CN103054548A - Fixation point measurement device and pupil recognition method and Purkinje image recognition method - Google Patents
Fixation point measurement device and pupil recognition method and Purkinje image recognition method Download PDFInfo
- Publication number
- CN103054548A CN103054548A CN2012102311449A CN201210231144A CN103054548A CN 103054548 A CN103054548 A CN 103054548A CN 2012102311449 A CN2012102311449 A CN 2012102311449A CN 201210231144 A CN201210231144 A CN 201210231144A CN 103054548 A CN103054548 A CN 103054548A
- Authority
- CN
- China
- Prior art keywords
- agglomerate
- image
- pupil
- area
- pul
- 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
Images
Abstract
The invention provides a fixation point measurement device which is based on video images. The fixation point measurement device is characterized by comprising a support, a camera, a light source, a host, a direct current stabilized power supply, a main displayer and an auxiliary displayer. The support is structurally provided with a base; a left stand column and a right stand column are fixed on the base; an upper forehead support and a lower jaw support are fixed on the left stand column and the right stand column; the camera, the main displayer and the auxiliary displayer are respectively in electrical connection with the host through respective ports; and the light source is in electrical connection with the direct current stabilized power supply. The device has the advantages of free of interference, precise in measurement and good in effect and the like. In a pupil recognition method, a pupil in an eye image can be precisely recognized; in a Purkinje image recognition method, a Purkinje image in the eye image can be precisely recognized; and therefore scientific bases are provided for precise measurement of a fixation point, and the pupil recognition method and the Purkinje image recognition method are important for the precise measurement of the fixation point, and have the advantages of being scientific and reasonable, and high in practical value and the like.
Description
Technical field
The present invention relates to a kind of fixation point measuring device and correlation technique thereof, relate in particular to the speck recognition methods of admiring of a kind of device of the point of fixation position of measurement measurand on display surface based on video image and pupil, pul.
Background technology
Eyes be human from the world around vitals of obtaining information, also be the window of reflection people's mental activity, so a people's of Measurement accuracy fixation point can be his mental activity of research a kind of important means is provided.The fixation point measuring device has a good application prospect, such as can be used for evaluate advertisements Design Works institute's produce an effect in colony of consumer.Advertisement is as a kind of mode of intelligence transmission, and its purpose is to promote the sale of goods.Eye movement when the fixation point measuring device can be watched client attentively advertisement is recorded, by analyzing recorded data, sequencing when the advertising man can be well understood to client and watches advertisement attentively, and client is to the situation of change of certain a part of fixation time of advertisement, fixation times, twitching of the eyelid distance, pupil diameter or area etc., and then the mental activity can analyze client and watch advertisement the time.Do like this and help advertiser to recognize whether commercial audience goes to watch attentively advertisement by advertising man's intention, whether leak and seen the important information in the advertisement, such as Business Name, trade name and product card mark etc.
Present existing fixation point measuring method mainly contains three kinds: electro-oculogram method, induction coil method and video image method.People's eyeball is an electrical body, generally has several millivolts electric potential difference between cornea and the retina.When Rotation of eyeball, the electromotive force around the eyeball can be along with changing, and the electro-oculogram method utilizes this phenomenon to realize the fixation point measurement.The induction coil method is to utilize the principle of electromagnetic induction to measure fixation point.When measuring fixation point with the induction coil method, at first embed induction coil in the contact lens and be worn on the eye cornea, then apply 3 mutually orthogonal magnetic fields in around eyes, can determine the position of eyeball and towards, and then the fixation point position of definite measurand by the exciting current in the measuring coil.Electro-oculogram method and induction coil method all belong to contact measurement method, because need to place some measurement electrode at the circumocular skin of people when measuring fixation point with the electro-oculogram method; When measuring fixation point with the induction coil method, induction coil need to be placed on the eye cornea.Just because of this, when using these two kinds of methods to measure fixation point, can produce certain interference to measurand.Compare with front two kinds of methods, video image is owned by France namely takes eyes image with video camera in contactless measuring method, then according to the admire fixation point of the position measurement measurand of speck in image of pupil and pul.The certainty of measurement of existing video image method and reliability are all not ideal enough, such as the complicated structure owing to human eye, therefore can't describe exactly relation between fixation point position and the head orientation with one group of mathematical formulae, this is to cause having now the low main cause of video image method certainty of measurement.Can accurately identify in addition pupil in the eyes image and the pul speck of admiring, be the principal element that determines the reliability height of video image method.When taking eyes image with video camera, can be subject to the interference of various factors unavoidably and make and have noise in the eyes image, if the unreliable situation that mistake identification will occur of recognizer, and then would affect the reliability of video image method.
