an eyes：When user looks at screen,
It will not blank screen；Intelligent rotating is opened, and mobile phone screen rotates automatically according to the head direction (90 degree) of user；Intelligence pause is opened, and is seen
Judge whether user sees screen automatic pause or broadcasting during video；Intelligent rolling is opened, when user uses internet, Email
When (only limiting both programs at present), screen can be according to the head or screen inclination degree of user come automatic scroll-up/down.But this
The user experience reaction of application module is not high, and the eyeball control module core algorithm that this is primarily due to Samsung is immature, by mistake
Operating rate is high.
The content of the invention
An object of the application is to provide a kind of accuracy rate high eye movement detecting and tracking method and apparatus.The application's
Target also resides in the side for providing that a kind of misuse rate is low, the eye of promotion user experience moves intelligent control player or similar application
Method.
An object of the application is moved detecting and tracking method by a kind of eye and is realized, this method includes：
Capture may include the consecutive image sequence of eyeball；
Detection positioning candidate's eyeball target rectangle in the imaging picture of described image sequence；
It goes unless Ins location and the eyeball target rectangle tracked；
Hash codes calculation procedure scans whole image in a frame of described image sequence and calculates each scanning window
Hash codes；
Comparison step compares the Hamming distance of the Hash codes of calculating and the Hash codes of the eyeball target rectangle of tracking, wherein
The scanning window of Hamming distance minimum is the eyeball target position of present frame；
The next frame eyeball target rectangle to be tracked is updated with the eyeball target rectangle of present frame, Hash codes is repeated and calculates step
Rapid and comparison step is until obtaining the eyeball target rectangle coordinate sequence of N two field pictures, N >=2；And
The angle of eyeball movement is calculated according to the coordinate sequence.
An object of the application is also moved detecting and tracking device by a kind of eye and is realized, which includes：
Image capture module, for capturing the consecutive image sequence that may include eyeball；
Candidate target frame acquisition module, for detection positioning candidate's eyeball target in the imaging picture of described image sequence
Rectangle；
Target rectangle determining module, for going unless Ins location and the eyeball target rectangle tracked；
Hash codes computing module, for scanning whole image in a frame of described image sequence and calculating each scanning window
The Hash codes of mouth；
Comparison module, for comparing the Hamming distance of the Hash codes of the eyeball target rectangle of the Hash codes of calculating and tracking,
The scanning window of wherein Hamming distance minimum is the eyeball target position of present frame；
Update module, for updating the next frame eyeball target rectangle to be tracked, weight with the eyeball target rectangle of present frame
Multiple Hash codes are calculated and compared until obtaining the eyeball target rectangle coordinate sequence of N two field pictures, N >=2；
Eyeball move angle computing module, for calculating the angle of eyeball movement according to the coordinate sequence.
The target of the present invention is also moved the method for detecting and tracking method control application operating, institute by a kind of eye using the present invention
Stating the method for control application operating includes：
Control signal corresponding with the angle is sent to application according to the angle that eyeball moves；
The application is operated according to the control signal.
The present invention realizes high-accuracy, efficient eyeball fortune by improving the process flow and Processing Algorithm of image
Dynamic detect and track is especially suitable for the mobile terminals such as the limited mobile phone of computing capability.In addition, the present invention is different from traditional touch screen
The mode of formula operating handset player, by the algorithm realization of image procossing and pattern-recognition eyeball intelligent control player,
Both hands have been liberated, have improved the convenience of mobile phone operation and the comfort level of user interaction, misuse rate is low, brings before user institute not
The high-quality experience having.
Unless explicitly stated otherwise, singulative as used herein " one ", "the", which include plural reference, (has " at least one "
The meaning).It will be further understood that terminology used herein " having ", " comprising " and/or "comprising" show in the presence of described
Feature, step, operation, element and/or component, but do not preclude the presence or addition of other one or more features, step, behaviour
Work, element, component and/or its combination.Term "and/or" as used in this includes one or more relevant items enumerated
Any and all combination.Unless explicitly stated otherwise, the step of any method disclosed herein need not be accurately according to disclosed order
It performs.
