CN107092872A - A kind of eye moves recognition methods and device - Google Patents
A kind of eye moves recognition methods and device Download PDFInfo
- Publication number
- CN107092872A CN107092872A CN201710226276.5A CN201710226276A CN107092872A CN 107092872 A CN107092872 A CN 107092872A CN 201710226276 A CN201710226276 A CN 201710226276A CN 107092872 A CN107092872 A CN 107092872A
- Authority
- CN
- China
- Prior art keywords
- eye
- summit
- point
- distance
- pupil center
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
Recognition methods and device are moved the present invention relates to a kind of eye, wherein method comprises the following steps：Step 1, user's eye picture is persistently obtained with prefixed time interval by camera；Step 2, continuously each frame picture is analyzed, calculate and store pupil center's point to the distance of eye socket upper and lower, left and right four direction；Step 3, according to the distance change of pupil center's point to eye socket upper and lower, left and right four direction judge that eye moves direction, i.e. using summit, lower summit, leftmost vertices, right side apex coordinate on the orbital border curve as fixed coordinates, calculate pupil center's point coordinates in each frame picture continuously obtained and judge that eye moves direction to this 4 points of distance, and according to this 4 points distance change in every frame picture.Compared with existing eye moves direction determination process, this method can save a large amount of computings, improve calculating speed and reduce hardware implementation cost.
Description
Technical field
The present invention relates to Intelligent hardware technical field, recognition methods and device are moved more specifically to a kind of eye.
Background technology
In human-computer interaction technique field, although currently having there is the trial of many emerging interactive modes, such as body feeling interaction,
The modes such as eye-tracking, interactive voice, bio-identification, but most interactive mode utilization rate be not it is very high, yet not
Into in business application popularization truly, more without which kind of man-machine interaction mode, can reach people can have no obstacle,
The level indiscriminately ad. as one wishes exchanged with equipment (machine).In addition to the multi-point touch interactive mode gradually popularized, other are big
Partial man-machine interaction mode need to be broken out of an encirclement in technology and stability in use.
The content of the invention
The technical problem to be solved in the present invention is, the drawbacks described above for prior art there is provided a kind of eye moves identification side
Method and device.
The technical solution adopted for the present invention to solve the technical problems is：
Construct a kind of eye and move recognition methods, wherein, comprise the following steps：
Step 1, user's eye picture is persistently obtained with prefixed time interval by camera；
Step 2, continuously each frame picture is analyzed, calculate and store pupil center's point to eye socket upper and lower, left and right
The distance of four direction；
Step 3, according to the distance change of pupil center's point to eye socket upper and lower, left and right four direction judge that eye moves direction,
I.e. using summit, lower summit, leftmost vertices, right side apex coordinate on the orbital border curve as fixed coordinates, calculating is continuously obtained
Each frame picture in pupil center's point coordinates to this 4 points of distance, and according to this 4 points distance change in every frame picture
Judge that eye moves direction.
Eye of the present invention moves recognition methods, wherein, the step 2 is specifically included：
Step 2-1, the extraction orbital border curve, obtain summit, lower summit, a left side on the orbital border curve respectively
Side summit, the coordinate on right side summit；
Step 2-2, extraction pupil center point coordinates；
Step 2-3, calculating pupil center's point coordinates are respectively to summit, lower summit, a left side on the orbital border curve
Side summit, the relative distance of right side apex coordinate.
Identifying device is moved present invention also offers a kind of eye, wherein, including：
Photographing module, for persistently obtaining user's eye picture with prefixed time interval by camera；
Distance calculation module, for continuously analyzing each frame picture, calculates and stores pupil center's point to eye socket
The distance of upper and lower, left and right four direction；
Judge module, for using summit on the orbital border curve, lower summit, leftmost vertices, right side apex coordinate as
Fixed coordinates, calculate in each frame picture for continuously obtaining pupil center's point coordinates to this 4 points of distance, and according to every frame figure
The distance change that 4 points of this in piece judges that eye moves direction.
Eye of the present invention moves identifying device, wherein, the distance calculation module includes：
Coordinate calculating unit, for extracting the orbital border curve, obtain respectively summit on the orbital border curve,
Lower summit, leftmost vertices, the coordinate on right side summit, extract pupil center's point coordinates；
Metrics calculation unit, for calculate pupil center's point coordinates respectively to summit on the orbital border curve,
Lower summit, leftmost vertices, the relative distance of right side apex coordinate.
