CN106203293A - A kind of method and apparatus detecting fatigue driving - Google Patents
A kind of method and apparatus detecting fatigue driving Download PDFInfo
- Publication number
- CN106203293A CN106203293A CN201610508524.0A CN201610508524A CN106203293A CN 106203293 A CN106203293 A CN 106203293A CN 201610508524 A CN201610508524 A CN 201610508524A CN 106203293 A CN106203293 A CN 106203293A
- Authority
- CN
- China
- Prior art keywords
- characteristic portion
- image
- fatigue driving
- eyes
- sample
- 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
- G06V40/16—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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the present invention proposes a kind of method and apparatus detecting fatigue driving, and method includes: obtain facial image step, including: obtain facial image from filming apparatus；Identify characteristic portion step, including: the characteristic portion in described facial image is identified, obtains characteristic portion image；Judge step, including: if the state of characteristic portion meets pre-conditioned described in continuous multiple described characteristic portion image, then it is judged to fatigue driving.The present invention can judge whether driver is fatigue driving accurately, thus improves the safety of driving, makes the cost of detection fatigue driving reduce.
Description
Technical field
The present invention relates to electronic applications, particularly relate to a kind of method and apparatus detecting fatigue driving.
Background technology
In life, the situation of driver tired driving happens occasionally, and endangers safe traffic.
In prior art, the detection to driver tired driving is not accurate enough, frequently results in false alarm, brings to driver
Puzzlement.
In order to solve to detect the various problems occurred in driver tired driving, need defect of the prior art is carried out
Improve, make the driver-operated safety of entirety improve simultaneously, make vehicle accident reduce.
Summary of the invention
Based on problem above, the present invention proposes a kind of method and apparatus detecting fatigue driving, by obtaining from filming apparatus
Take facial image, the characteristic portion in facial image is identified, obtain characteristic portion image, if continuous multiple characteristic portion
In image, the eigenvalue of characteristic portion meets pre-conditioned, then be judged to the mode of fatigue driving, it is possible to judge accurately to drive
Whether the person of sailing is fatigue driving, thus improves the safety of driving, makes the cost of detection fatigue driving reduce.
On the one hand, the present invention proposes a kind of method detecting fatigue driving, including:
Obtain facial image step, including: obtain facial image from filming apparatus；
Identify characteristic portion step, including: the characteristic portion in described facial image is identified, obtains features bitmap
Picture；
Judge step, including: if the state of characteristic portion meets pre-conditioned described in continuous multiple described characteristic portion image,
Then it is judged to fatigue driving.
Additionally, characteristic portion includes eyes and/or mouth described in described identification characteristic portion step.
Additionally, described characteristic portion is eyes, described identification characteristic portion step specifically includes: in described facial image
Eyes be identified, obtain left eye image, right eye image or two eye images.
Additionally, described judgement step specifically includes: if continuous multiple left eye image, right eye image or two eyes figures
In Xiang, the absolute difference between upper marginal position and the lower edge position of eyes is less than presetting the first difference, then be judged as that fatigue is driven
Sail；
Or described judgement step specifically includes: calculate the upper of eyes in left eye image, right eye image or two eye images
Eyes absolute difference between marginal position and lower edge position, calculates between upper marginal position and the lower edge position of eyeball
Eyeball absolute difference, if the ratio between continuous multiple eyeball absolute difference and eyes absolute difference is less than preset ratio value, then
It is judged as fatigue driving；
Or described judgement step specifically includes: if eye in continuous multiple left eye image, right eye image or two eye images
Eyeball is closure state, then be judged as fatigue driving.
Additionally, described characteristic portion is mouth, described identification characteristic portion step specifically includes: in described facial image
Mouth is identified, and obtains mouth image.
Additionally, described judgement step specifically includes: if the upper marginal position of mouth and lower limb position in continuous multiple mouth image
Absolute difference between putting more than presetting the second difference, is then judged as fatigue driving；
Or described judgement step specifically includes: if the mouth in continuous multiple mouth image is open configuration, be then judged as fatigue driving.
Additionally, the characteristic portion in described facial image is identified by described identification characteristic portion step, specifically wrap
Include: by sliding window image, the described characteristic portion in described facial image is scanned for, identify described characteristic portion.