Summary of the invention
The objective of the invention is based on a present general inventive concept, provide a kind of noiseless, measure accurately, reliable fixation point measuring device, and provide realize fixation point accurately, the speck recognition methods of admiring of a kind of pupil identification method at reliable measurements key technology place and pul.
Realize that the technical scheme that the object of the invention adopts is, a kind of fixation point measuring device, it is characterized in that, it comprises support, video camera, light source, main frame, D.C. regulated power supply, basic display unit and auxiliary display, described supporting structure is, have base, be fixed with left column and right column at base, be fixed with E Tuo and Lower jaw support at left column and right column; The port that video camera, basic display unit and auxiliary display pass through separately respectively is electrically connected with main frame, and light source is electrically connected with D.C. regulated power supply.
Described light source is near-infrared luminous diode.
In measuring the process of fixation point, measurand is placed on lower jaw on the Lower jaw support in the support, simultaneously forehead is relied in the upper volume holder in the support, can make like this that the head of measurand is basic in the process of measuring fixation point to keep motionless.Auxiliary display is placed on the dead ahead of support, is used for representing the stimulus object that eye movement experiment needs use.The light that sends for fear of light source produces interference to measurand, adopts near-infrared luminous diode to do light source.The Infrared irradiation that light source is sent is at the face of measurand, then take the image of a certain eyes of measurand with video camera, for fear of natural light image quality is produced adverse influence, at the inner arrowband infrared fileter that is complementary with near-infrared light source of installing of the camera lens of video camera.
The light that near-infrared light source sends reflects at the cornea of measurand eyes, the pul that therefore can form a high brightness in the eyes image of the shot by camera speck of admiring.When the Rotation of eyeball of measurand, the relative position relation that the pupil in the eyes image and pul are admired between the speck also can change.In eyes image, identify respectively pupil and the pul speck of admiring, and calculate admire position offset (Δ between the speck center of pupil center and pul
x, Δ
y).With one group of mathematical formulae with the fixation point coordinate of measurand on auxiliary display surface (
X,
Y) and side-play amount (Δ
x, Δ
y) between set up contact, this group mathematical formulae can be described as fixation point and measures mathematical model.Before measuring fixation point, need to demarcate fixation point and measure mathematical model, namely definite fixation point is measured the unknown parameter in the mathematical model.In auxiliary display, show successively the spotting that some coordinates are known, the position is different, allow simultaneously measurand stare these spottings, in this course, can obtain some groups of fixation point coordinates (
X i ,
Y i ) and side-play amount (Δ
x i , Δ
y i ), then measure mathematical model by fixation point and make up a system of linear equations, find the solution this equation group and can try to achieve fixation point and measure unknown parameter in the mathematical model.When measuring fixation point, at first determine admire position offset between the speck center of pupil center and pul in the eyes image, then solved the coordinate of the fixation point of measurand on auxiliary display surface by fixation point measurement mathematical model.