The beneficial effects of the present invention are：By calculating and storing acquired every frame picture pupil center point to eye socket
The distance of upper and lower, left and right four direction, and according to the distance change of pupil center's point to eye socket upper and lower, left and right four direction
Judge that eye moves direction, can quickly realize that eye moves the judgement in direction, compared with existing eye moves direction determination process, this method can be saved
A large amount of computings are saved, calculating speed is improved and reduces hardware implementation cost.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below in conjunction with accompanying drawing and reality
Applying example, the invention will be further described, and drawings in the following description are only the section Example of the present invention, for this area
For those of ordinary skill, on the premise of not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings：
Fig. 1 is that the eye of present pre-ferred embodiments moves recognition methods flow chart；
Fig. 2 a, 2b, 2c, 2d are 4 frame eye picture schematic diagrames of the lasting acquisition of present pre-ferred embodiments；
Fig. 3 is that the eye of present pre-ferred embodiments moves identifying device theory diagram.
Embodiment
In order that the purpose, technical scheme and advantage of the embodiment of the present invention are clearer, below in conjunction with present invention implementation
Technical scheme in example carries out clear, complete description, it is clear that described embodiment is the section Example of the present invention, and
It is not all of embodiment.Based on embodiments of the invention, those of ordinary skill in the art are not before creative work is paid
The every other embodiment obtained is put, protection scope of the present invention is belonged to.
The eye of present pre-ferred embodiments moves recognition methods flow as shown in figure 1, comprising the following steps：
Step S10, user's eye picture is persistently obtained with prefixed time interval by camera；
Step S20, continuously each frame picture is analyzed, calculate and store pupil center's point to eye socket it is upper and lower, left,
The distance of right four direction；
Step S30, judge according to the distance change of pupil center's point to eye socket upper and lower, left and right four direction the dynamic side of eye
To.
The inventive method is by calculating and storing acquired every frame picture pupil center point to eye socket upper and lower, left and right four
The distance in individual direction, and judge that eye moves direction according to the distance change of pupil center's point to eye socket upper and lower, left and right four direction,
It can quickly realize that eye moves the judgement in direction, compared with existing eye moves direction determination process, this method can save a large amount of computings, carry
High calculating speed simultaneously reduces hardware implementation cost.
Above-mentioned eye is moved in recognition methods, and step S20 is specifically included：
Step S21, extract orbital border curve, respectively obtain orbital border curve on summit, lower summit, leftmost vertices,
The coordinate on right side summit；
Step S22, extraction pupil center point coordinates；
Step S23, calculating pupil center point coordinates are respectively to summit, lower summit, leftmost vertices, the right side on orbital border curve
The relative distance of side apex coordinate.
Above-mentioned eye is moved in recognition methods, and step S30 is specifically included：
Using summit, lower summit, leftmost vertices, right side apex coordinate on orbital border curve as fixed coordinates, calculate continuous
Pupil center's point coordinates becomes to this 4 points of distance, and according to this 4 points distance in every frame picture in each frame picture obtained
Change judges that eye moves direction.
Above-mentioned eye is moved in recognition methods, and step S30 is specifically included：
Each frame picture of acquisition is placed in same coordinate, summit on orbital border curve, lower summit, leftmost vertices,
Right side apex coordinate, and pupil center's point coordinates are moving point；
Pupil center's point coordinates is calculated in each frame picture for continuously obtaining to other 4 points of distances, and according to every frame figure
The distance change that 4 points of this in piece judges that eye moves direction.
Fig. 2 a, 2b, 2c, 2d are 4 frame eye picture schematic diagrames of lasting acquisition, from Fig. 2 a sequentially into Fig. 2 b, 2c, 2d, pupil
Move to the left in hole.Using summit c, lower summit d, leftmost vertices a, right side summit b coordinates on orbital border curve as fixed coordinates,
Calculate respectively in this 4 frame picture, pupil center's point e coordinates to this 4 points of distance, four distance values be designated as respectively e-c, e-d,
E-a, e-b, by list, it can be found that tri- distance values of e-c, e-d, e-b become big successively, e-a then diminishes, it can be determined that go out
Pupil is moved to eye socket leftmost vertices direction.
In another embodiment, pupil direction movement from upper summit c and leftmost vertices a to Fig. 2 a, i.e., move to upper left side
Dynamic, it is to become larger that above-mentioned distance value e-d, e-b can be now calculated by the above method, and distance value e-a, e-c then by
Gradual change is small.
In the particular embodiment, can by the change of tetra- values of e-c, e-d, e-a, e-b respectively big, two states that diminish with
Permutation and combination form lists corresponding eye and moves direction state outcome, obtains above-mentioned e-c, e-d, e-a, e-b tetra- in calculating and is worth it
Afterwards, table look-at obtains corresponding eye and moves walking direction result, can further improve judgement speed.