Additionally, also include sample training step before described judgement step, including: face sample is trained, to non-
Face sample is trained, be trained eye sample, be trained non-ocular sample, eyes are opened sample instructs
Practice, be trained eyes closed sample, lip-syncing sample is trained, be trained non-mouth sample, lip-syncing is opened sample and entered
Row training and/or lip-syncing Guan Bi sample are trained.
Additionally, after described judgement step, also include pointing out step, including: if being judged as fatigue driving, then pass through sound
Or the mode of image points out.
On the other hand, the present invention proposes a kind of device detecting fatigue driving, including:
Obtain facial image module, be used for: obtain facial image from filming apparatus；
Identify characteristic portion module, be used for: the characteristic portion in described facial image is identified, obtain features bitmap
Picture；
Judge module, is used for: if the eigenvalue of characteristic portion described in continuous multiple described characteristic portion image meets presets bar
Part, then be judged to fatigue driving.
Use technique scheme, have the advantages that
By obtaining facial image from filming apparatus, the characteristic portion in facial image is identified, obtains features bitmap
Picture, if the eigenvalue of characteristic portion meets pre-conditioned in continuous multiple characteristic portion image, is then judged to the side of fatigue driving
Formula, it is possible to judge whether driver is fatigue driving accurately, thus improve the safety of driving, make detection fatigue driving
Cost reduce.
Accompanying drawing explanation
Fig. 1 is the flow chart of the method detecting fatigue driving according to an embodiment of the invention；
Fig. 2 is the gray level image schematic diagram of the face obtained in accordance with another embodiment of the present invention；
Fig. 3 is the schematic diagram after intercepting face in accordance with another embodiment of the present invention；
Fig. 4 is the schematic diagram of the human eye identified in accordance with another embodiment of the present invention；
Fig. 5 is the flow chart of the method detecting fatigue driving in accordance with another embodiment of the present invention；
Fig. 6 is the block diagram of the device detecting fatigue driving in accordance with another embodiment of the present invention.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
The a part of embodiment of the present invention rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under not making creative work premise, broadly falls into the scope of protection of the invention.
With reference to Fig. 1, the present invention proposes a kind of method detecting fatigue driving, including:
Obtain facial image step S001, including: obtain facial image from filming apparatus；
Identify characteristic portion step S002, including: the characteristic portion in facial image is identified, obtains features bitmap
Picture；
Judge step S003, including: if the eigenvalue of characteristic portion meets pre-conditioned, then in continuous multiple characteristic portion image
It is judged to fatigue driving.
Obtaining in facial image step S001, filming apparatus is the device that can take pictures continuously, such as photographic head.Facial image is
The facial image of driver, obtains the facial image of driver from filming apparatus continuous print.By being arranged on taking the photograph of driver front
As head acquires the live figure on road surface.
Owing to the seat of driver is fixed, and driver needs to fasten the safety belt, so the position of driver is substantially stationary
Constant, i.e. the change in location of the face of driver is little, it is possible to the mode using the face to driver to be identified, and sentences
Disconnected driver whether drive by fatigue.
Identify in characteristic portion step S002, facial image is first carried out image procossing, specific as follows:
Facial image is converted to gray level image, and the transfer function in image library is cvCvtColor, then enters gray level image
Row denoising, the denoising function in image library is cvSmooth.
Face in gray level image is detected roughly, image library function cvHaarDetectObjects can be used
Face is detected roughly.
Then, got rid of the facial image of non-driver by training sample, if training sample is model_face, pass through
Model_face removes the facial image of non-driver, retains the facial image high with training sample similarity.
Support vector machine, because of its English entitled support vector machine, therefore is typically called for short SVM.
In machine learning, support vector machine (SVM goes back support vector network) is the prison relevant with relevant learning algorithm
Superintend and direct learning model, can be with analytical data, recognition mode, for classification and regression analysis.Given one group of training sample, each labelling
For belonging to two classes, a SVM training algorithm establishes a model, and distributing new example is a class or other classes so that it is become
Non-probability binary linearity is classified.The example of one SVM model, such as point in space, maps so that described different classification
Example is to be the expression of the widest division by obvious gap.New embodiment is then mapped in identical space, and
Prediction falls to belonging to a classification in described clearance side based on them.
Except carrying out linear classification, support vector machine can use so-called geo-nuclear tracin4, and their input is implicit to be mapped to
High-dimensional feature space carries out Nonlinear Classification effectively.