Main frame plays an important role in fixation point measuring device of the present invention: the image that (1) acquisition camera is taken; (2) identification pupil and the pul speck of admiring in eyes image, and calculate admire position offset between the speck center of pupil center and pul; (3) demarcate fixation point and measure mathematical model; (4) calculate the fixation point coordinate; (5) play the stimulus object that the eye movement experiment is used.Main frame support multi-display connection mode also provides two video ports, and one of them video port links to each other with basic display unit, and another video port links to each other with auxiliary display.The shown content of basic display unit and auxiliary display is identical, but their purposes is different.Basic display unit is that the personnel for operation fixation point measuring device provide, and auxiliary display is used to tested object to represent eye movement to test employed stimulus object.
As previously mentioned, accurately identifying pupil in the eyes image and the pul speck of admiring is the committed step that realizes that fixation point is measured, for this reason:
Realize that the technical scheme that another purpose of the present invention adopts is, a kind of pupil identification method is characterized in that, it comprises following steps:
1) according to the gray threshold that sets, original eyes image is converted to bianry image;
2) each agglomerate in the bianry image (mutually disjoint closed area) is carried out labelling;
3) calculate the area of each agglomerate, that is: pixel count;
4) according to the agglomerate in the area threshold screening bianry image that sets;
5) in the agglomerate that satisfies the area threshold condition, determine which agglomerate is that pupil in the eyes image is through closed area that binaryzation generates.
Described step 1) further is: set gray threshold
T 1, with gray value in the original eyes image greater than threshold value
T 1Pixel regard background pixel as, and its gray value is set to 255; With gray value in the original eyes image less than or equal to threshold value
T 1Pixel regard object pixel as, and its gray value is set to 0.
Described step 4) further is: set two area thresholds
S p1
With
S p2
, wherein
S p1
＜
S p2
, from bianry image, choose those areas more than or equal to
S p1
And less than or equal to
S p2
Agglomerate.
Described step 5) further is: if there is not agglomerate to satisfy the area threshold condition that sets, then pupil recognition failures in the bianry image; If the area threshold condition of only having 1 agglomerate to satisfy in the bianry image to set, then pupil is identified successfully, and regards this agglomerate as pupil in the eyes image through closed area that binaryzation generates; If there is the agglomerate more than 2 or 2 to satisfy the area threshold condition that sets in the bianry image, then respectively by the outline point fitted ellipse of each agglomerate, and regard outline as pupil in the eyes image through closed area that binaryzation generates close to that agglomerate of circle.
Realize that the technical scheme that another object of the present invention adopts is, the speck recognition methods of admiring of a kind of pul is characterized in that it comprises following steps:
(1) according to the gray threshold that sets, original eyes image is converted to bianry image;
(2) each agglomerate in the bianry image (mutually disjoint closed area) is carried out labelling;
(3) calculate the area of each agglomerate, that is: pixel count;
(4) according to the agglomerate in the area threshold screening bianry image that sets;
(5) in the agglomerate that satisfies the area threshold condition, determine which agglomerate is that pul in the eyes image is admired speck through closed area that binaryzation generates.
Described step (1) further is: set gray threshold
T 2, with gray value in the original eyes image more than or equal to threshold value
T 2Pixel regard object pixel as, and its gray value is set to 0; With gray value in the original eyes image less than threshold value
T 2Pixel regard background pixel as, and its gray value is set to 255.
Described step (4) further is: set two area thresholds
S g1
With
S g2
, wherein
S g1
＜
S g2
, from bianry image, choose those areas more than or equal to
S g1
And less than or equal to
S g2
Agglomerate.
Described step (5) further is: if the area threshold condition that does not have agglomerate to satisfy in the bianry image to set, then the pul speck recognition failures of admiring; If the area threshold condition of only having 1 agglomerate to satisfy in the bianry image to set, then the pul speck of admiring is identified successfully, and regards this agglomerate as pul in the eyes image admire speck through closed area that binaryzation generates; If there is the agglomerate more than 2 or 2 to satisfy the area threshold condition that sets in the bianry image, then calculate respectively the centre-to-centre spacing between each agglomerate and the pupil, that is: pixel count, and regard that nearest agglomerate as pul in the eyes image admire speck through closed area that binaryzation generates.