Description of the drawings
The present invention will more completely be illustrated below with reference to attached drawing and with reference to preferred embodiment.
Fig. 1 is the flow chart according to an embodiment of the method for the present invention.
Fig. 2 is the structure diagram according to an embodiment of apparatus of the present invention.
Fig. 3 is the schematic diagram that method shown in FIG. 1 is used to control the operation of player.
For clarity, these attached drawings are figure that is schematic and simplifying, they are only gived for understanding institute of the present invention
Necessary details, and omit other details.
Specific embodiment
By detailed description given below, the scope of application of the invention will be evident.It will be appreciated, however, that detailed
While thin description and specific example show the preferred embodiment of the present invention, they are provided only for illustration purpose.
Fig. 1 shows an embodiment of the method for the present invention, and this method is used to be detected eyeball positioning and to same
The movement locus of eyeball is into line trace.Eyeball detects, and is the imaging for the consecutive image sequence for including eyeball from the possibility of capture
The position of eyeball in the picture is positioned in figure.Eyes are different from skin, there is gem-pure shape and color characteristic.In order to ensure
The real-time of algorithm, the method for the embodiment realize eye using the algorithm combination prior information that image preprocessing and image are split
Eyeball positions.Eye tracking analyzes the movement locus of the eyeball detected within a certain period of time.The method of the embodiment uses frame
Between calculus of finite differences do the motion detection of eyeball, and draw the track of eyeball with reference to the track algorithm that Hash perceives.
Specifically, the method for embodiment illustrated in fig. 1 starts from step S10, and capture may include the consecutive image sequence of eyeball
Row.Afterwards, processing proceeds to step S20, the imaging picture in the image sequence of capture is pre-processed, pretreatment may include
One of the following or a variety of pretreatments：It is imaged picture denoising：Image is done using image median filter algorithm smoothly, removal picture is small
Noise；It is imaged picture binaryzation：Image binaryzation is realized using maximum variance between clusters；Morphologic filtering：Fill binary picture
The connected region of picture removes white noise point or burr.Afterwards, processing proceeds to step S30, splits detection positioning using connected region
The rectangle of the encirclement eyeball target of candidate's eyeball position, i.e. candidate, is known as candidate's eyeball target rectangle.Afterwards, processing proceeds to
Step S40 is gone than preset value unless Ins location, the eyeball mesh tracked using eyeball the ratio of width to height and profile bumps of priori
Mark rectangle.Human eyeball's approximation positive round, so the ratio of width to height of its extraneous rectangle frame is close to 1, such as 0.9-1.1.In addition, eyeball
Profile is convex, so concave-convex ratio at least should be greater than 1.Be unsatisfactory for these preset value conditions, then show its be not eyeball or
It is not complete eyeball, should casts out from the processing of the present invention.
While detection positions eyeball target rectangle, the method for the embodiment further includes step S20 ', utilizes frame-to-frame differences
Point-score carries out motion detection to eyeball.Frame differential method is to extract figure using being made the difference between consecutive frame image in image sequence
Moving region as in.Two images by same background, at different moments carry out calculus of differences, the not changed background of gray scale
Part is subtracted, since position of the moving target in adjacent two frame is different, and with background gray scale difference, after two frames subtract each other
It will protrude moving target (eyeball) to come, so as to substantially determine the position of moving target in the picture.Detect motor area
Behind domain, processing proceeds to step S50, by moving region and the eyeball target rectangle phase of tracking obtained in step S40 and, two
Person's overlapping area causes processing to terminate when being less than 60%.If the two overlapping area is more than 60%, secondary to be proved to be successful, processing
Proceed to step S60, the tracking to the target eyeball is unfolded.Target following is exactly in a continuous videos sequence, each
The position of same moving target (eyeball) is found in frame monitored picture, the position of each frame is connected just on a timeline
Obtain the movement locus of target.In this embodiment, eye tracking is realized using Hash perception algorithm.Tracking is calculated first
Hash (hash) code of eyeball target rectangle then when each frame arrives, scans whole image, calculates each scanning window
The hash codes of mouth.The computational methods of hash codes are as follows：
(1) reduce the size：Average Hash (pHash) is started with small picture, but picture is preferably greater than 8*8, and 32*32 is optimal.