Portion intercepts non-face in the facial image that will retain falls, and only retains the part of face.One of which
In embodiment, it is 100x100 that the facial image after intercepting zooms to resolution, stores facial image with standard size, convenient
Follow-up characteristic portion identification, characteristic portion compares.
In one of which embodiment, when the uneven illumination of facial image, normalized method can be used to process, make
In image, the luminance difference of the image of different parts reduces, and makes brightness uniformity.
Facial image after intercepting is carried out characteristic portion identification, and characteristic portion includes: eyes or mouth.Sliding window can be used to calculate
Characteristic portion is identified by method.
In sliding window algorithm (sliding window algorithm), the size of sliding window is 12x32, makes sliding window after intercepting
Facial image in scan for, obtain 900 sliding windows, 900 sliding windows classified respectively, according to eyes instruct
Practicing sample model_eye and the image in classification is calculated score, the sliding window of highest scoring is eye image.Eye according to right eye eyeball
Eyeball training sample obtains eye image img_eye_right, obtains left-eye image img_ according to the eye exercise sample of left eye eyeball
eye_left。
Open sample with eyes and eyes closed sample model_open_close identifies that the eyes in eye image are to open
Open or close.
Citing: the gray level image after facial image gray proces is as in figure 2 it is shown, go non-face part in gray level image
Fall, keep the image of face part as it is shown on figure 3, the eye image identified by sliding window algorithm as shown in Figure 4.
It is also possible to use mouth training sample lip-syncing to be identified.
Judge in step S003, if the state of characteristic portion meets pre-conditioned, then in continuous multiple characteristic portion image
It is judged to fatigue driving.When in continuous multiple facial images, eyes are in closure state, then think fatigue driving.
In one of which embodiment, the profile of eyes in facial image after detection intercepting, if judging the top of eyes
Absolute difference between edge position and lower edge position less than presetting the first difference, is then judged as fatigue driving.If it is the most multiple
In mouth image, the decision difference between upper marginal position and the lower edge position of mouth is more than presetting the second difference, then be judged as fatigue
Drive.
Such as, one second obtains 30 frame facial images, then persistently reach 3 seconds when the time of eyes closed, then judge
Driver is fatigue driving.Maybe when detecting that mouth persistently keeps open configuration 3 seconds, then judge that driver is as fatigue driving.
In one of which embodiment, if facial image is distorted, then it is corrected facial image processing.If inspection
Measure facial image to rotate, then can pass through the angle between line and the horizontal line between two eyes detected
Value, carrys out correction chart picture, makes image be in level.
By obtaining facial image from filming apparatus, the characteristic portion in facial image is identified, obtains features
Bit image, if the eigenvalue of characteristic portion meets pre-conditioned in continuous multiple characteristic portion image, is then judged to fatigue driving
Mode, it is possible to judge whether driver is fatigue driving accurately, thus improve the safety of driving, make detection tired
The cost driven reduces.
In one of which embodiment, identify that in characteristic portion step, characteristic portion includes eyes and/or mouth.By eye
The closing time of eyeball judges that whether driver is in sleep of closing one's eyes.Judge whether driver is yawning by the time of opening of mouth.
Can judge whether driver is fatigue driving accurately by the two characteristic portion.
In one of which embodiment, characteristic portion is eyes, identifies that characteristic portion step specifically includes: to face figure
Eyes in Xiang are identified, and obtain left eye image, right eye image or two eye images.By sliding window algorithm to face
Eyes in image are identified.
In one of which embodiment, it is judged that step specifically includes: if continuous multiple left eye image, right eye image
Or in two eye images absolute difference between upper marginal position and the lower edge position of eyes less than presetting the first difference, then
It is judged as fatigue driving；
Or judge that step specifically includes: calculate the top edge of eyes in left eye image, right eye image or two eye images
Eyes absolute difference between position and lower edge position, calculates the eyeball between upper marginal position and the lower edge position of eyeball
Absolute difference, if the ratio between continuous multiple eyeball absolute difference and eyes absolute difference is less than preset ratio value, then judges
For fatigue driving；
Or judge that step specifically includes: if eyes are in continuous multiple left eye image, right eye image or two eye images
Closure state, then be judged as fatigue driving.
In the contour images of employing detection eyes, the absolute difference between upper marginal position and the lower edge position of eyes is
No less than presetting the first difference, judge whether driver narrows eye or eye closing, thus judge driver's whether fatigue driving.