Fixation point measuring device of the present invention is based on the fixation point measuring device of video image, has noiselessly, measures the advantages such as accurate, reliable; Can accurately identify pupil in the eyes image by pupil identification method of the present invention, can accurately identify pul in the eyes image speck of admiring by the pul of the present invention speck recognition methods of admiring, thereby for the Measurement accuracy of fixation point provides scientific basis, it is the key point of the Measurement accuracy of fixation point, it is reasonable to have methodological science, the practical value advantages of higher.
Description of drawings
Fig. 1 is fixation point measuring device structural representation of the present invention;
Fig. 2 shows the flow chart of identification pupil in eyes image;
Fig. 3 shows in eyes image the admire flow chart of speck of identification pul;
Fig. 4 shows the eyes image of taking with video camera;
Fig. 5 shows the result of the image binaryzation in the pupil identifying;
Fig. 6 shows the result of the agglomerate screening in the pupil identifying;
Fig. 7 shows the result of the agglomerate outline point fitted ellipse in the pupil identifying;
Fig. 8 shows the admire result of the image binaryzation in the speck identifying of pul;
Fig. 9 shows the admire result of the agglomerate screening in the speck identifying of pul.
The specific embodiment
Below in conjunction with accompanying drawing, describe preferred embodiment of the present invention in detail:
With reference to Fig. 1, fixation point measuring device of the present invention comprises support 1, is placed on light source 2 and the video camera 3 of support 1 front lower place, main frame 4, and basic display unit 5 is placed on auxiliary display 6 and the D.C. regulated power supply 7 of support 1 dead ahead.The structure of support 1 is, is fixed with left column 102 and right column 103 on the base 101, is fixed with Lower jaw support 104 and upper volume holder 105 at left column 102 and right column 10.When measuring fixation point, measurand is placed on lower jaw on the Lower jaw support 104, upper volume is relied in the upper volume holder 105 simultaneously, can make like this head basic maintenance in the process of measuring fixation point of measurand motionless.Main frame 4 plays an important role in the device of measuring fixation point, such as images acquired; The identification pupil; Calculate the stimulus object of fixation point coordinate and broadcast eye movement experiment use etc., main frame 4 supports the multi-display connection modes also to provide two video ports, and one of them video port links to each other with basic display unit 5, and another video port links to each other with auxiliary display 6.The shown content of basic display unit 5 and auxiliary display 6 is identical, but their purposes is different.Basic display unit 5 is that auxiliary display 6 then is used to tested object to represent eye movement and tests employed stimulus object for the personnel that operate the fixation point measuring device provide.Light source 2 is by D.C. regulated power supply 7 power supplies.Then the rayed that light source 2 sends takes the image of a certain eyes of measurand at the face of measurand with video camera 3.The light that sends for fear of light source 2 produces interference to measurand, adopt near infrared diode to do light source, simultaneously for fear of natural light image quality is produced adverse influence, arrowband infrared fileter with the light source coupling is installed in the camera lens of video camera 3, doing light source 2 such as the infrared diode that adopts 850nm, need to the mounting center wavelength be the arrowband infrared fileter of 850nm in the camera lens of video camera 3 then.Therefore the light that light source sends reflects at the cornea of measurand eyes, can generate a pul as shown in Figure 4 speck 401 of admiring in the captured image of video camera 3.When measurand changed in the position of auxiliary display 6 lip-deep fixation pointes, the relative position that the pupil 402 in the eyes image and pul are admired between the speck 401 also can change.In eyes image, identify respectively pupil 402 and the pul hot spot 401 of admiring, then calculate admire position deviation (Δ between hot spot 401 centers of pupil 402 centers and pul
x, Δ
y).The coordinate of center in eyes image of supposing pupil 402 for (
x p ,
y p ), pul admire speck 401 the coordinate of center in eyes image for (
x g ,
y g ), then:
With one group of mathematical formulae with measurand the coordinate of auxiliary display 6 lip-deep fixation pointes (
X,
Y) and position deviation (Δ
x, Δ
y) between set up contact:
This group mathematical formulae is exactly for the mathematical model of measuring fixation point, wherein
a i With
b i (
i=1,2 ..., 6) and be model parameter.Before measuring the fixation point coordinate, at first should demarcate fixation point and measure mathematical model, namely determine the numerical value of model parameter.In auxiliary display 6, show successively the spotting that some coordinates are known, the position is different, allow simultaneously tested object stare these spottings, in this course, can obtain
n(
n〉=5) group fixation point coordinate (
X i ,
Y i ) and side-play amount (Δ
x i , Δ
y i ), then measure mathematical model by fixation point and make up one 2
nThe system of linear equations of dimension:
Find the solution this equation group, can try to achieve the model parameter in the fixation point measurement mathematical model
a i With
b i (
i=1,2 ..., 6) numerical value.Measure the fixation point coordinate time, identification pupil 402 and the pul speck 401 of admiring in eyes image at first, and calculate the two position deviation (Δ
x, Δ
y), then with Δ
xAnd Δ
ySubstitution fixation point measurement model just can be tried to achieve measurand at the coordinate of auxiliary display 6 lip-deep fixation pointes.
As previously mentioned, accurately identifying pupil 402 in the eyes image and the pul speck 401 of admiring is the keys that realize that fixation point is measured.For this reason, Fig. 2 shows a kind of pupil identification method of the present invention, may further comprise the steps:
Step 203 is according to the agglomerate in the area threshold screening bianry image that sets.Such as setting two area thresholds
S p1
With
S p2
, wherein
S p1
＜
S p2
, from bianry image, choose those areas more than or equal to
S p1
And less than or equal to
S p2
Agglomerate.Shown in Figure 6 is the result who obtains according to behind the agglomerate in the area threshold screening bianry image shown in Figure 5, the area threshold that wherein adopts
S p1
Be 497 pixel counts;
S p2
Be 2000 pixel counts.
Fig. 3 shows a kind of pul of the present invention speck recognition methods of admiring, and may further comprise the steps:
Step 306 judges whether the agglomerate quantity that satisfies the area threshold condition in the bianry image equals 1.Equal 1 if satisfy the agglomerate quantity of area threshold condition in the bianry image, then execution in step 307, otherwise execution in step 308.
Step 307 is regarded this agglomerate as the pul in the eyes image admire speck through the closed area that binaryzation generates, and finishes the pul speck identifying of admiring.
Claims (10)
1. fixation point measuring device, it is characterized in that: it comprises support, video camera, light source, main frame, D.C. regulated power supply, basic display unit and auxiliary display, described supporting structure is, has base, be fixed with left column and right column at base, be fixed with E Tuo and Lower jaw support at left column and right column; The port that video camera, basic display unit and auxiliary display pass through separately respectively is electrically connected with main frame, and light source is electrically connected with D.C. regulated power supply.
2. fixation point measuring device according to claim 1, it is characterized in that: described light source is near-infrared luminous diode.
3. pupil identification method, it is characterized in that: it comprises following steps:
1) according to the gray threshold that sets, original eyes image is converted to bianry image;
2) each agglomerate in the bianry image is carried out labelling;
3) calculate the area of each agglomerate, that is: pixel count;
4) according to the agglomerate in the area threshold screening bianry image that sets;
5) in the agglomerate that satisfies the area threshold condition, determine which agglomerate is that pupil in the eyes image is through closed area that binaryzation generates.
4. a kind of pupil identification method according to claim 3, it is characterized in that: described step 1) further is: set gray threshold
T 1, with gray value in the original eyes image greater than threshold value
T 1Pixel regard background pixel as, and its gray value is set to 255; With gray value in the original eyes image less than or equal to threshold value
T 1Pixel regard object pixel as, and its gray value is set to 0.
