CN109044363A - Driver Fatigue Detection based on head pose and eye movement - Google Patents
Driver Fatigue Detection based on head pose and eye movement Download PDFInfo
- Publication number
- CN109044363A CN109044363A CN201811029521.4A CN201811029521A CN109044363A CN 109044363 A CN109044363 A CN 109044363A CN 201811029521 A CN201811029521 A CN 201811029521A CN 109044363 A CN109044363 A CN 109044363A
- Authority
- CN
- China
- Prior art keywords
- eye movement
- user
- head
- head pose
- driver fatigue
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1116—Determining posture transitions
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/18—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state for vehicle drivers or machine operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
-
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/20—Workers
- A61B2503/22—Motor vehicles operators, e.g. drivers, pilots, captains
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Psychiatry (AREA)
- Molecular Biology (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Multimedia (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Psychology (AREA)
- Human Computer Interaction (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Social Psychology (AREA)
- Dentistry (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Ophthalmology & Optometry (AREA)
- Eye Examination Apparatus (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses the Driver Fatigue Detections based on head pose and eye movement, comprising the following steps: obtains image sequence；Detect human face characteristic point and ocular image information；Analysis human face characteristic point solves head pose, and analysis ocular image information solves eye movement vector；Calculate the time of the head pose attitude angle and eye movement vector shift secure threshold；The driving condition of real-time monitoring driver.Driver Fatigue Detection based on head pose and eye movement of the invention is according to the physiologic habits of people's observed objects, using head pose and eye movement as effectively information is watched attentively, using facial orientation as benchmark direction of gaze；This method is not necessarily to demarcating steps, without carrying out the dynamic compensation of head, it can be achieved that really detecting driver fatigue without constraint.
Description
Technical field
The present invention relates to human-computer interaction technique fields, and in particular to a kind of driver fatigue based on head pose and eye movement
Detection method.
Background technique
With the development of economy and society, motor vehicle becomes one of most important trip mode.At the same time, traffic accident is not
Evitable rapid growth, fatigue driving is the ever-increasing major reason of traffic accident, and can pass through technology hand
The big traffic security risk that Duan Jinhang gives warning in advance.According to statistics, casualties situation caused by fatigue driving is no less than drunk
It drives.Absent minded state caused by driver itself fatigue state can cause serious personnel casualty accidents frequent at present
Occur.Therefore need one kind can real-time detection driver fatigue situation, and be capable of the device of early warning, this will be prevention fatigue
Drive and cause the effective means of traffic accident.
But found out in the driver fatigue monitor system of comparative maturity at present, reliable is by extracting arteries and veins
It fights signal detection, but driver is required to wear physiological signal inductor on the way driving, driver can be caused to bear, to driving
Safety belt carrys out certain hidden danger.Simultaneously traditional, off-board, contact, non real-time driving fatigue detection method oneself
It is not suitable with the requirement in epoch, needs to seek a kind of driver fatigue detection device, in real time to driver fatigue shape in driving procedure
The detection and early warning of state.
When driver fatigue, it will usually be frequent bow, come back, nodding, eyes closed and frequency of wink it is excessively slow
Etc. features.Therefore monitoring in real time is carried out to the head pose of driver and accurately estimates head pose, be fatigue driving inspection
Important link in survey.The monitoring driver fatigue method based on head pose and Eye-controlling focus be applied in the field come,
The prompting that driver's driving condition exception can be achieved can take effective measures when necessary, stop driving, to reduce accident
Risk ensures driver's personal safety and property safety.
Summary of the invention
In view of this, the present invention provides one kind to be based on head pose and eye to solve above-mentioned the problems of the prior art
Dynamic Driver Fatigue Detection, to solve real-time monitoring driver fatigue in non-intrusion type human-computer interaction technique field
Problem.
To achieve the above object, technical scheme is as follows.
A kind of Driver Fatigue Detection based on head pose and eye movement comprising following steps:
Step 1 obtains image sequence by the image acquisition units of non-intrusion type；
In step 2, each frame image based on described image sequence, human face characteristic point image information and eye area are detected
Area image information；
Step 3, based on the human face characteristic point image information, solve head pose；
Step 4, based on the ocular image information, solve eye movement vector；
Step 5, in conjunction with the head pose and eye movement vector, determine the driving condition of driver.