Because varying in size of the human eye of different people, so can also be by judging eyeball absolute difference and eyes absolute difference
Whether the ratio between value is less than the mode of preset ratio value, it is judged that whether driver is fatigue driving.Thus solve because of people
Eye is different, and uses same standard that human eye judges the erroneous judgement brought.
Use the mode with eye exercise sample matches, obtain the state of eyes, if eyes are closure state, be then judged as
Fatigue driving.
In one of which embodiment, characteristic portion is mouth, identifies that characteristic portion step specifically includes: to facial image
In mouth be identified, obtain mouth image.
In one of which embodiment, it is judged that step specifically includes: if the top edge position of mouth in continuous multiple mouth image
Put the absolute difference between lower edge position and be more than default second difference, be then judged as fatigue driving；
Or judge that step specifically includes: if the mouth in continuous multiple mouth image is open configuration, then it is judged as fatigue driving.
The profile of detection mouth, if the absolute difference between the upper marginal position of mouth and lower edge position is poor more than presetting second
Value, then be judged as fatigue driving.When mouth is yawning time, and mouth can persistently open a period of time, so by the inspection of lip-syncing
Survey can accurately judge whether driver is fatigue driving.
In one of which embodiment, identify in characteristic portion step and the characteristic portion in facial image is known
Not, specifically include: by sliding window image, the characteristic portion in facial image is scanned for, identify characteristic portion.By cunning
Window image adaptation training sample method, makes the characteristic portion identified more accurate.
In one of which embodiment, it is judged that also include sample training step before step, including: face sample is entered
Row is trained, is trained non-face sample, is trained eye sample, non-ocular sample is trained, is opened eyes
Open that sample is trained, is trained eyes closed sample, lip-syncing sample is trained, non-mouth sample be trained, right
Mouth open sample be trained and/or lip-syncing Guan Bi sample be trained.
In one of which embodiment, it is judged that after step, also include pointing out step, including: if being judged as, fatigue is driven
Sail, then point out by the way of sound or image.By driver is pointed out, make driver can release sleepiness,
Or drive again, such that it is able to avoid dangerous driving after selecting to have a rest.
With reference to Fig. 5, the flow process of one embodiment of the invention is described.
Step S501, continuously acquires facial image from camera head；
Step S502, carries out gray proces, Denoising disposal to facial image；
Step S503, removes non-face part in facial image, only retains face part；
Step S504, uses sliding window algorithm, coordinates training sample, the characteristic portion in facial image: eyes and mouth are known
Not；
Step S505, it is judged that eyes and the state of mouth, if continuing the state that state is closure state or mouth of 3 seconds eyes for opening
Open state, then judge that driver is as fatigue driving；
Step S506, is pointed out driver by sound.
With reference to Fig. 6, the present invention also proposes a kind of device detecting fatigue driving, including:
Obtain facial image module 601, be used for: obtain facial image from filming apparatus；
Identify characteristic portion module 602, be used for: the characteristic portion in facial image is identified, obtain characteristic portion image；
Judge module 603, is used for: if the eigenvalue of characteristic portion meets pre-conditioned, then in continuous multiple characteristic portion image
It is judged to fatigue driving.
Device embodiment described above is only schematically, and the wherein said unit illustrated as separating component can
To be or to may not be physically separate, the parts shown as unit can be or may not be physics list
Unit, i.e. may be located at a place, or can also be distributed on multiple NE.Can be selected it according to the actual needs
In some or all of module realize the purpose of the present embodiment scheme.Those of ordinary skill in the art are not paying creativeness
Work in the case of, be i.e. appreciated that and implement.
Through the above description of the embodiments, those skilled in the art it can be understood that to each embodiment can
The mode adding required general hardware platform by software realizes, naturally it is also possible to pass through hardware.Based on such understanding, on
State the part that prior art contributes by technical scheme the most in other words to embody with the form of software product, should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD etc., including some fingers
Make with so that a computer equipment (can be personal computer, server, or the network equipment etc.) performs each and implements
The method described in some part of example or embodiment.
Last it is noted that above example is only in order to illustrate technical scheme, it is not intended to limit；Although
With reference to previous embodiment, the present invention is described in detail, it will be understood by those within the art that: it still may be used
So that the technical scheme described in foregoing embodiments to be modified, or wherein portion of techniques feature is carried out equivalent；
And these amendment or replace, do not make appropriate technical solution essence depart from various embodiments of the present invention technical scheme spirit and
Scope.