In this embodiment, using the picture of 32*32.The purpose for the arrangement is that the calculating of discrete cosine transform (DCT) can be simplified, and
It is not to reduce frequency.
(2) color is simplified：Picture is changed into gray level image, is further simplified calculation amount.
(3) DCT is calculated：The dct transform of picture is calculated, obtains the DCT coefficient matrix of 32*32.
(4) DCT is reduced：Although DCT's the result is that the matrix of 32*32 sizes, need to only retain the square of the 8*8 in the upper left corner
Battle array, this part presents the low-limit frequency in picture.
(5) average value is calculated：As average Hash, the average of DCT is calculated.
(6) hash values are calculated：According to the DCT matrixes of 8*8, the hash values of 64 of setting 0 or 1, more than or equal to DCT averages
Be set to " 1 ", less than being set to " 0 " for DCT averages.It combines, just constitutes the integer of one 64, here it is this figures
The hash codes of piece.
Afterwards, the Hamming distance of the hash codes of the hash codes of picture and the eyeball target rectangle of tracking, Hamming distance are compared
The minimum scanning window of distance and target are most like, that is, the target position of the frame.It, can be only in order to accelerate
Image-region is scanned around previous frame target.Meanwhile for the variation for adapting to target, it is also necessary to after successfully tracking
Each frame update target to be tracked, i.e., update the next frame eyeball target square to be tracked with the eyeball target rectangle of present frame
Shape.It repeats the above steps, the position sequence for obtaining the eyeball of N two field pictures is [(x1,y1),(x2,y2),...(xn,yn),...
(xN,yN)], calculate a slope k every z framesn, 1≤z≤10, z values are bigger, and precision is lower, and 3, i.e. k are taken as in this zn=yn+3-
yn/xn+3-xn, so as to obtain angle [alpha]=arctan (kn).Afterwards, the angle sequence [α that a sum is M is obtained1,α2,...
αm,...αM], the angle that eyeball movement can be calculated from the angle sequence isIn this way, just complete eyeball
The tracking of movement.
Fig. 2 shows an embodiment of apparatus of the present invention, which is used to implement oculomotor detect and track, the dress
Put including：Image capture module 10, for capturing the consecutive image sequence that may include eyeball；Candidate target frame acquisition module
20, for detection positioning candidate's eyeball target rectangle in the imaging picture of described image sequence；Target rectangle determining module 30,
For going unless Ins location and the eyeball target rectangle tracked；Hash codes computing module 40, in described image sequence
Whole image is scanned during one frame of row and calculates the Hash codes of each scanning window；Comparison module 50, for comparing the Kazakhstan of calculating
The Hamming distance of the Hash codes of uncommon code and the eyeball target rectangle of tracking, the scanning window of wherein Hamming distance minimum are as current
The eyeball target position of frame；Update module 60, for what is tracked with the eyeball target rectangle of present frame update next frame
Eyeball target rectangle repeats Hash codes and calculates and compare until obtaining the eyeball target rectangle coordinate sequence of N two field pictures, N >=2；
Eyeball move angle computing module 70, for calculating the angle of eyeball movement according to the coordinate sequence.
Fig. 3 shows that the eye of embodiment illustrated in fig. 1 moves detecting and tracking method for controlling the schematic diagram of application operating.Control
The operation of application includes：According to the action for the angle-determining eyeball that the eyeball that calculates moves, further according to eyeball action to should
With transmission control signal corresponding with the action；It is operated using according to the control signal received.It is played herein with controlling
Exemplified by device operation, this method can also be applied to the other applications such as reader.For example, set as shown in following table, eyeball action
Correspondence between player function.