Further, include following sub-step in the step 3:
Step 31 carries out facial feature points detection on human face image information region, identifies at least three face characteristics
Point；
The human face characteristic point is carried out face characteristic point alignment by step 32, obtains the space coordinate of user's head；
Step 33, the space coordinate based on the user's head construct head geometry three-dimensional model, obtain user's head appearance
State angle；
Step 34 makees a ray by endpoint of a characteristic point on face, and directions of rays is that the user's head posture is angular
The direction of amount.
Further, the human face characteristic point include left eye canthus, right eye canthus, the left corners of the mouth of mouth, the right corners of the mouth of mouth and
Nose.
Further, the step 4 includes following sub-step:
Step 41 is based on the ocular image information, obtains iris position, divides the pupil side in human eye area
Edge, and position pupil center；
Step 42, based on the relative position between pupil center and canthus, construct the big canthus vector of pupil center-(Δ x,
Δ y) obtains the eye movement vector of user.
Further, the step 5 includes following sub-step:
Step 51 sets the secure threshold of user's head attitude angle and eye movement vector as D1；
Step 52, record user's head attitude angle or eye movement vector are greater than secure threshold D1Time be t1；
Step 53, setting user's head attitude angle or eye movement vector are greater than secure threshold D1Maximum safety time be t2；
Step 54 calculates the time t1And t2Difference be T；
Step 55 compares size relation between T and 0, obtains the driving condition of user；
Step 56, based on the eye movement vector, counting user number of winks K1, set the user security number of winks upper limit
For K2, lower limit K3；
Step 57 compares K1With K2、K3Size relation, obtain the driving condition of user.
Compared with the prior art, the Driver Fatigue Detection of the invention based on head pose and eye movement is seen according to people
The physiologic habit for surveying object, using head pose and eye movement as effectively information is watched attentively, using head pose as benchmark direction of gaze；
Space reflection model is resettled, the time of the head pose and eye movement vector shift secure threshold is calculated, real-time monitoring is driven
The driving condition for the person of sailing.This method is not necessarily to demarcating steps, without carrying out the dynamic compensation of head, it can be achieved that really driving without constraint detection
Member's fatigue.
Detailed description of the invention
Fig. 1 is the Driver Fatigue Detection logic diagram of the invention based on head pose and eye movement.
Fig. 2 is the embodiment 1 of non-intrusion type face eyes image video acquisition unit.
Fig. 3 is the embodiment 1 of non-intrusion type Image Acquisition unit and user relative position.
Fig. 4 is the embodiment 2 of non-intrusion type Image Acquisition unit and user relative position.
Fig. 5 is the embodiment 3 of non-intrusion type Image Acquisition unit and user relative position.
Fig. 6 is the embodiment 2 of non-intrusion type face eyes image video acquisition unit.
Fig. 7 is pupil center-inner eye corner eye movement vector.
Fig. 8 is gray integration function and Snake model orientation pupil center.
Specific embodiment
Specific implementation of the invention is described further below in conjunction with attached drawing and specific embodiment.It may be noted that
Being, if having the process (such as convolutional neural networks) or parameter of not special detailed description below, is that those skilled in the art can join
According to the prior art realize or understand.Described embodiments are only a part of the embodiments of the present invention, rather than whole realities
Example is applied, based on the embodiments of the present invention, those of ordinary skill in the art are obtained without making creative work
Every other embodiment, shall fall within the protection scope of the present invention.
Embodiment 1
As shown in Figure 1, a kind of Driver Fatigue Detection based on head pose and eye movement, comprising the following steps:
Step 1 obtains image sequence by the image acquisition units of non-intrusion type；
Man face image acquiring unit is the camera near monitoring screen observed by user is arranged in, for for shooting
Family face area, user acquire what user used in real time without wearing any assisted acquisition device (non-intrusion type), by camera
Image is converted into 256 rank grayscale images.