In an alternative embodiment of the invention, additionally provide a kind of eye and move identifying device, as shown in figure 3, specifically including：Shooting
Module 10, for persistently obtaining user's eye picture with prefixed time interval by camera；Distance calculation module 20, for even
It is continuous that each frame picture is analyzed, calculate and store pupil center's point to the distance of eye socket upper and lower, left and right four direction；Sentence
Disconnected module 30, for judging that eye moves direction according to the distance change of pupil center's point to eye socket upper and lower, left and right four direction.This
Invention is by calculating and stores acquired every frame picture pupil center point to the distance of eye socket upper and lower, left and right four direction,
And judge that eye moves direction according to the distance change of pupil center's point to eye socket upper and lower, left and right four direction, can quickly it realize
The judgement in the dynamic direction of eye, compared with existing eye moves direction determination process, this method can save a large amount of computings, improve calculating speed simultaneously
Reduce hardware implementation cost.
In above-described embodiment, photographing module can be single camera, or camera module.Distance calculation module, sentence
Disconnected module can be solidified in the hardware circuit module on FPGA plates, realize that data are calculated by PLD.
Above-mentioned eye is moved in identifying device, and distance calculation module includes：Coordinate calculating unit, it is bent for extracting orbital border
Line, obtains summit, lower summit, leftmost vertices, the coordinate on right side summit on orbital border curve respectively, extracts pupil center's point and sits
Mark；Metrics calculation unit, for calculating pupil center's point coordinates respectively to summit, lower summit, left side top on orbital border curve
The relative distance of point, right side apex coordinate.
Above-mentioned eye is moved in identifying device, and judge module includes the first judging unit, for summit on orbital border curve,
Lower summit, leftmost vertices, right side apex coordinate are fixed coordinates, calculate pupil center's point in each frame picture continuously obtained and sit
Mark judges that eye moves direction to this 4 points of distance, and according to this 4 points distance change in every frame picture.
Above-mentioned eye is moved in identifying device, and judge module includes the second judging unit, for each frame picture of acquisition to be put
In same coordinate, summit, lower summit, leftmost vertices, right side apex coordinate on orbital border curve, and pupil center's point are sat
Mark is moving point, calculates in each frame picture for continuously obtaining pupil center's point coordinates to other 4 points of distances, and according to
This 4 points distance change judges that eye moves direction in per frame picture.
It should be appreciated that for those of ordinary skills, can according to the above description be improved or converted,
And all these modifications and variations should all belong to the protection domain of appended claims of the present invention.
Claims (4)
1. a kind of eye moves recognition methods, it is characterised in that comprise the following steps：
Step 1, user's eye picture is persistently obtained with prefixed time interval by camera；
Step 2, continuously each frame picture is analyzed, calculate and store pupil center's point to eye socket upper and lower, left and right four
The distance in direction；
Step 3, according to the distance change of pupil center's point to eye socket upper and lower, left and right four direction judge that eye moves direction, i.e., with
Summit, lower summit, leftmost vertices, right side apex coordinate are fixed coordinates on the orbital border curve, calculate what is continuously obtained
Pupil center's point coordinates judges to this 4 points of distance, and according to this 4 points distance change in every frame picture in each frame picture
The dynamic direction of eye.
2. eye according to claim 1 moves recognition methods, it is characterised in that the step 2 is specifically included：
Step 2-1, the extraction orbital border curve, obtain summit on the orbital border curve, lower summit, left side top respectively
Point, the coordinate on right side summit；
Step 2-2, extraction pupil center point coordinates；
Step 2-3, calculating pupil center's point coordinates are respectively to summit, lower summit, left side top on the orbital border curve
The relative distance of point, right side apex coordinate.
3. a kind of eye moves identifying device, it is characterised in that including：
Photographing module, for persistently obtaining user's eye picture with prefixed time interval by camera；
Distance calculation module, for continuously analyzing each frame picture, calculate and store pupil center's point to eye socket,
Under, the distance of left and right four direction；
Judge module, for using summit, lower summit, leftmost vertices, right side apex coordinate on the orbital border curve as fixation
Coordinate, calculates in each frame picture for continuously obtaining pupil center's point coordinates to this 4 points of distance, and according in every frame picture
This 4 points distance change judges that eye moves direction.