Claims (10)
1. the method detecting fatigue driving, it is characterised in that including:
Obtain facial image step, including: obtain facial image from filming apparatus；
Identify characteristic portion step, including: the characteristic portion in described facial image is identified, obtains features bitmap
Picture；
Judge step, including: if the state of characteristic portion meets pre-conditioned described in continuous multiple described characteristic portion image,
Then it is judged to fatigue driving.
The method of detection fatigue driving the most according to claim 1, it is characterised in that:
Described in described identification characteristic portion step, characteristic portion includes eyes and/or mouth.
The method of detection fatigue driving the most according to claim 2, it is characterised in that:
Described characteristic portion is eyes, and described identification characteristic portion step specifically includes: enter the eyes in described facial image
Row identifies, obtains left eye image, right eye image or two eye images.
The method of detection fatigue driving the most according to claim 3, it is characterised in that:
Described judgement step specifically includes: if eyes in continuous multiple left eye image, right eye image or two eye images
Upper marginal position and lower edge position between absolute difference less than preset the first difference, then be judged as fatigue driving；
Or described judgement step specifically includes: calculate the upper of eyes in left eye image, right eye image or two eye images
Eyes absolute difference between marginal position and lower edge position, calculates between upper marginal position and the lower edge position of eyeball
Eyeball absolute difference, if the ratio between continuous multiple eyeball absolute difference and eyes absolute difference is less than preset ratio value, then
It is judged as fatigue driving；
Or described judgement step specifically includes: if eye in continuous multiple left eye image, right eye image or two eye images
Eyeball is closure state, then be judged as fatigue driving.
The method of detection fatigue driving the most according to claim 2, it is characterised in that:
Described characteristic portion is mouth, and described identification characteristic portion step specifically includes: know the mouth in described facial image
Not, mouth image is obtained.
The method of detection fatigue driving the most according to claim 5, it is characterised in that:
Described judgement step specifically includes: if exhausted between upper marginal position and the lower edge position of mouth in continuous multiple mouth image
To difference more than presetting the second difference, then it is judged as fatigue driving；
Or described judgement step specifically includes: if the mouth in continuous multiple mouth image is open configuration, be then judged as fatigue driving.
The method of detection fatigue driving the most according to claim 1, it is characterised in that:
Characteristic portion in described facial image is identified by described identification characteristic portion step, specifically includes: by cunning
Described characteristic portion in described facial image is scanned for by window image, identifies described characteristic portion.
8. according to the method for the detection fatigue driving described in any one of claim 1 to 7, it is characterised in that:
Sample training step is also included before described judgement step, including: face sample is trained, non-face sample is entered
Row is trained, is trained eye sample, is trained non-ocular sample, eyes are opened sample is trained, to eyes
Sample is trained Guan Bi, lip-syncing sample is trained, be trained non-mouth sample, lip-syncing open sample be trained and/
Or lip-syncing Guan Bi sample is trained.
The method of detection fatigue driving the most according to claim 8, it is characterised in that:
After described judgement step, also include pointing out step, including: if being judged as fatigue driving, then by sound or image
Mode is pointed out.