Cam lens of the present invention are equipped with infrared fileter, can filter out visible light wave range, retain infrared band.Camera sense
Optical element CCD or CMOS can be photosensitive to infrared band.Near cam lens, arranges infrared LED array of source, circlewise divide
Cloth.Light-source brightness can be adjusted by PWM modulation signal according to actual environment needs.The present invention can be used a camera and complete,
Also multiple camera collocation can be used, enhance imaging effect.
As shown in Fig. 2, being a kind of embodiment of non-intrusion type image acquisition units.Which includes interactive screen, take the photograph
As head, infrared LED light source.The characteristics of camera, is the infrared band light that its energy light-sensitive infrared LED light source issues, front end dress
Have an infrared filtering eyeglass, characteristic parameter such as cutoff frequency etc. according to the LED light source of actual use and user apart from situations such as
Adjustment.When LED light source uses the infrared LED light source of 800nm wave band or more, cutoff frequency is selected in 800nm or more, usually
, bandpass-type filtering is more preferable than high-pass type filter effect.
As shown in figure 3, being the embodiment 1 of non-intrusion type Image Acquisition unit Yu user relative position.Wherein non-intruding
Lower position of the formula Image Acquisition unit in user face.
As shown in figure 4, being the embodiment 2 of non-intrusion type Image Acquisition unit Yu user relative position.Wherein non-intruding
Formula Image Acquisition unit is in the square position of user face.
As shown in figure 5, being the embodiment 3 of non-intrusion type Image Acquisition unit Yu user relative position.Wherein non-intruding
Formula Image Acquisition unit is in the top position of user face.
Embodiment 2
Although only needing a camera, an infrared LED light source that image sampling can be completed in the embodiment of the present invention, it is
Multiple light courcess, multi-camera system, division of labor collocation can be used in acquisition higher quality of image signals.As shown in fig. 6, being invaded to be non-
Another embodiment for entering formula image acquisition units, the present embodiment provides a scheme, camera 1 is equipped with infrared LED light source, uses
In shooting wide scene, face is captured；Camera 2 and camera 3 are used to shoot the high-definition image of eye areas, and interactive screen is left
Upper angle and the upper right corner are respectively equipped with infrared LED light source.
Step 2 is based on described image sequence, in each frame image of image sequence, detects that face characteristic point image is believed
Breath and ocular image information；
Step 3, based on the human face characteristic point in described image, analyze head pose image information, solve head pose,
Using head pose as directions of rays, the directions of rays is intersected with image acquisition units and obtains an intersection point, by the intersection point
As benchmark head pose point；
Include following sub-step in the step 3:
Step 31 carries out facial feature points detection on human face region, identifies five human face characteristic points；
Five human face characteristic points are carried out face characteristic point alignment by step 32, the method based on convolutional neural networks,
Obtain the space coordinate of user's head；
Step 33, the space coordinate based on the user's head construct head geometry three-dimensional model, solve the rotation on head
Shaft angle；If rotation shaft angle is α, each component of the rotary shaft under the geometry three-dimensional model is set as βx、βyAnd βz, warp
Formula is converted to quaternary number, the formula are as follows:
W=cos (α/2)
X=sin (α/2) cos (βx)
Y=sin (α/2) cos (βy)
Z=sin (α/2) cos (βz)
Wherein, w, x, y and z are quaternary number.
Based on the quaternary number, user's head attitude angle, the formula are obtained through formula are as follows:
Wherein ψ is facial orientation or so angle, and φ is lower angle on facial orientation,For facial orientation roll angle；
Step 34 makees a ray by endpoint of certain characteristic point on face, and directions of rays is that the user's head posture is angular
The direction of amount.
Five human face characteristic points include left eye canthus, right eye canthus, the left corners of the mouth of mouth, the right corners of the mouth of mouth and nose.
Two-dimensional image sequence file is built into 3-D geometric model by five human face characteristic points by the embodiment of the present invention, is obtained
Three-dimensional head pose information is taken, head pose is obtained.
Step 4, based on the benchmark head pose point, centered on the benchmark head pose point, in equipment screen
Curtain regional assignment watching area, using the center of watching area as basic point, the region for dividing 2/3rds is safety zone；
Based on the watching area, the ocular image information is analyzed, eye movement vector is solved, by eye movement vector
In device screen as sight line point.