5. a kind of pupil identification method according to claim 3, it is characterized in that: described step 4) further is: set two area thresholds
S p1
With
S p2
, wherein
S p1
＜
S p2
, from bianry image, choose those areas more than or equal to
S p1
And less than or equal to
S p2
Agglomerate.
6. a kind of pupil identification method according to claim 3, it is characterized in that: described step 5) further is: if there is not agglomerate to satisfy the area threshold condition that sets, then pupil recognition failures in the bianry image; If the area threshold condition of only having 1 agglomerate to satisfy in the bianry image to set, then pupil is identified successfully, and regards this agglomerate as pupil in the eyes image through closed area that binaryzation generates; If there is the agglomerate more than 2 or 2 to satisfy the area threshold condition that sets in the bianry image, then respectively by the outline point fitted ellipse of each agglomerate, and regard outline as pupil in the eyes image through closed area that binaryzation generates close to that agglomerate of circle.
7. pul speck recognition methods of admiring is characterized in that it comprises following steps:
(1) according to the gray threshold that sets, original eyes image is converted to bianry image;
(2) each agglomerate in the bianry image is carried out labelling;
(3) calculate the area of each agglomerate, that is: pixel count;
(4) according to the agglomerate in the area threshold screening bianry image that sets;
(5) in the agglomerate that satisfies the area threshold condition, determine which agglomerate is that pul in the eyes image is admired speck through closed area that binaryzation generates.
8. the pul according to claim 7 speck recognition methods of admiring, it is characterized in that: described step (1) further is: set gray threshold
T 2, with gray value in the original eyes image more than or equal to threshold value
T 2Pixel regard object pixel as, and its gray value is set to 0; With gray value in the original eyes image less than threshold value
T 2Pixel regard background pixel as, and its gray value is set to 255.
9. the pul according to claim 7 speck recognition methods of admiring, it is characterized in that: described step (4) further is: set two area thresholds
S g1
With
S g2
, wherein
S g1
＜
S g2
, from bianry image, choose those areas more than or equal to
S g1
And less than or equal to
S g2
Agglomerate.
10. the pul according to claim 7 speck recognition methods of admiring, it is characterized in that: described step (5) further is: if there is not agglomerate to satisfy the area threshold condition that sets in the bianry image, the pul speck recognition failures of admiring then; If the area threshold condition of only having 1 agglomerate to satisfy in the bianry image to set, then the pul speck of admiring is identified successfully, and regards this agglomerate as pul in the eyes image admire speck through closed area that binaryzation generates; If there is the agglomerate more than 2 or 2 to satisfy the area threshold condition that sets in the bianry image, then calculate respectively the centre-to-centre spacing between each agglomerate and the pupil, that is: pixel count, and regard that nearest agglomerate as pul in the eyes image admire speck through closed area that binaryzation generates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012102311449A CN103054548A (en) | 2012-07-05 | 2012-07-05 | Fixation point measurement device and pupil recognition method and Purkinje image recognition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012102311449A CN103054548A (en) | 2012-07-05 | 2012-07-05 | Fixation point measurement device and pupil recognition method and Purkinje image recognition method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103054548A true CN103054548A (en) | 2013-04-24 |
Family
ID=48097671