4. eye according to claim 3 moves identifying device, it is characterised in that the distance calculation module includes：
Coordinate calculating unit, for extracting the orbital border curve, obtains summit, lower top on the orbital border curve respectively
Point, leftmost vertices, the coordinate on right side summit, extract pupil center's point coordinates；
Metrics calculation unit, for calculating pupil center's point coordinates respectively to summit, lower top on the orbital border curve
Point, leftmost vertices, the relative distance of right side apex coordinate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710226276.5A CN107092872A (en) | 2017-04-08 | 2017-04-08 | A kind of eye moves recognition methods and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710226276.5A CN107092872A (en) | 2017-04-08 | 2017-04-08 | A kind of eye moves recognition methods and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107092872A true CN107092872A (en) | 2017-08-25 |
Family
ID=59636821
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710226276.5A Pending CN107092872A (en) | 2017-04-08 | 2017-04-08 | A kind of eye moves recognition methods and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107092872A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110148075A (en) * | 2019-06-19 | 2019-08-20 | 重庆工商职业学院 | A kind of learning evaluation method and device based on artificial intelligence |
| CN110162187A (en) * | 2019-06-19 | 2019-08-23 | 重庆工商职业学院 | Eyeball mobile identification method and device based on artificial intelligence |
| CN110298569A (en) * | 2019-06-19 | 2019-10-01 | 重庆工商职业学院 | Learning evaluation method and device based on eye movement identification |
| CN110297539A (en) * | 2019-06-19 | 2019-10-01 | 重庆工商职业学院 | A kind of eye movement recognition methods and device based on artificial intelligence |
| US10860098B1 (en) | 2019-12-30 | 2020-12-08 | Hulu, LLC | Gesture-based eye tracking |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103885589A (en) * | 2014-03-06 | 2014-06-25 | 华为技术有限公司 | Eye movement tracking method and device |
| CN104793732A (en) * | 2015-01-04 | 2015-07-22 | 北京君正集成电路股份有限公司 | Intelligent glasses operation method and intelligent glasses |
| US20160034029A1 (en) * | 2011-12-14 | 2016-02-04 | Kenton M. Lyons | Gaze activated content transfer system |
-
2017
- 2017-04-08 CN CN201710226276.5A patent/CN107092872A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160034029A1 (en) * | 2011-12-14 | 2016-02-04 | Kenton M. Lyons | Gaze activated content transfer system |
| CN103885589A (en) * | 2014-03-06 | 2014-06-25 | 华为技术有限公司 | Eye movement tracking method and device |
| CN104793732A (en) * | 2015-01-04 | 2015-07-22 | 北京君正集成电路股份有限公司 | Intelligent glasses operation method and intelligent glasses |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110148075A (en) * | 2019-06-19 | 2019-08-20 | 重庆工商职业学院 | A kind of learning evaluation method and device based on artificial intelligence |
| CN110162187A (en) * | 2019-06-19 | 2019-08-23 | 重庆工商职业学院 | Eyeball mobile identification method and device based on artificial intelligence |
| CN110298569A (en) * | 2019-06-19 | 2019-10-01 | 重庆工商职业学院 | Learning evaluation method and device based on eye movement identification |
| CN110297539A (en) * | 2019-06-19 | 2019-10-01 | 重庆工商职业学院 | A kind of eye movement recognition methods and device based on artificial intelligence |
| CN110298569B (en) * | 2019-06-19 | 2022-04-08 | 重庆工商职业学院 | Learning evaluation method and device based on eye movement recognition |
| US10860098B1 (en) | 2019-12-30 | 2020-12-08 | Hulu, LLC | Gesture-based eye tracking |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107092872A (en) | A kind of eye moves recognition methods and device | |
| CN106295476B (en) | Face key point localization method and device | |
| CN105930767A (en) | Human body skeleton-based action recognition method | |
| CN108229293A (en) | Face image processing process, device and electronic equipment | |
| CN105447823B (en) | A kind of image processing method and a kind of electronic equipment | |
| CN108920490A (en) | Assist implementation method, device, electronic equipment and the storage medium of makeup | |
| CN105426850A (en) | Human face identification based related information pushing device and method | |
| CN104639725B (en) | interface switching method and device | |
| CN105511600B (en) | A kind of multimedia human-computer interaction platform based on mixed reality | |
| CN106407891A (en) | Target matching method based on convolutional neural network and device | |
| CN106503043B (en) | A kind of interaction data processing method for intelligent robot | |
| CN107533640A (en) | Sight corrects | |
| CN110443167A (en) | Intelligent identification Method, intelligent interactive method and the relevant apparatus of traditional culture gesture | |
| CN110689479B (en) | Face makeup method, device, equipment and medium | |
| CN106371718A (en) | Screen capture method and device | |
| CN107340964A (en) | The animation effect implementation method and device of a kind of view | |
| CN107784355A (en) | The multi-modal interaction data processing method of visual human and system | |
| CN108176049A (en) | A kind of information cuing method, device, terminal and computer readable storage medium | |
| CN107102732A (en) | A kind of eye moves determination methods and device | |
| CN107066979A (en) | A kind of human motion recognition method based on depth information and various dimensions convolutional neural networks | |
| CN108874234A (en) | A kind of touch control identification method, device and touch control display apparatus | |
| CN104793732A (en) | Intelligent glasses operation method and intelligent glasses | |
| CN109330556A (en) | Utilize the vision testing method and system of image technique and cloud control technology | |
| CN108415561A (en) | Gesture interaction method based on visual human and system | |
| CN110083238A (en) | Man-machine interaction method and system based on augmented reality |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170825 |