Include following sub-step in the step 4:
Step 41, the method (methods of convolutional neural networks) based on deep learning, detection are fallen in the watching area
Ocular；By gray integration function, iris position is obtained, is then based on Snake model, divides the pupil in human eye area
Hole edge, and position pupil center；
Step 42, based on the relative position between pupil center and canthus, construct pupil center-inner eye corner eye movement vector
(Δ x, Δ y) can be obtained user in the sight line point of the watching area.
Further, in this embodiment the eye movement vector illustrated is pupil center-inner eye corner vector, as shown in Figure 7.It is first
First, inner eye corner belongs to one of human face characteristic point, has passed through the acquisition of benchmark gazing direction detecting submodule.By being based on deep learning
Method (methods of such as convolutional neural networks) and Hough transformation image processing method, use human eye classifier divide human eye area
Domain.In human eye area, by gray integration function, iris region is obtained, Snake model is reused and is partitioned into iris edge,
Pupil center is fitted, process is shown in attached drawing 8.Then, camera coordinate system is set, and world coordinate system is drawn outer with 1 point on the face
Prolong ray, is met at a bit with interactive screen.
Step 5, based on the head pose image information and ocular image information, obtain user and watch attentively described
The driving condition in region.
Include following sub-step in the step 5:
Step 51 sets the secure threshold of user's head attitude angle and eye movement vector as D1；
Step 52 obtains user's head attitude angle or eye movement vector greater than secure threshold D1Time be t1；
Step 53, setting user's head attitude angle or eye movement vector are greater than secure threshold D1Maximum safety time be t2；
Step 54 calculates the time t1And t2Difference be T；
Step 55, based on the T, when T is more than or equal to zero, determine user in fatigue driving state, when T is less than
When zero, determine user in normal driving state；
Step 56, based on the eye movement vector, counting user number of winks K1, set the user security number of winks upper limit
For K2, lower limit K3；
Step 57, the number of winks K based on the user1, work as K1Greater than K3And it is less than K2When, determine user just
Normal driving condition, when working as K1Less than K3Or it is greater than K2When, determine user in fatigue driving state.
In conclusion the Driver Fatigue Detection of the invention based on head pose and eye movement is according to people's observed objects
Physiologic habit, using head pose and eye movement as effectively information is watched attentively, using head pose as benchmark direction of gaze；It resettles
Space reflection model calculates the time of the head pose and eye movement vector shift secure threshold, real-time monitoring driver's
Driving condition.This method is not necessarily to demarcating steps, without carrying out the dynamic compensation of head, it can be achieved that really tired without constraint detection driver
Labor.
Above-listed detailed description is illustrating for possible embodiments of the present invention, and the embodiment is not to limit this hair
Bright the scope of the patents, all equivalence enforcements or change without departing from carried out by the present invention, is intended to be limited solely by the scope of the patents of this case.
Claims (5)
1. a kind of Driver Fatigue Detection based on head pose and eye movement, which comprises the following steps:
Step 1 obtains image sequence by the image acquisition units of non-intrusion type；
In step 2, each frame image based on described image sequence, human face characteristic point image information and ocular figure are detected
As information；
Step 3, based on the human face characteristic point image information, solve head pose；
Step 4, based on the ocular image information, solve eye movement vector；
Step 5, in conjunction with the head pose and eye movement vector, determine the driving condition of driver.
2. the Driver Fatigue Detection according to claim 1 based on head pose and eye movement, which is characterized in that institute
State includes following sub-step in step 3:
Step 31 carries out facial feature points detection on human face image information region, identifies at least three human face characteristic points；
The human face characteristic point is carried out face characteristic point alignment by step 32, obtains the space coordinate of user's head；
Step 33, the space coordinate based on the user's head construct head geometry three-dimensional model, obtain user's head posture
Angle；
Step 34 makees a ray by endpoint of a characteristic point on face, and directions of rays is the user's head attitude angle vector
Direction.
3. the Driver Fatigue Detection according to claim 1 or 2 based on head pose and eye movement, feature exist
In: the human face characteristic point includes left eye canthus, right eye canthus, the left corners of the mouth of mouth, the right corners of the mouth of mouth and nose.
