CN107729871A - Infrared light-based human eye movement track tracking method and device - Google Patents
Infrared light-based human eye movement track tracking method and device Download PDFInfo
- Publication number
- CN107729871A CN107729871A CN201711067388.7A CN201711067388A CN107729871A CN 107729871 A CN107729871 A CN 107729871A CN 201711067388 A CN201711067388 A CN 201711067388A CN 107729871 A CN107729871 A CN 107729871A
- Authority
- CN
- China
- Prior art keywords
- msub
- pupil
- human eye
- image
- hot spot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000004424 eye movement Effects 0.000 title abstract 4
- 210000001747 pupil Anatomy 0.000 claims abstract description 94
- 238000000605 extraction Methods 0.000 claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 22
- 230000001815 facial effect Effects 0.000 claims description 22
- 239000013598 vector Substances 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 10
- 230000007246 mechanism Effects 0.000 claims description 7
- 230000005484 gravity Effects 0.000 claims description 5
- 230000003287 optical effect Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 241001300078 Vitrea Species 0.000 claims 4
- 238000011160 research Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000011514 reflex Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/19—Sensors therefor
-
- 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
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/013—Eye tracking input arrangements
Abstract
The invention discloses a human eye movement track tracking method and a human eye movement track tracking device based on infrared light, which comprise a human face image capturing module, a human eye image extracting module, a pupil and light spot extracting module, a fixation point determining module and a track determining module, wherein the human face image capturing module is used for collecting a human face image of which the pupil has light spots; the human eye image extraction module is used for extracting a human eye region image from the human face image; the pupil and light spot extraction module is used for extracting pupil images and light spot images from the human eye area images and determining the relation between the central coordinates of the pupils and the light spots and the fixation point; the fixation point determining module is used for determining fixation point coordinates according to the relation between the central coordinates of the pupil and the light spot and the fixation point; and the track determining module is used for determining the motion track of human eyes according to the coordinates of the plurality of fixation points. The invention can realize the tracking of the human eye movement track and improve the tracking accuracy.
Description
Technical field
The present invention discloses a kind of human eye event trace method for tracing and device based on infrared light, belongs to image procossing and people
Work technical field of intelligence.
Background technology
Human eye event trace has very high researching value, in man-machine interaction, psychology and behavioral study, pattern-recognition, city
The fields such as field research, medical research, highway engineering research, driver training and evaluation are with a wide range of applications.
Pupil-canthus vector method is a kind of method for determining human eye event trace, and it is to utilize pupil-canthus vector and screen
Coordinate mapping relations between curtain produce calibrating parameters, and the eye then calculated on screen moves position.This method extensive use
In the research of eye-tracking, but because human eye pupil and hot spot are smaller, and can be by surrounding environment or hair glasses
Deng occlusion issue, propose more stable and accurate pupil and spot location algorithm for improving whole Arithmetic of Eye-tracking System
Robustness is extremely important.
The content of the invention
In view of the foregoing, it is an object of the invention to provide a kind of human eye event trace method for tracing based on infrared light
And device, it can realize that human eye event trace is followed the trail of, improve tracking accuracy.
To achieve the above object, the present invention uses following technical scheme：
A kind of human eye event trace follow-up mechanism based on infrared light, including facial image acquisition module, eye image carry
Modulus block, pupil and hot spot extraction module, blinkpunkt determining module, track determining module,
Facial image acquisition module, there is the facial image of hot spot for gathering pupil；
Eye image extraction module, for extracting human eye area image from the facial image；
Pupil and hot spot extraction module, for extracting pupil image, light spot image from the human eye area image, and determine
The relation of pupil, the centre coordinate of hot spot and blinkpunkt；
Blinkpunkt determining module, for the relation according to pupil, the centre coordinate of hot spot and blinkpunkt, determine that blinkpunkt is sat
Mark；
Track determining module, for watching point coordinates attentively according to some, determine human eye event trace.
Face picture is gathered using infrared camera or the ordinary optical camera lens for adding infrared filter, obtains the pupil
Facial image with hot spot.
The method of pupil image is extracted from the human eye area image is：
The point that pixel value changes are maximum in the human eye area image is determined using gradient algorithm, as pupil；With this
Centered on pupil, a pupil region is divided；OTSU algorithms are utilized to the pupil region, generate pupil image.
