CN108875541A - A kind of visual fatigue detection algorithm based on virtual reality technology - Google Patents
A kind of visual fatigue detection algorithm based on virtual reality technology Download PDFInfo
- Publication number
- CN108875541A CN108875541A CN201810216441.3A CN201810216441A CN108875541A CN 108875541 A CN108875541 A CN 108875541A CN 201810216441 A CN201810216441 A CN 201810216441A CN 108875541 A CN108875541 A CN 108875541A
- Authority
- CN
- China
- Prior art keywords
- eyes
- visual fatigue
- edge
- wink
- eyelid
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
- G06V10/446—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering using Haar-like filters, e.g. using integral image techniques
-
- 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
- G06V40/193—Preprocessing; Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- General Engineering & Computer Science (AREA)
- Eye Examination Apparatus (AREA)
- Image Analysis (AREA)
Abstract
A kind of visual fatigue detection algorithm based on virtual reality technology is made of detection eyes marginal information, measurement eyelid distance and calculating frequency of wink.It detects eyes marginal information and uses Sobel edge detection operator, detect the gray value of pixel in eyes, obtain edge value of each pixel of eyes on horizontal and vertical;The edge value for measuring eyelid bottom a line in record eyes, is retrieved upwards in turn, until retrieving upper edge and recording, is recorded the edge value that leftmost one arranges in eyes, is successively retrieved to the right, until retrieving the right edge and recording, to obtain eyelid distance;The standard parameter that frequency of wink defines a visual fatigue is calculated, is compared with the numerical value and standard parameter that obtain.The present invention is capable of the visual fatigue degree of real-time monitoring human eye, has great application prospect.
Description
Technical field
The present invention relates to a kind of the visual fatigue detection algorithm based on virtual reality technology, the visual fatigue detection calculation
Method is the visual fatigue degree for detecting human eye, establishes a kind of new detection method, the invention belongs to electronic technology fields.
Background technique
Virtual reality technology (Virtual Reality, abbreviation VR) is originating from 20 world sixties, with social productive forces
With the development of science and technology, the 3-D image processing capacity of computer has obtained significantly being promoted, and senser element is also gradually cheap, this just makes
Virtual reality technology rapid development is obtained, all trades and professions also there are more demands to virtual reality technology, to virtual reality technology
Research and development be also taken seriously gradually, become the major fields of Social Science Research.Currently, in theoretic and application
Relatively good development is all obtained, industrial also in military affairs, medicine etc. all plays an important role.
When using virtual reality technology, the mode immersed, interacted can be used, a kind of vision of solid is brought to user
Grand banquet, but if watching for a long time, it is likely that bring visual fatigue to even result in the ill symptoms such as dizziness headache to user.
Therefore, when in use for virtual reality technology, visual fatigue can be led to the problem of, it would be highly desirable to develop a detection and solution party
Method, also at the focus of attention of technical staff in recent years.
Summary of the invention
In order to solve problems in the prior art, the present invention a kind of visual fatigue calculation based on virtual reality technology in providing
Method, the visual fatigue algorithm use Sobel edge detection operator, can real-time monitoring wearer's vision degree of fatigue.
A kind of visual fatigue detection algorithm based on virtual reality technology, which is characterized in that it is believed by detection eyes edge
Breath, measurement eyelid distance and calculating frequency of wink composition;The detection eyes marginal information is calculated using Sobel edge detection
Son detects the gray value of pixel in eyes, obtains edge value of each pixel of eyes on horizontal and vertical;The measurement
The edge value of bottom a line, retrieves upwards in turn, until retrieving upper edge and recording, records in eyelid distance record eyes
In eyes leftmost one arrange edge value, successively retrieve to the right, until retrieve the right along and record, thus obtain eyelid away from
From;The calculating frequency of wink defines the standard parameter of a visual fatigue, is compared with the numerical value and standard parameter that obtain, from
And obtain visual fatigue degree.