4. the Driver Fatigue Detection according to claim 1 based on head pose and eye movement, which is characterized in that institute
Stating step 4 includes following sub-step:
Step 41 is based on the ocular image information, obtains iris position, divides the pupil edge in human eye area, and
Position pupil center；
Step 42, based on the relative position between pupil center and canthus, construct the big canthus vector of pupil center-(Δ x, Δ y),
Obtain the eye movement vector of user.
5. the Driver Fatigue Detection according to claim 1 based on head pose and eye movement, which is characterized in that institute
Stating step 5 includes following sub-step:
Step 51 sets the secure threshold of user's head attitude angle and eye movement vector as D1；
Step 52, record user's head attitude angle or eye movement vector are greater than secure threshold D1Time be t1；
Step 53, setting user's head attitude angle or eye movement vector are greater than secure threshold D1Maximum safety time be t2；
Step 54 calculates the time t1And t2Difference be T；
Step 55 compares size relation between T and 0, obtains the driving condition of user；
Step 56, based on the eye movement vector, counting user number of winks K1, the user security number of winks upper limit is set as K2,
Lower limit is K3；
Step 57 compares K1With K2、K3Size relation, obtain the driving condition of user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811029521.4A CN109044363A (en) | 2018-09-04 | 2018-09-04 | Driver Fatigue Detection based on head pose and eye movement |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811029521.4A CN109044363A (en) | 2018-09-04 | 2018-09-04 | Driver Fatigue Detection based on head pose and eye movement |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109044363A true CN109044363A (en) | 2018-12-21 |
Family
ID=64759601
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811029521.4A Pending CN109044363A (en) | 2018-09-04 | 2018-09-04 | Driver Fatigue Detection based on head pose and eye movement |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109044363A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109878528A (en) * | 2019-01-31 | 2019-06-14 | 电子科技大学 | Head movement attitude detection system towards vehicle-mounted stereo visual system |
| CN109965843A (en) * | 2019-03-14 | 2019-07-05 | 华南师范大学 | A kind of eye movements system passing picture based on filtering |
| CN110197169A (en) * | 2019-06-05 | 2019-09-03 | 南京邮电大学 | A kind of contactless learning state monitoring system and learning state detection method |
| CN110909596A (en) * | 2019-10-14 | 2020-03-24 | 广州视源电子科技股份有限公司 | Side face recognition method, device, equipment and storage medium |
| CN111626221A (en) * | 2020-05-28 | 2020-09-04 | 四川大学 | Driver gazing area estimation method based on human eye information enhancement |
| CN112084820A (en) * | 2019-06-14 | 2020-12-15 | 初速度（苏州）科技有限公司 | Personnel state detection method and device based on head information |
| CN112232128A (en) * | 2020-09-14 | 2021-01-15 | 南京理工大学 | Eye tracking based method for identifying care needs of old disabled people |
| CN112869701A (en) * | 2021-01-11 | 2021-06-01 | 上海微创医疗机器人（集团）股份有限公司 | Sight line detection method, surgical robot system, control method, and storage medium |
| CN112926364A (en) * | 2019-12-06 | 2021-06-08 | 北京四维图新科技股份有限公司 | Head posture recognition method and system, automobile data recorder and intelligent cabin |
| CN113331839A (en) * | 2021-05-28 | 2021-09-03 | 武汉科技大学 | Network learning attention monitoring method and system based on multi-source information fusion |
| CN113591762A (en) * | 2021-08-09 | 2021-11-02 | 重庆理工大学 | Safe driving early warning method under free angle |
| CN113591699A (en) * | 2021-07-30 | 2021-11-02 | 西安电子科技大学 | Online visual fatigue detection system and method based on deep learning |
| TWI754806B (en) * | 2019-04-09 | 2022-02-11 | 栗永徽 | System and method for locating iris using deep learning |