| Player function | Eyeball acts |
| Player F.F. | Eyeball is looked squarely to move from left to right |
| Player retreats | Eyeball is looked squarely to move from right to left |
| It plays next | Eyeball is looked squarely to move from the top down |
| Play one | Eyeball is looked squarely to move from bottom to top |
| Increase volume | Eyeball is seen obliquely |
| Reduce volume | Eyeball is seen obliquely |
As shown in Figure 3, when the angle for the eyeball movement being calculated is in [- 10 °, 10 °] scope, represent that eyeball is put down
Depending on moving from left to right.If the eyeball traced into is such eyeball action, F.F. control signal is sent to player, is broadcast
It puts device and carries out forwarding operation.Similarly, when the angle of eyeball movement is in [- 170 °, -190 °] scope, represent that eyeball is looked squarely
It moves from right to left；When in [35 °, 55 °] scope, represent that eyeball is seen obliquely；When in [- 125 °, -145 °] scope, table
Show that eyeball is seen obliquely；When in [80 °, 100 °] scope, represent that eyeball moves from bottom to top；In [- 80 °, -100 °] scope
When, represent that eyeball moves from the top down.In embodiment, according to the needs of precision, aforementioned angular scope may be set to be not
Same angular range.Different according to the application of control, it is also different that eyeball acts corresponding application function.In this way, user only needs
The progress that can control player by the eyeball i.e. brush eye that moves up and down and switching up and down, adjust without manual touch screen.
Some preferred embodiments are illustrated in front, it should be emphasized, however, that the present invention is not limited to this
A little embodiments, but can be realized with the other manner in the range of present subject matter.
Claims (9)
1. a kind of eye moves detecting and tracking method, which is characterized in that the described method includes：
Capture may include the consecutive image sequence of eyeball；
Detection positioning candidate's eyeball target rectangle in the imaging picture of described image sequence；
It goes unless Ins location and the eyeball target rectangle tracked；
Hash codes calculation procedure scans whole image in a frame of described image sequence and calculates the Hash of each scanning window
Code；
Comparison step compares the Hamming of the Hash codes of each scanning window of calculating and the Hash codes of the eyeball target rectangle of tracking
The scanning window of distance, wherein Hamming distance minimum is the eyeball target position of present frame；
Update the next frame eyeball target rectangle to be tracked with the eyeball target rectangle of present frame, repeat Hash codes calculation procedure and
Comparison step is until obtaining eyeball target rectangle the coordinate sequence [(x of N two field pictures1,y1),(x2,y2),...(xn,yn),...
(xN,yN)], N >=2；
A slope k is calculated every z framesnTo obtain angle sequence [α of the sum for M1,α2,...αm,...αM], wherein kn=
yn+z-yn/xn+z-xn, α=arctan (kn), 1≤z≤10；And
The angle, θ of eyeball movement is calculated,
2. according to the method described in claim 1, it is characterized in that, detection positioning candidate's eyeball position includes：
Denoising is carried out to the imaging picture to remove the small noise of picture；And/or
Image binaryzation processing is carried out to the imaging picture to obtain binary image；And
The connected region of the binary image is filled to remove white noise point or burr；And
Split positioning candidate's eyeball position using connected region.
3. according to the method described in claim 1, it is characterized in that, the ratio of width to height and profile in candidate's eyeball target rectangle are concave-convex
It is removed during than being unsatisfactory for preset value as non-Ins location.
4. according to the method described in claim 1, it is characterized in that, the method further includes before Hash codes calculation procedure：
Using making the difference to extract the moving region in image between consecutive frame image in image sequence；
By the moving region with track eyeball target rectangle phase with, the two overlapping area be less than 60% when cause processing tie
Beam.
5. according to the method described in claim 1, it is characterized in that, the calculating of the Hash codes includes：
The discrete cosine transform of picture is calculated, obtains DCT coefficient matrix；
Calculate the average of DCT coefficient matrix；
According to DCT coefficient matrix, it will be greater than being set to " 1 " equal to DCT averages, be set to " 0 " less than DCT averages, scanned
The Hash codes of window.
6. according to the method described in claim 5, it is characterized in that, the method further includes before DCT is calculated：
Dimension of picture is reduced to simplify the calculating of DCT；And/or
Picture is changed into gray level image to simplify the calculating of DCT.