It is M that the Sobel edge detection operator, which defines horizontal and vertical edge value,a(i, j) and Mb(i, j), wherein
It is Y that the detection eyes marginal information, which enables upper eyelid,U, palpebra inferior YL, left eyelid ZU, right eyelid ZL, then
Distance H=Y up and down can be calculatedU-YL, left and right distance W=ZU-ZL。
The frame number that the calculating frequency of wink defines image is n, and total number of image frames is N, frequency of wink P, then P=n/
N, frequency of wink P is bigger, then proves that user is more tired.
The invention has the advantages that being carried out real using Sobel edge detection operator to the user of virtual reality technology
When visual fatigue monitoring.
Detailed description of the invention
Figure is Sobel edge detection operator flow chart of the invention.
Specific embodiment
The present invention is to carry out visual fatigue detection by algorithm based on the variation of acquisition user's eye.It uses
Sobel edge detection operator detects the edge of user's eyes;It is arrived using the integral projection algorithm measurement user left side
The right canthus and the distance for arriving following eyelid above;It calculates frequency of wink and identifies the state of visual fatigue.
The gray value at eyes edge is set as 0, and calculates separately each pixel of eyes in horizontal edge and vertical edge edge
On edge value Ma(i, j) and Mb(i, j).Expression formula is:
Wherein, A (i, j) indicates the gray value of the ith row and jth column pixel in eyes;.Ga(m, n), Gb(m, n) is
The element value of the corresponding m row of Sobel edge detection operator matrix and the n-th column, and center is the 0th row, the 0th column.Ga, Gb
For the Sobel edge detection operator matrix form of expression:
Assuming that M* (i, j) is the edge value initially determined that within the scope of eyes.Compare | Ma(i, j) | with | Mb(i, j) | it is big
It is small, if | Ma(i, j) | >=| Mb(i, j) |, then M* (i, j)=| Ma(i, j) |;If | Ma(i, j) | < | Mb(i, j) |, then M* (i, j)
=| Mb(i, j) |.
Assuming that a threshold X, wherein the numerical value of X be according to the average value of gray value within the scope of eyes at the beginning by a certain percentage
What amplification obtained.
Using above and below integral projection algorithm measurement eye socket with left and right at a distance from.Within the scope of eye detection, from bottom
A line is retrieved upwards in turn, records the number that every a line grey scale pixel value is 1, and then it is corresponded to row grey scale pixel value is 1
The sum of number array A is recordedcIn [i], i adds 1 after having searched for a line.
If 1 < A after being countedc[i]≤3&&Ac[i+1] > Ac[i]+5&&Ac[i+2]≥Ac[i+1] then shows certainly
The dynamic lower edge for detecting eyes, records the row i where it, if YLFor a variable, Y is enabledL=i.If Ac[i] > Ac[i+1]&&
Ac[i+1]≥Ac[i+2]&&Ac[i+2] < 3 then shows the upper edge for having automatically detected eyes, records the row i where it,
If YUFor a variable, Y is enabledU=i.
It is detecting eyes upper edge, then is increasing by three rows as the upper bound of detection range upwards and be expressed as YU=YU+
3.It is detecting eyes lower edge, is reducing by three rows still further below, as the lower bound of detection range, be expressed as YL=YL-3。
Similarly, it within the scope of eye detection, is retrieved to the right from a Leie of leftmost, records each column pixel grey scale
Then array A is recorded in the sum of the number that its respective column grey scale pixel value is 1 by the number that value is 1lIn [j], a column have been searched for
J adds 1 afterwards.
If 1 < A after being countedl[j]≤3&&Al[j+1] > Al[j]+5&&Al[j+2]≥Al[j+1] then shows certainly
The dynamic left margin for detecting eyes, records the column j where it, if ZLFor a variable, Z is enabledL=j.
If Al[j] > Al[j+1]&&Al[j+1]≥Al[j+2]&&Al[j+2] < 3, then show to have automatically detected eyes
The column j where it is recorded, if Z in the right edgeUFor a variable, Z is enabledU=j.
Then obtain eye socket up and down with control at a distance from, H and W, wherein H=YU-YL, W=ZU-ZL.Opening for eyes is determined again
Degree R is opened, wherein R=H/W.If the R being calculated is in not less than the threshold X of setting, eyes and opens state, otherwise eyes
In closed state.