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012102311449A Pending CN103054548A (en) | 2012-07-05 | 2012-07-05 | Fixation point measurement device and pupil recognition method and Purkinje image recognition method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103054548A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103356163A (en) * | 2013-07-08 | 2013-10-23 | 东北电力大学 | Fixation point measurement device and method based on video images and artificial neural network |
| CN104199544A (en) * | 2014-08-28 | 2014-12-10 | 华南理工大学 | Targeted advertisement delivery method based on eye gaze tracking |
| CN105358045A (en) * | 2013-07-09 | 2016-02-24 | 斯玛特艾公司 | Eye gaze imaging |
| CN105955465A (en) * | 2016-04-25 | 2016-09-21 | 华南师范大学 | Desktop portable sight line tracking method and apparatus |
| CN110929672A (en) * | 2019-11-28 | 2020-03-27 | 联想(北京)有限公司 | Pupil positioning method and electronic equipment |
| CN111027502A (en) * | 2019-12-17 | 2020-04-17 | Oppo广东移动通信有限公司 | Eye image positioning method and device, electronic equipment and computer storage medium |
| WO2021134710A1 (en) * | 2019-12-31 | 2021-07-08 | 深圳市大疆创新科技有限公司 | Control method and related device |
| CN113693553A (en) * | 2021-09-14 | 2021-11-26 | 首都医科大学附属北京儿童医院 | Method and device for eliminating inter-cooling effect interference in eye movement detection |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08145644A (en) * | 1994-11-28 | 1996-06-07 | Agency Of Ind Science & Technol | Elliptic approximation measuring system strong against noise |
| JP2002102172A (en) * | 2000-07-28 | 2002-04-09 | National Institute Of Advanced Industrial & Technology | Method and system for detecting visual axis |
| JP2005013752A (en) * | 2000-07-28 | 2005-01-20 | National Institute Of Advanced Industrial & Technology | Sight line detecting system |
| CN101172034A (en) * | 2006-11-03 | 2008-05-07 | 上海迪康医学生物技术有限公司 | Eyeball moving track detecting method |
| CN101206116A (en) * | 2007-12-07 | 2008-06-25 | 北京机械工业学院 | Goal spot global automatic positioning method |
| CN101344919A (en) * | 2008-08-05 | 2009-01-14 | 华南理工大学 | Sight tracing method and disabled assisting system using the same |
| CN101730500A (en) * | 2007-03-08 | 2010-06-09 | 北英属哥伦比亚大学 | The equipment and the method that are used for objective perimetry visual field test |
| CN102149325A (en) * | 2008-09-26 | 2011-08-10 | 松下电器产业株式会社 | Line-of-sight direction determination device and line-of-sight direction determination method |
| WO2012055444A1 (en) * | 2010-10-29 | 2012-05-03 | IT-Universitetet i København | Method of determining reflections of light |
-
2012
- 2012-07-05 CN CN2012102311449A patent/CN103054548A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08145644A (en) * | 1994-11-28 | 1996-06-07 | Agency Of Ind Science & Technol | Elliptic approximation measuring system strong against noise |
| JP2002102172A (en) * | 2000-07-28 | 2002-04-09 | National Institute Of Advanced Industrial & Technology | Method and system for detecting visual axis |
| JP2005013752A (en) * | 2000-07-28 | 2005-01-20 | National Institute Of Advanced Industrial & Technology | Sight line detecting system |
| CN101172034A (en) * | 2006-11-03 | 2008-05-07 | 上海迪康医学生物技术有限公司 | Eyeball moving track detecting method |
| CN101730500A (en) * | 2007-03-08 | 2010-06-09 | 北英属哥伦比亚大学 | The equipment and the method that are used for objective perimetry visual field test |
| CN101206116A (en) * | 2007-12-07 | 2008-06-25 | 北京机械工业学院 | Goal spot global automatic positioning method |
| CN101344919A (en) * | 2008-08-05 | 2009-01-14 | 华南理工大学 | Sight tracing method and disabled assisting system using the same |
| CN102149325A (en) * | 2008-09-26 | 2011-08-10 | 松下电器产业株式会社 | Line-of-sight direction determination device and line-of-sight direction determination method |
| WO2012055444A1 (en) * | 2010-10-29 | 2012-05-03 | IT-Universitetet i København | Method of determining reflections of light |
Non-Patent Citations (2)
| Title |
|---|
| 周薇: "眼动视频图像处理与跟踪系统研究", 《硕士学位论文》, 1 January 2007 (2007-01-01) * |
| 迟健男 等.: "视线追踪系统眼部特征检测及视线方向计算方法研究", 《控制与决策》, 30 September 2009 (2009-09-30) * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103356163A (en) * | 2013-07-08 | 2013-10-23 | 东北电力大学 | Fixation point measurement device and method based on video images and artificial neural network |