The method of light spot image is extracted from the human eye area image is：
The human eye area image is carried out negating processing, generates human eye area image of the inverted；Utilize gradient algorithm
The point that pixel value changes are maximum in human eye area image of the inverted is determined, as hot spot point；Centered on the hot spot point, division
One spot area；Utilize OTSU algorithms successively to the spot area, generate light spot image.
The centre coordinate of the pupil, hot spot is determined using gravity model appoach, using pupil-cornea vector bounce technique, establishes institute
State the centre coordinate of pupil and hot spot and the mapping relations of blinkpunkt.
A kind of human eye event trace method for tracing based on infrared light, including：
Collection pupil has the facial image of hot spot；
Human eye area image is extracted from the facial image；
Pupil image, light spot image are extracted from the human eye area image；
The centre coordinate of pupil, hot spot is determined,
Determine relation of the centre coordinate of pupil, hot spot with watching point coordinates attentively；
According to continuously point coordinates is watched attentively, human eye event trace is obtained.
Face picture is gathered using infrared camera or the ordinary optical camera lens for adding infrared filter, obtains the pupil
Facial image with hot spot.
The method of pupil image is extracted from the human eye area image is：
The point that pixel value changes are maximum in the human eye area image is determined using gradient algorithm, as pupil；With this
Centered on pupil, a pupil region is divided；OTSU algorithms are utilized to the pupil region, generate pupil image.
The method of light spot image is extracted from the human eye area image is：
The human eye area image is carried out negating processing, generates human eye area image of the inverted；Utilize gradient algorithm
The point that pixel value changes are maximum in human eye area image of the inverted is determined, as hot spot point；Centered on the hot spot point, division
One spot area；Utilize OTSU algorithms successively to the spot area, generate light spot image.
Using pupil-cornea vector bounce technique, the mapping for establishing the centre coordinate and blinkpunkt of the pupil and hot spot is closed
It is to be,
Wherein, (Xgaze, Ygaze) to watch point coordinates attentively,
Wherein, (xp, yp) be pupil centre coordinate, (xc, yc) be hot spot centre coordinate, determine institute using gravity model appoach
State the centre coordinate of pupil, hot spot.
It is an advantage of the invention that：
The human eye event trace method for tracing and device based on infrared light of the present invention, it is real based on pupil-canthus vector method
Human eye event trace tracing process is showed, there is higher tracking accuracy, can be applied in Miniature Terminal equipment.
Brief description of the drawings
Fig. 1 is the apparatus structure block diagram of the present invention.
Fig. 2 is the method flow schematic diagram of the present invention.
Embodiment
Below in conjunction with drawings and examples, the present invention is described in further detail.
As shown in figure 1, the human eye event trace follow-up mechanism disclosed by the invention based on infrared light, including facial image are picked
Modulus block, eye image extraction module, pupil and hot spot extraction module, blinkpunkt determining module, track determining module.
Facial image acquisition module, there is the facial image of hot spot for gathering pupil；
Eye image extraction module, for extracting human eye area image from the facial image；
Pupil and hot spot extraction module, for determining pupil image, light spot image from the human eye area image, and determine
The relation of pupil, the centre coordinate of hot spot and blinkpunkt；
Blinkpunkt determining module, for the relation according to pupil, the centre coordinate of hot spot and blinkpunkt, determine that blinkpunkt is sat
Mark；
Track determining module, for watching point coordinates attentively according to some, determine human eye event trace.
As shown in Fig. 2 the human eye event trace method for tracing disclosed by the invention based on infrared light, including：
S1：Collection pupil has the facial image of hot spot；
Face picture is gathered using infrared camera or the ordinary optical camera lens for adding infrared filter, obtains pupil tool
There is the facial image of hot spot.
S2：The facial image is handled, obtains human eye area image；
Human eye area-of-interest is extracted from facial image using human eye extraction algorithm or deep learning method, is obtained
Human eye area image.
S3：Based on human eye area image, pupil image and light spot image are extracted respectively；
S31：Based on human eye area image, pupil image is extracted
The point that pixel value changes are maximum in human eye area image is determined using gradient algorithm, as pupil；
Centered on the pupil, a pupil region is divided；
OTSU algorithms are utilized to the pupil region, generate pupil image.