It calculates frequency of wink and identifies the state of visual fatigue, define frequency of wink P as the parameter for judging visual fatigue,
The frame number for defining image in certain time is n, and total number of image frames is N, then P=n/N.Frequency of wink P is bigger, then proves user
It is more tired, to calculate the degree of user's visual fatigue.
Claims (4)
1. a kind of visual fatigue detection algorithm based on virtual reality technology, which is characterized in that it by detection eyes marginal information,
It measures eyelid distance and calculates frequency of wink composition;The detection eyes marginal information uses Sobel algorithm, detects eyes
The gray value of interior pixel obtains edge value of each pixel of eyes on horizontal and vertical;The measurement eyelid distance record
The edge value of bottom a line, is retrieved upwards in turn in eyes, until retrieving upper edge and recording, records leftmost in eyes
The edge value of one column, is successively retrieved to the right, until retrieving the right edge and recording, to obtain eyelid distance;The calculating
Frequency of wink defines the standard parameter of a visual fatigue, is compared with the numerical value and standard parameter that obtain, to show that vision is tired
Labor degree.
2. a kind of visual fatigue detection algorithm based on virtual reality technology according to claim 1, which is characterized in that institute
It is M that the Sobel algorithm stated, which defines horizontal and vertical edge value,a(I, j)And Mb(I, j), wherein Ma(I, j)=、Mb(I, j)=。
3. a kind of visual fatigue detection algorithm based on virtual reality technology according to claim 1, which is characterized in that institute
It is Y that the detection eyes marginal information stated, which enables upper eyelid,U, palpebra inferior YL, left eyelid ZU, right eyelid ZL, then can calculate
Lower distance H=YU-YL, left and right distance W=ZU-ZL。
4. a kind of visual fatigue detection algorithm based on virtual reality technology according to claim 1, which is characterized in that institute
The frame number that the calculating frequency of wink stated defines image is n, and total number of image frames is N, frequency of wink P, then P=n/N, frequency of wink P
It is bigger, then prove that user is more tired.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810216441.3A CN108875541A (en) | 2018-03-16 | 2018-03-16 | A kind of visual fatigue detection algorithm based on virtual reality technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810216441.3A CN108875541A (en) | 2018-03-16 | 2018-03-16 | A kind of visual fatigue detection algorithm based on virtual reality technology |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108875541A true CN108875541A (en) | 2018-11-23 |
Family
ID=64326094
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810216441.3A Pending CN108875541A (en) | 2018-03-16 | 2018-03-16 | A kind of visual fatigue detection algorithm based on virtual reality technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108875541A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109522868A (en) * | 2018-11-30 | 2019-03-26 | 北京七鑫易维信息技术有限公司 | A kind of method and apparatus of detection blink |
CN110413124A (en) * | 2019-08-01 | 2019-11-05 | 贵州电网有限责任公司 | A kind of man-machine interactive system and its application method based on VR video |
CN113995412A (en) * | 2021-12-07 | 2022-02-01 | 福州大学 | Construction worker construction fatigue degree detection device and method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030214583A1 (en) * | 2002-05-20 | 2003-11-20 | Mokhtar Sadok | Distinguishing between fire and non-fire conditions using cameras |
CN101209207A (en) * | 2006-12-26 | 2008-07-02 | 爱信精机株式会社 | Eyelid detecting apparatus, eyelid detecting method and program thereof |
CN101375796A (en) * | 2008-09-18 | 2009-03-04 | 浙江工业大学 | Real-time detection system of fatigue driving |
CN104574820A (en) * | 2015-01-09 | 2015-04-29 | 安徽清新互联信息科技有限公司 | Fatigue drive detecting method based on eye features |
CN105894735A (en) * | 2016-05-31 | 2016-08-24 | 成都九十度工业产品设计有限公司 | Intelligent vehicle-mounted fatigue monitoring system and method |
CN106485880A (en) * | 2016-11-15 | 2017-03-08 | 广东技术师范学院 | Automobile driving safe early warning vehicle intelligent terminal |