| CN114432098A (en) * | 2022-01-27 | 2022-05-06 | 中山大学附属第一医院 | Gait orthotic devices based on model |
| CN117227740A (en) * | 2023-09-14 | 2023-12-15 | 南京项尚车联网技术有限公司 | Multi-mode sensing system and method for intelligent driving vehicle |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030169907A1 (en) * | 2000-07-24 | 2003-09-11 | Timothy Edwards | Facial image processing system |
| CN101419664A (en) * | 2007-10-25 | 2009-04-29 | 株式会社日立制作所 | Sight direction measurement method and sight direction measurement device |
| CN105279493A (en) * | 2015-10-22 | 2016-01-27 | 四川膨旭科技有限公司 | System for identifying visions of drivers in vehicle running process |
| CN106598221A (en) * | 2016-11-17 | 2017-04-26 | 电子科技大学 | Eye key point detection-based 3D sight line direction estimation method |
| CN107193383A (en) * | 2017-06-13 | 2017-09-22 | 华南师范大学 | A kind of two grades of Eye-controlling focus methods constrained based on facial orientation |
| CN108427503A (en) * | 2018-03-26 | 2018-08-21 | 京东方科技集团股份有限公司 | Human eye method for tracing and human eye follow-up mechanism |
-
2018
- 2018-09-04 CN CN201811029521.4A patent/CN109044363A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030169907A1 (en) * | 2000-07-24 | 2003-09-11 | Timothy Edwards | Facial image processing system |
| CN101419664A (en) * | 2007-10-25 | 2009-04-29 | 株式会社日立制作所 | Sight direction measurement method and sight direction measurement device |
| CN105279493A (en) * | 2015-10-22 | 2016-01-27 | 四川膨旭科技有限公司 | System for identifying visions of drivers in vehicle running process |
| CN106598221A (en) * | 2016-11-17 | 2017-04-26 | 电子科技大学 | Eye key point detection-based 3D sight line direction estimation method |
| CN107193383A (en) * | 2017-06-13 | 2017-09-22 | 华南师范大学 | A kind of two grades of Eye-controlling focus methods constrained based on facial orientation |
| CN108427503A (en) * | 2018-03-26 | 2018-08-21 | 京东方科技集团股份有限公司 | Human eye method for tracing and human eye follow-up mechanism |
Non-Patent Citations (1)
| Title |
|---|
| 迟健男: "驾驶疲劳监测方法综述", 《交通节能与环保》 * |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109878528A (en) * | 2019-01-31 | 2019-06-14 | 电子科技大学 | Head movement attitude detection system towards vehicle-mounted stereo visual system |
| CN109965843A (en) * | 2019-03-14 | 2019-07-05 | 华南师范大学 | A kind of eye movements system passing picture based on filtering |
| CN109965843B (en) * | 2019-03-14 | 2022-05-24 | 华南师范大学 | Eye movement system based on filtering image transmission |
| TWI754806B (en) * | 2019-04-09 | 2022-02-11 | 栗永徽 | System and method for locating iris using deep learning |
| CN110197169A (en) * | 2019-06-05 | 2019-09-03 | 南京邮电大学 | A kind of contactless learning state monitoring system and learning state detection method |
| CN110197169B (en) * | 2019-06-05 | 2022-08-26 | 南京邮电大学 | Non-contact learning state monitoring system and learning state detection method |
| CN112084820A (en) * | 2019-06-14 | 2020-12-15 | 初速度（苏州）科技有限公司 | Personnel state detection method and device based on head information |
| CN112084820B (en) * | 2019-06-14 | 2022-06-24 | 魔门塔(苏州)科技有限公司 | Personnel state detection method and device based on head information |
| CN110909596A (en) * | 2019-10-14 | 2020-03-24 | 广州视源电子科技股份有限公司 | Side face recognition method, device, equipment and storage medium |
| CN112926364B (en) * | 2019-12-06 | 2024-04-19 | 北京四维图新科技股份有限公司 | Head gesture recognition method and system, automobile data recorder and intelligent cabin |
| CN112926364A (en) * | 2019-12-06 | 2021-06-08 | 北京四维图新科技股份有限公司 | Head posture recognition method and system, automobile data recorder and intelligent cabin |
| CN111626221A (en) * | 2020-05-28 | 2020-09-04 | 四川大学 | Driver gazing area estimation method based on human eye information enhancement |
| CN112232128A (en) * | 2020-09-14 | 2021-01-15 | 南京理工大学 | Eye tracking based method for identifying care needs of old disabled people |