S32：Based on human eye area image, light spot image is extracted
Human eye area image is carried out to negate processing, generates human eye area image of the inverted；
The point that pixel value changes are maximum in human eye area image of the inverted is determined using gradient algorithm, as hot spot point；
Centered on the hot spot point, a spot area is divided；
Utilize OTSU algorithms successively to the spot area, generate light spot image.
S4：Based on pupil image and light spot image, the centre coordinate of pupil and hot spot is determined respectively；
Solve the centre coordinate of pupil and the centre coordinate of hot spot respectively using gravity model appoach.
S41：Calculate the centre coordinate of pupil
Calculation formula is：
Wherein, (xp, yp) be pupil centre coordinate, xn、ynPixel value respectively is InHorizontal stroke, ordinate, n is pixel
Number.
S42：Calculate the centre coordinate of hot spot
Calculation formula is：
Wherein, (xc, yc) be hot spot centre coordinate.
S5：Establish the centre coordinate of pupil and hot spot and the mapping relations of blinkpunkt；
Using pupil-cornea vector bounce technique, the centre coordinate of pupil and hot spot and the mapping relations of blinkpunkt are established.Bag
Include：
First, the P-CR vectors between the centre coordinate of pupil and the centre coordinate of hot spot are calculated：
Wherein, (xp, yp) be pupil centre coordinate, (xc, yc) be hot spot centre coordinate, (xe, ye) it is P-CR
(Pupil Corneal Reflex) vector.
Then, using pupil-cornea vector bounce technique of six parameters, the mapping established between blinkpunkt and P-CR vectors is closed
It is to be：
Wherein, (Xgaze, Ygaze) it is to watch point coordinates attentively in demarcation plane.
S6：Known point coordinate is demarcated on screen, determines the centre coordinate of pupil and hot spot and the mapping relations of blinkpunkt；
The coordinate of known point is demarcated on screen, parametric solution is carried out to formula (4), determines that the center of pupil and hot spot is sat
The mapping relations of mark and blinkpunkt.
In a specific embodiment of the invention, parametric solution is carried out using least square method：
Wherein, i is calibration point, respectively 1,2,3,4,5,6,7,8,9.
According to the parameter result of calculation of formula (5), the parameter being calculated is substituted into formula (4), obtains blinkpunkt seat
Mark.
S7：According to continuously point coordinates is watched attentively, human eye event trace is obtained.
By the calculating of successive frame, continuous human eye fixation point coordinate is obtained according to formula (4), (5), so as to obtain human eye
Event trace.
The human eye event trace method for tracing of the present invention, can be applied to desktop computer, notebook, tablet personal computer, intelligence
Mobile phone etc. is configured with the operation terminal of infrared camera, realizes human-computer interaction function.
The technical principle described above for being presently preferred embodiments of the present invention and its being used, for those skilled in the art
For, without departing from the spirit and scope of the present invention, any equivalent change based on the basis of technical solution of the present invention
Change, the simply obvious change such as replacement, belong within the scope of the present invention.
Claims (10)
1. the human eye event trace follow-up mechanism based on infrared light, it is characterised in that including facial image acquisition module, people's eye pattern
Picture extraction module, pupil and hot spot extraction module, blinkpunkt determining module, track determining module,
Facial image acquisition module, there is the facial image of hot spot for gathering pupil；
Eye image extraction module, for extracting human eye area image from the facial image；
Pupil and hot spot extraction module, for extracting pupil image, light spot image from the human eye area image, and determine pupil
The relation in hole, the centre coordinate of hot spot and blinkpunkt；
Blinkpunkt determining module, for the relation according to pupil, the centre coordinate of hot spot and blinkpunkt, it is determined that watching point coordinates attentively；
Track determining module, for watching point coordinates attentively according to some, determine human eye event trace.
2. the human eye event trace follow-up mechanism according to claim 1 based on infrared light, it is characterised in that utilize infrared
Camera or the ordinary optical camera lens collection face picture for adding infrared filter, obtaining the pupil has the face figure of hot spot
Picture.
3. the human eye event trace follow-up mechanism according to claim 1 based on infrared light, it is characterised in that from the people
The method of pupil image is extracted in Vitrea eye area image is：
The point that pixel value changes are maximum in the human eye area image is determined using gradient algorithm, as pupil；With the pupil
Centered on point, a pupil region is divided；OTSU algorithms are utilized to the pupil region, generate pupil image.