7. method according to claim 5 or 6, which is characterized in that the method is also wrapped before the average of DCT is calculated
It includes：
DCT coefficient matrix is reduced only to retain the part for presenting the low-limit frequency in picture.
8. a kind of eye moves detecting and tracking device, which is characterized in that described device includes：
Image capture module, for capturing the consecutive image sequence that may include eyeball；
Candidate target frame acquisition module, for detection positioning candidate's eyeball target square in the imaging picture of described image sequence
Shape；
Target rectangle determining module, for going unless Ins location and the eyeball target rectangle tracked；
Hash codes computing module, for scanning whole image in a frame of described image sequence and calculating each scanning window
Hash codes；
Comparison module, for comparing the Hamming distance of the Hash codes of the eyeball target rectangle of the Hash codes of calculating and tracking, wherein
The scanning window of Hamming distance minimum is the eyeball target position of present frame；
Update module for updating the next frame eyeball target rectangle to be tracked with the eyeball target rectangle of present frame, repeats to breathe out
Uncommon code is calculated and compared until obtaining the eyeball target rectangle coordinate sequence of N two field pictures, N >=2；
Eyeball move angle computing module, for calculating a slope k every z framesnTo obtain angle sequence [α of the sum for M1,
α2,...αm,...αM], wherein kn=yn+z-yn/xn+z-xn, α=arctan (kn), 1≤z≤10 and the angle for calculating eyeball movement
Spend θ,
A kind of 9. method using according to any method control application operatings of claim 1-7, which is characterized in that described
The method of control application operating includes：
Control signal corresponding with the angle is sent to application according to the angle that eyeball moves；
The application is operated according to the control signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511028928.1A CN105677024B (en) | 2015-12-31 | 2015-12-31 | A kind of eye moves detecting and tracking method, apparatus and application thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511028928.1A CN105677024B (en) | 2015-12-31 | 2015-12-31 | A kind of eye moves detecting and tracking method, apparatus and application thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105677024A CN105677024A (en) | 2016-06-15 |
| CN105677024B true CN105677024B (en) | 2018-05-29 |
Family
ID=56189906
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511028928.1A Active CN105677024B (en) | 2015-12-31 | 2015-12-31 | A kind of eye moves detecting and tracking method, apparatus and application thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105677024B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106990839B (en) * | 2017-03-21 | 2020-06-05 | 张文庆 | Eyeball identification multimedia player and implementation method thereof |
| CN108392170A (en) * | 2018-02-09 | 2018-08-14 | 中北大学 | A kind of human eye follow-up mechanism and recognition positioning method for optometry unit |
| CN109144238B (en) * | 2018-05-14 | 2021-09-28 | 孙佳楠 | Human-computer interaction system based on electro-oculogram coding and interaction method thereof |
| CN109598207B (en) * | 2018-11-14 | 2021-08-10 | 华南理工大学 | Fast human eye tracking method based on convolutional neural network |
| CN109799908B (en) * | 2019-01-02 | 2022-04-01 | 东南大学 | Image zooming and dragging method based on eye movement signal |
| CN110033652B (en) * | 2019-03-11 | 2021-06-04 | 中国民航大学 | Radar dynamic target calibration method and system based on eye tracking |
| CN110147752A (en) * | 2019-05-15 | 2019-08-20 | 浙江大华技术股份有限公司 | Motion detection processing method, device, electronic equipment and storage medium |
| CN110248091B (en) * | 2019-06-12 | 2021-06-04 | Oppo广东移动通信有限公司 | Focal length adjusting method and related product |
| CN112885435B (en) * | 2019-11-29 | 2023-04-21 | 天津拓影科技有限公司 | Method, device and system for determining image target area |
| CN111353429A (en) * | 2020-02-28 | 2020-06-30 | 深圳壹账通智能科技有限公司 | Interest degree method and system based on eyeball turning |
| CN111523474B (en) * | 2020-04-23 | 2023-09-26 | 维沃移动通信有限公司 | Target object tracking method and electronic device |
| CN111638780A (en) * | 2020-04-30 | 2020-09-08 | 长城汽车股份有限公司 | Vehicle display control method and vehicle host |