| CN103356163B (en) * | 2013-07-08 | 2016-03-30 | 东北电力大学 | Based on fixation point measuring device and the method thereof of video image and artificial neural network |
| CN105358045A (en) * | 2013-07-09 | 2016-02-24 | 斯玛特艾公司 | Eye gaze imaging |
| CN104199544A (en) * | 2014-08-28 | 2014-12-10 | 华南理工大学 | Targeted advertisement delivery method based on eye gaze tracking |
| CN104199544B (en) * | 2014-08-28 | 2018-06-22 | 华南理工大学 | Advertisement orientation put-on method based on eye tracking |
| CN105955465A (en) * | 2016-04-25 | 2016-09-21 | 华南师范大学 | Desktop portable sight line tracking method and apparatus |
| CN110929672A (en) * | 2019-11-28 | 2020-03-27 | 联想(北京)有限公司 | Pupil positioning method and electronic equipment |
| CN110929672B (en) * | 2019-11-28 | 2024-03-01 | 联想(北京)有限公司 | Pupil positioning method and electronic equipment |
| CN111027502A (en) * | 2019-12-17 | 2020-04-17 | Oppo广东移动通信有限公司 | Eye image positioning method and device, electronic equipment and computer storage medium |
| WO2021134710A1 (en) * | 2019-12-31 | 2021-07-08 | 深圳市大疆创新科技有限公司 | Control method and related device |
| CN113693553A (en) * | 2021-09-14 | 2021-11-26 | 首都医科大学附属北京儿童医院 | Method and device for eliminating inter-cooling effect interference in eye movement detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103054548A (en) | Fixation point measurement device and pupil recognition method and Purkinje image recognition method | |
| CN104146721B (en) | A kind of emotion bandwidth assay method and system | |
| KR101535432B1 (en) | Contents valuation system and contents valuating method using the system | |
| CN108565023A (en) | A kind of children disease prevention and control monitoring method, device and system | |
| CN103748598A (en) | Systems and methods for identifying gaze tracking scene reference locations | |
| CN105955465A (en) | Desktop portable sight line tracking method and apparatus | |
| CN103356163A (en) | Fixation point measurement device and method based on video images and artificial neural network | |
| CN103679180A (en) | Sight tracking method based on single light source of single camera | |
| CN205054771U (en) | Domestic medical detector of intelligence based on massage armchair | |
| Chouinard et al. | Using automatic face analysis to score infant behaviour from video collected online | |
| CN109528217A (en) | A kind of mood detection and method for early warning based on physiological vibrations analysis | |
| CN107085464B (en) | Emotion identification method based on P300 characters spells task | |
| CN110135242A (en) | Emotion identification device and method based on low resolution infrared thermal imaging depth perception | |
| Giannakakis et al. | Evaluation of head pose features for stress detection and classification | |
| Yan et al. | Measuring dynamic micro-expressions via feature extraction methods | |
| CN109902574A (en) | The high-risk personnel detection device and method of human body presentation variation measurement human body mood | |
| US20230043838A1 (en) | Method for determining preference, and device for determining preference using same | |
| Wallace et al. | Contactless remote assessment of heart rate and respiration rate using video magnification | |
| Hossain et al. | Facial emotion verification by infrared image | |
| CN109938727A (en) | Non-human primate 3D vision stimulation test system and method | |
| Casson et al. | Enabling free movement EEG tasks by eye fixation and gyroscope motion correction: EEG effects of color priming in dress shopping | |
| CN106055083B (en) | Method for monitoring the visual behaviour of people | |
| CN105100791B (en) | A kind of system and method for measuring stereoscopic vision comfort level | |
| O'Toole et al. | The neural representation of faces and bodies in motion and at rest | |
| CN110115796A (en) | The awake system of fatigue detecting and rush of eye movement parameter monitoring based on N-range image processing algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130424 |