4. the human eye event trace follow-up mechanism according to claim 3 based on infrared light, it is characterised in that from the people
The method of light spot image is extracted in Vitrea eye area image is：
The human eye area image is carried out negating processing, generates human eye area image of the inverted；Determined using gradient algorithm
The maximum point of pixel value changes in human eye area image of the inverted, as hot spot point；Centered on the hot spot point, one is divided
Spot area；Utilize OTSU algorithms successively to the spot area, generate light spot image.
5. the human eye event trace follow-up mechanism according to claim 4 based on infrared light, it is characterised in that utilize center of gravity
Method determines the centre coordinate of the pupil, hot spot, using pupil-cornea vector bounce technique, establishes in the pupil and hot spot
The mapping relations of heart coordinate and blinkpunkt.
6. the human eye event trace method for tracing based on infrared light, it is characterised in that including：
Collection pupil has the facial image of hot spot；
Human eye area image is extracted from the facial image；
Pupil image, light spot image are extracted from the human eye area image；
The centre coordinate of pupil, hot spot is determined,
Determine relation of the centre coordinate of pupil, hot spot with watching point coordinates attentively；
According to continuously point coordinates is watched attentively, human eye event trace is obtained.
7. the human eye event trace method for tracing according to claim 6 based on infrared light, it is characterised in that utilize infrared
Camera or the ordinary optical camera lens collection face picture for adding infrared filter, obtaining the pupil has the face figure of hot spot
Picture.
8. the human eye event trace method for tracing according to claim 6 based on infrared light, it is characterised in that from the people
The method of pupil image is extracted in Vitrea eye area image is：
The point that pixel value changes are maximum in the human eye area image is determined using gradient algorithm, as pupil；With the pupil
Centered on point, a pupil region is divided；OTSU algorithms are utilized to the pupil region, generate pupil image.
9. the human eye event trace method for tracing according to claim 6 based on infrared light, it is characterised in that from the people
The method of light spot image is extracted in Vitrea eye area image is：
The human eye area image is carried out negating processing, generates human eye area image of the inverted；Determined using gradient algorithm
The maximum point of pixel value changes in human eye area image of the inverted, as hot spot point；Centered on the hot spot point, one is divided
Spot area；Utilize OTSU algorithms successively to the spot area, generate light spot image.
10. the human eye event trace method for tracing according to claim 6 based on infrared light, it is characterised in that utilize pupil
Hole-cornea vector bounce technique, the mapping relations of the centre coordinate and blinkpunkt of establishing the pupil and hot spot are,
<mrow>
<msub>
<mi>X</mi>
<mrow>
<mi>g</mi>
<mi>a</mi>
<mi>z</mi>
<mi>e</mi>
</mrow>
</msub>
<mo>=</mo>
<msub>
<mi>a</mi>
<mn>0</mn>
</msub>
<mo>+</mo>
<msub>
<mi>a</mi>
<mn>1</mn>
</msub>
<msub>
<mi>x</mi>
<mi>e</mi>
</msub>
<mo>+</mo>
<msub>
<mi>a</mi>
<mn>2</mn>
</msub>
<msub>
<mi>y</mi>
<mi>e</mi>
</msub>
<mo>+</mo>
<msub>
<mi>a</mi>
<mn>3</mn>
</msub>
<msubsup>
<mi>x</mi>
<mi>e</mi>
<mn>2</mn>
</msubsup>
<mo>+</mo>
<msub>
<mi>a</mi>
<mn>4</mn>
</msub>
<msub>
<mi>x</mi>
<mi>e</mi>
</msub>
<msub>
<mi>y</mi>
<mi>e</mi>
</msub>
<mo>+</mo>
<msub>
<mi>a</mi>
<mn>5</mn>
</msub>
<msubsup>
<mi>y</mi>
<mi>e</mi>
<mn>2</mn>
</msubsup>
</mrow>
<mrow>
<msub>
<mi>Y</mi>
<mrow>
<mi>g</mi>
<mi>a</mi>
<mi>z</mi>
<mi>e</mi>
</mrow>
</msub>
<mo>=</mo>
<msub>
<mi>b</mi>
<mn>0</mn>
</msub>
<mo>+</mo>
<msub>
<mi>b</mi>
<mn>1</mn>
</msub>
<msub>
<mi>x</mi>
<mi>e</mi>
</msub>
<mo>+</mo>
<msub>
<mi>b</mi>