-
2018
- 2018-03-16 CN CN201810216441.3A patent/CN108875541A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030214583A1 (en) * | 2002-05-20 | 2003-11-20 | Mokhtar Sadok | Distinguishing between fire and non-fire conditions using cameras |
CN101209207A (en) * | 2006-12-26 | 2008-07-02 | 爱信精机株式会社 | Eyelid detecting apparatus, eyelid detecting method and program thereof |
CN101375796A (en) * | 2008-09-18 | 2009-03-04 | 浙江工业大学 | Real-time detection system of fatigue driving |
CN104574820A (en) * | 2015-01-09 | 2015-04-29 | 安徽清新互联信息科技有限公司 | Fatigue drive detecting method based on eye features |
CN105894735A (en) * | 2016-05-31 | 2016-08-24 | 成都九十度工业产品设计有限公司 | Intelligent vehicle-mounted fatigue monitoring system and method |
CN106485880A (en) * | 2016-11-15 | 2017-03-08 | 广东技术师范学院 | Automobile driving safe early warning vehicle intelligent terminal |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109522868A (en) * | 2018-11-30 | 2019-03-26 | 北京七鑫易维信息技术有限公司 | A kind of method and apparatus of detection blink |
CN109522868B (en) * | 2018-11-30 | 2021-07-23 | 北京七鑫易维信息技术有限公司 | Method and device for detecting blink |
CN110413124A (en) * | 2019-08-01 | 2019-11-05 | 贵州电网有限责任公司 | A kind of man-machine interactive system and its application method based on VR video |
CN113995412A (en) * | 2021-12-07 | 2022-02-01 | 福州大学 | Construction worker construction fatigue degree detection device and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104978548B (en) | A kind of gaze estimation method and device based on three-dimensional active shape model | |
CN110532887A (en) | A kind of method for detecting fatigue driving and system based on facial characteristics fusion | |
CN108875541A (en) | A kind of visual fatigue detection algorithm based on virtual reality technology | |
CN110032271A (en) | Contrast control device and its method, virtual reality device and storage medium | |
CN110084259A (en) | A kind of facial paralysis hierarchical synthesis assessment system of combination face texture and Optical-flow Feature | |
CN104680524B (en) | A kind of leafy vegetable disease screening method | |
US20180342078A1 (en) | Information processing device, information processing method, and information processing system | |
US20160025612A1 (en) | Cell counting method, cell counting device, and cell counting program | |
CN111126180B (en) | Facial paralysis severity automatic detection system based on computer vision | |
CN111291701B (en) | Sight tracking method based on image gradient and ellipse fitting algorithm | |
CN109271918B (en) | Method for distinguishing people with balance ability disorder based on gravity center shift model | |
CN112308932A (en) | Gaze detection method, device, equipment and storage medium | |
CN111160239A (en) | Concentration degree evaluation method and device | |
CN102567734A (en) | Specific value based retina thin blood vessel segmentation method | |
CN112232128B (en) | Eye tracking based method for identifying care needs of old disabled people | |
CN109685830A (en) | Method for tracking target, device and equipment and computer storage medium | |
CN111402235B (en) | Growth recording method and device for colony image, electronic equipment and storage medium | |
CN107194364B (en) | Huffman-L BP multi-pose face recognition method based on divide and conquer strategy | |
CN109410191B (en) | OCT (optical coherence tomography) image-based fundus blood vessel positioning method and anemia screening method thereof | |
CN113255476A (en) | Target tracking method and system based on eye movement tracking and storage medium | |
CN117338234A (en) | Diopter and vision joint detection method | |
CN111680566A (en) | Hand sample face recognition method based on sliding block generation countermeasure network | |
CN116884036A (en) | Live pig posture detection method, device, equipment and medium based on YOLOv5DA | |
CN113591797B (en) | Depth video behavior recognition method | |
CN103955695B (en) | The method that computer is based on human eye state in gray level co-occurrence matrixes energy variation Intelligent Recognition video |
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: 20181123 |
|
WD01 | Invention patent application deemed withdrawn after publication |