| CN112232128B (en) * | 2020-09-14 | 2022-09-13 | 南京理工大学 | Eye tracking based method for identifying care needs of old disabled people |
| CN112869701B (en) * | 2021-01-11 | 2024-03-29 | 上海微创医疗机器人（集团）股份有限公司 | Sight line detection method, surgical robot system, control method, and storage medium |
| CN112869701A (en) * | 2021-01-11 | 2021-06-01 | 上海微创医疗机器人（集团）股份有限公司 | Sight line detection method, surgical robot system, control method, and storage medium |
| CN113331839A (en) * | 2021-05-28 | 2021-09-03 | 武汉科技大学 | Network learning attention monitoring method and system based on multi-source information fusion |
| CN113591699A (en) * | 2021-07-30 | 2021-11-02 | 西安电子科技大学 | Online visual fatigue detection system and method based on deep learning |
| CN113591699B (en) * | 2021-07-30 | 2024-02-09 | 西安电子科技大学 | Online visual fatigue detection system and method based on deep learning |
| CN113591762A (en) * | 2021-08-09 | 2021-11-02 | 重庆理工大学 | Safe driving early warning method under free angle |
| CN113591762B (en) * | 2021-08-09 | 2023-07-25 | 重庆理工大学 | Safe driving early warning method under free angle |
| CN114432098A (en) * | 2022-01-27 | 2022-05-06 | 中山大学附属第一医院 | Gait orthotic devices based on model |
| CN117227740A (en) * | 2023-09-14 | 2023-12-15 | 南京项尚车联网技术有限公司 | Multi-mode sensing system and method for intelligent driving vehicle |
| CN117227740B (en) * | 2023-09-14 | 2024-03-19 | 南京项尚车联网技术有限公司 | Multi-mode sensing system and method for intelligent driving vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109044363A (en) | Driver Fatigue Detection based on head pose and eye movement | |
| Chen et al. | Deepphys: Video-based physiological measurement using convolutional attention networks | |
| CN107193383B (en) | Secondary sight tracking method based on face orientation constraint | |
| US5570698A (en) | System for monitoring eyes for detecting sleep behavior | |
| US7692550B2 (en) | Method and system for detecting operator alertness | |
| US7692551B2 (en) | Method and system for detecting operator alertness | |
| JP5109922B2 (en) | Driver monitoring device and program for driver monitoring device | |
| Batista | A drowsiness and point of attention monitoring system for driver vigilance | |
| Ghosh et al. | Real time eye detection and tracking method for driver assistance system | |
| JP6855872B2 (en) | Face recognition device | |
| CN109076176A (en) | The imaging device and its illumination control method of eye position detection device and method, imaging sensor with rolling shutter drive system | |
| CN109964230A (en) | Method and apparatus for eyes measurement acquisition | |
| JP2004192552A (en) | Eye opening/closing determining apparatus | |
| Kunka et al. | Non-intrusive infrared-free eye tracking method | |
| US10188292B2 (en) | Device for screening convergence insufficiency and related computer implemented methods | |
| Yoon et al. | Driver’s eye-based gaze tracking system by one-point calibration | |
| Anwar et al. | Development of real-time eye tracking algorithm | |
| Apoorva et al. | Review on Drowsiness Detection | |
| Hegde et al. | Low cost eye based human computer interface system (Eye controlled mouse) | |
| Huang et al. | An optimized eye locating and tracking system for driver fatigue monitoring | |
| CN106682588A (en) | Real-time pupil detection and tracking method | |
| EP1901252A2 (en) | Method and system for detecting operator alertness | |
| Venugopal et al. | Real Time Implementation of Eye Tracking System Using Arduino Uno Based Hardware Interface | |
| Thayanithi et al. | Real-Time Voice Enabled Drivers' Safety Monitoring System Using Image Processing | |
| Malla | Automated video-based measurement of eye closure using a remote camera for detecting drowsiness and behavioural microsleeps |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181221 |