<mn>2</mn>
</msub>
<msub>
<mi>y</mi>
<mi>e</mi>
</msub>
<mo>+</mo>
<msub>
<mi>b</mi>
<mn>3</mn>
</msub>
<msubsup>
<mi>x</mi>
<mi>e</mi>
<mn>2</mn>
</msubsup>
<mo>+</mo>
<msub>
<mi>b</mi>
<mn>4</mn>
</msub>
<msub>
<mi>x</mi>
<mi>e</mi>
</msub>
<msub>
<mi>y</mi>
<mi>e</mi>
</msub>
<mo>+</mo>
<msub>
<mi>b</mi>
<mn>5</mn>
</msub>
<msubsup>
<mi>y</mi>
<mi>e</mi>
<mn>2</mn>
</msubsup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, (Xgaze, Ygaze) to watch point coordinates attentively,
<mrow>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>x</mi>
<mi>e</mi>
</msub>
<mo>=</mo>
<msub>
<mi>x</mi>
<mi>p</mi>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mi>c</mi>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>y</mi>
<mi>e</mi>
</msub>
<mo>=</mo>
<msub>
<mi>y</mi>
<mi>p</mi>
</msub>
<mo>-</mo>
<msub>
<mi>y</mi>
<mi>c</mi>
</msub>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, (xp, yp) be pupil centre coordinate, (xc, yc) be hot spot centre coordinate, determine the pupil using gravity model appoach
Hole, the centre coordinate of hot spot.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711067388.7A CN107729871A (en) | 2017-11-02 | 2017-11-02 | Infrared light-based human eye movement track tracking method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711067388.7A CN107729871A (en) | 2017-11-02 | 2017-11-02 | Infrared light-based human eye movement track tracking method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107729871A true CN107729871A (en) | 2018-02-23 |
Family
ID=61222047
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711067388.7A Pending CN107729871A (en) | 2017-11-02 | 2017-11-02 | Infrared light-based human eye movement track tracking method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107729871A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109613984A (en) * | 2018-12-29 | 2019-04-12 | 歌尔股份有限公司 | Processing method, equipment and the system of video image in VR live streaming |
| CN111061372A (en) * | 2019-12-18 | 2020-04-24 | Oppo广东移动通信有限公司 | Equipment control method and related equipment |
| CN111443804A (en) * | 2019-12-27 | 2020-07-24 | 安徽大学 | Method and system for describing fixation point track based on video analysis |
| CN111528788A (en) * | 2020-05-27 | 2020-08-14 | 温州医科大学 | Portable detecting instrument for evaluating visual fatigue degree |
| CN112464829A (en) * | 2020-12-01 | 2021-03-09 | 中航航空电子有限公司 | Pupil positioning method, pupil positioning equipment, storage medium and sight tracking system |
| CN113362775A (en) * | 2021-06-24 | 2021-09-07 | 东莞市小精灵教育软件有限公司 | Display screen control method and device, electronic equipment and storage medium |
| CN114022946A (en) * | 2022-01-06 | 2022-02-08 | 深圳佑驾创新科技有限公司 | Sight line measuring method and device based on binocular camera |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103530618A (en) * | 2013-10-23 | 2014-01-22 | 哈尔滨工业大学深圳研究生院 | Non-contact sight tracking method based on corneal reflex |
| CN103679180A (en) * | 2012-09-19 | 2014-03-26 | 武汉元宝创意科技有限公司 | Sight tracking method based on single light source of single camera |
| US20160081547A1 (en) * | 2013-05-15 | 2016-03-24 | The Johns Hopkins University | Eye tracking and gaze fixation detection systems, components and methods using polarized light |
-
2017
- 2017-11-02 CN CN201711067388.7A patent/CN107729871A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103679180A (en) * | 2012-09-19 | 2014-03-26 | 武汉元宝创意科技有限公司 | Sight tracking method based on single light source of single camera |
| US20160081547A1 (en) * | 2013-05-15 | 2016-03-24 | The Johns Hopkins University | Eye tracking and gaze fixation detection systems, components and methods using polarized light |
| CN103530618A (en) * | 2013-10-23 | 2014-01-22 | 哈尔滨工业大学深圳研究生院 | Non-contact sight tracking method based on corneal reflex |
Non-Patent Citations (2)
| Title |
|---|
| 谢波: "基于视频图像的瞳孔定位算法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 陈秋香: "基于瞳孔-角膜反射的视线跟踪算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109613984A (en) * | 2018-12-29 | 2019-04-12 | 歌尔股份有限公司 | Processing method, equipment and the system of video image in VR live streaming |