| CN113992907B (en) * | 2021-10-29 | 2023-11-07 | 南昌虚拟现实研究院股份有限公司 | Eyeball parameter verification method, eyeball parameter verification system, computer and readable storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104348969A (en) * | 2013-09-05 | 2015-02-11 | 陈英时 | Method for operating mobile phone by stare of line of sight |
| CN105139420A (en) * | 2015-08-03 | 2015-12-09 | 山东大学 | Particle filter and perceptual hash-based video target tracking method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3586431B2 (en) * | 2001-02-28 | 2004-11-10 | 松下電器産業株式会社 | Personal authentication method and device |
| US8078825B2 (en) * | 2009-03-11 | 2011-12-13 | Oracle America, Inc. | Composite hash and list partitioning of database tables |
-
2015
- 2015-12-31 CN CN201511028928.1A patent/CN105677024B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104348969A (en) * | 2013-09-05 | 2015-02-11 | 陈英时 | Method for operating mobile phone by stare of line of sight |
| CN105139420A (en) * | 2015-08-03 | 2015-12-09 | 山东大学 | Particle filter and perceptual hash-based video target tracking method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105677024A (en) | 2016-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105677024B (en) | A kind of eye moves detecting and tracking method, apparatus and application thereof | |
| US11227368B2 (en) | Method and device for controlling an electronic device based on determining a portrait region using a face region detection and depth information of the face region detected | |
| US11398049B2 (en) | Object tracking device, object tracking method, and object tracking program | |
| TWI357582B (en) | Image tracking system and method thereof | |
| JP6548518B2 (en) | INFORMATION PROCESSING APPARATUS AND INFORMATION PROCESSING METHOD | |
| KR101173802B1 (en) | Object tracking apparatus, object tracking method, and recording medium for control program | |
| US8395676B2 (en) | Information processing device and method estimating a posture of a subject in an image | |
| CN109389021B (en) | Physiological signal measuring system and method for measuring physiological signal | |
| US9727800B2 (en) | Optimized object detection | |
| US20020135581A1 (en) | Method and system for controlling an avatar using computer vision | |
| WO2018052547A1 (en) | An automatic scene calibration method for video analytics | |
| KR20210014774A (en) | Tracker assisted image capture | |
| KR101868903B1 (en) | Apparatus and method for tracking human hand by using color features | |
| CN104182718A (en) | Method and device for locating facial feature points | |
| JP2008113071A (en) | Automatic tracking device | |
| KR20130043394A (en) | Method of image processing for detecting object, device, method for user interface and user interface thereof | |
| US10621730B2 (en) | Missing feet recovery of a human object from an image sequence based on ground plane detection | |
| EP2998960A1 (en) | Method and device for video browsing | |
| CN108921010B (en) | Pupil detection method and detection device | |
| CN112041884A (en) | Object segmentation in a sequence of color image frames by background image and background depth correction | |
| KR100474760B1 (en) | Object domain detecting method for image | |
| US20130222621A1 (en) | Information processing apparatus, terminal apparatus, image capturing apparatus, information processing method, and information provision method for an image capturing apparatus | |
| JP2008288684A (en) | Person detection device and program | |
| KR20100025048A (en) | Image analysis apparatus and method for motion capture | |
| JP4559375B2 (en) | Object position tracking method, apparatus, and program |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210201 Address after: 101300 room 153, 1 / F, building 17, 16 Caixiang East Road, Nancai Town, Shunyi District, Beijing Patentee after: Yuanxin Information Technology Group Co.,Ltd. Address before: 100176 room 2222, building D, building 33, 99 Kechuang 14th Street, Beijing Economic and Technological Development Zone, Daxing District, Beijing Patentee before: BEIJING YUANXIN SCIENCE & TECHNOLOGY Co.,Ltd. |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20160615 Assignee: Beijing Yuanxin Junsheng Technology Co.,Ltd. Assignor: Yuanxin Information Technology Group Co.,Ltd. Contract record no.: X2021110000018 Denomination of invention: Eye movement detection and tracking method, device and Application Granted publication date: 20180529 License type: Common License Record date: 20210531 |