| CN109613984B (en) * | 2018-12-29 | 2022-06-10 | 歌尔光学科技有限公司 | Method, device and system for processing video images in VR live broadcast |
| CN111061372A (en) * | 2019-12-18 | 2020-04-24 | Oppo广东移动通信有限公司 | Equipment control method and related equipment |
| CN111443804A (en) * | 2019-12-27 | 2020-07-24 | 安徽大学 | Method and system for describing fixation point track based on video analysis |
| CN111443804B (en) * | 2019-12-27 | 2022-08-19 | 安徽大学 | Method and system for describing fixation point track based on video analysis |
| CN111528788A (en) * | 2020-05-27 | 2020-08-14 | 温州医科大学 | Portable detecting instrument for evaluating visual fatigue degree |
| CN112464829A (en) * | 2020-12-01 | 2021-03-09 | 中航航空电子有限公司 | Pupil positioning method, pupil positioning equipment, storage medium and sight tracking system |
| CN112464829B (en) * | 2020-12-01 | 2024-04-09 | 中航航空电子有限公司 | Pupil positioning method, pupil positioning equipment, storage medium and sight tracking system |
| CN113362775A (en) * | 2021-06-24 | 2021-09-07 | 东莞市小精灵教育软件有限公司 | Display screen control method and device, electronic equipment and storage medium |
| CN114022946A (en) * | 2022-01-06 | 2022-02-08 | 深圳佑驾创新科技有限公司 | Sight line measuring method and device based on binocular camera |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107729871A (en) | Infrared light-based human eye movement track tracking method and device | |
| Angelopoulos et al. | Event based, near eye gaze tracking beyond 10,000 hz | |
| CN104866105B (en) | The eye of aobvious equipment is dynamic and head moves exchange method | |
| US11556741B2 (en) | Devices, systems and methods for predicting gaze-related parameters using a neural network | |
| US11194161B2 (en) | Devices, systems and methods for predicting gaze-related parameters | |
| CN105094300B (en) | A kind of sight line tracking system and method based on standardization eye image | |
| CN107193383A (en) | A kind of two grades of Eye-controlling focus methods constrained based on facial orientation | |
| WO2019033569A8 (en) | Eyeball movement analysis method, device and storage medium | |
| Anilkumar et al. | Pose estimated yoga monitoring system | |
| US20200364453A1 (en) | Devices, systems and methods for predicting gaze-related parameters | |
| WO2020020022A1 (en) | Method for visual recognition and system thereof | |
| Chang et al. | A pose estimation-based fall detection methodology using artificial intelligence edge computing | |
| Cho | Automated mental stress recognition through mobile thermal imaging | |
| CN109063545A (en) | A kind of method for detecting fatigue driving and device | |
| CN105912126A (en) | Method for adaptively adjusting gain, mapped to interface, of gesture movement | |
| Wei et al. | Real-time limb motion tracking with a single imu sensor for physical therapy exercises | |
| Sangeetha | A survey on deep learning based eye gaze estimation methods | |
| CN106618479A (en) | Pupil tracking system and method thereof | |
| Hori et al. | Silhouette-based synthetic data generation for 3D human pose estimation with a single wrist-mounted 360° camera | |
| CN107832699A (en) | Method and device for testing interest point attention degree based on array lens | |
| Kar et al. | Eye-gaze systems-An analysis of error sources and potential accuracy in consumer electronics use cases | |
| Chen et al. | Deep-learning-based human motion tracking for rehabilitation applications using 3D image features | |
| Madhusanka et al. | Concentrated gaze base interaction for decision making using human-machine interface | |
| US20220198789A1 (en) | Systems and methods for determining one or more parameters of a user's eye | |
| Skowronek et al. | Eye Tracking Using a Smartphone Camera and Deep Learning |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180223 |
|
| WD01 | Invention patent application deemed withdrawn after publication |