10. the device detecting fatigue driving, it is characterised in that including:
Obtain facial image module, be used for: obtain facial image from filming apparatus；
Identify characteristic portion module, be used for: the characteristic portion in described facial image is identified, obtain features bitmap
Picture；
Judge module, is used for: if the eigenvalue of characteristic portion described in continuous multiple described characteristic portion image meets presets bar
Part, then be judged to fatigue driving.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610508524.0A CN106203293A (en) | 2016-06-29 | 2016-06-29 | A kind of method and apparatus detecting fatigue driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610508524.0A CN106203293A (en) | 2016-06-29 | 2016-06-29 | A kind of method and apparatus detecting fatigue driving |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106203293A true CN106203293A (en) | 2016-12-07 |
Family
ID=57464496
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610508524.0A Pending CN106203293A (en) | 2016-06-29 | 2016-06-29 | A kind of method and apparatus detecting fatigue driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106203293A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106898119A (en) * | 2017-04-26 | 2017-06-27 | 华迅金安（北京）科技有限公司 | Safety operation intelligent monitoring system and method based on binocular camera |
| CN106965675A (en) * | 2017-04-26 | 2017-07-21 | 华迅金安（北京）科技有限公司 | A kind of lorry swarm intelligence safety work system |
| WO2020015145A1 (en) * | 2018-07-16 | 2020-01-23 | 华为技术有限公司 | Method and electronic device for detecting open and closed states of eyes |
| WO2020062969A1 (en) * | 2018-09-27 | 2020-04-02 | 北京市商汤科技开发有限公司 | Action recognition method and device, and driver state analysis method and device |
| CN110956781A (en) * | 2019-11-28 | 2020-04-03 | 同济大学 | Fatigue driving monitoring system based on video analysis |
| CN111645695A (en) * | 2020-06-28 | 2020-09-11 | 北京百度网讯科技有限公司 | Fatigue driving detection method and device, computer equipment and storage medium |
| US10963135B2 (en) | 2019-03-15 | 2021-03-30 | Oracle International Corporation | Language-based manipulation of data visualizations |
| CN113095108A (en) * | 2019-12-23 | 2021-07-09 | 中移物联网有限公司 | Fatigue driving detection method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101950355A (en) * | 2010-09-08 | 2011-01-19 | 中国人民解放军国防科学技术大学 | Method for detecting fatigue state of driver based on digital video |
| CN102436715A (en) * | 2011-11-25 | 2012-05-02 | 大连海创高科信息技术有限公司 | Detection method for fatigue driving |
| CN104809445A (en) * | 2015-05-07 | 2015-07-29 | 吉林大学 | Fatigue driving detection method based on eye and mouth states |
| CN105632104A (en) * | 2016-03-18 | 2016-06-01 | 内蒙古大学 | Fatigue driving detection system and method |
-
2016
- 2016-06-29 CN CN201610508524.0A patent/CN106203293A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101950355A (en) * | 2010-09-08 | 2011-01-19 | 中国人民解放军国防科学技术大学 | Method for detecting fatigue state of driver based on digital video |
| CN102436715A (en) * | 2011-11-25 | 2012-05-02 | 大连海创高科信息技术有限公司 | Detection method for fatigue driving |
| CN104809445A (en) * | 2015-05-07 | 2015-07-29 | 吉林大学 | Fatigue driving detection method based on eye and mouth states |
| CN105632104A (en) * | 2016-03-18 | 2016-06-01 | 内蒙古大学 | Fatigue driving detection system and method |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106898119A (en) * | 2017-04-26 | 2017-06-27 | 华迅金安（北京）科技有限公司 | Safety operation intelligent monitoring system and method based on binocular camera |
| CN106965675A (en) * | 2017-04-26 | 2017-07-21 | 华迅金安（北京）科技有限公司 | A kind of lorry swarm intelligence safety work system |
| CN106965675B (en) * | 2017-04-26 | 2019-02-05 | 华迅金安（北京）科技有限公司 | A kind of lorry swarm intelligence safety work system |
| WO2020015145A1 (en) * | 2018-07-16 | 2020-01-23 | 华为技术有限公司 | Method and electronic device for detecting open and closed states of eyes |
| WO2020062969A1 (en) * | 2018-09-27 | 2020-04-02 | 北京市商汤科技开发有限公司 | Action recognition method and device, and driver state analysis method and device |
| US10963135B2 (en) | 2019-03-15 | 2021-03-30 | Oracle International Corporation | Language-based manipulation of data visualizations |
| CN110956781A (en) * | 2019-11-28 | 2020-04-03 | 同济大学 | Fatigue driving monitoring system based on video analysis |
| CN113095108A (en) * | 2019-12-23 | 2021-07-09 | 中移物联网有限公司 | Fatigue driving detection method and device |
| CN113095108B (en) * | 2019-12-23 | 2023-11-10 | 中移物联网有限公司 | Fatigue driving detection method and device |
| CN111645695A (en) * | 2020-06-28 | 2020-09-11 | 北京百度网讯科技有限公司 | Fatigue driving detection method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106203293A (en) | A kind of method and apparatus detecting fatigue driving | |
| KR102596897B1 (en) | Method of motion vector and feature vector based fake face detection and apparatus for the same | |
| CN106257489A (en) | Expression recognition method and system | |
| CN105404884B (en) | Image analysis method | |
| CN107358152B (en) | Living body identification method and system | |
| CN101211411B (en) | Human body detection process and device | |
| US20210334998A1 (en) | Image processing method, apparatus, device and medium for locating center of target object region | |
| CN104361332B (en) | A kind of face eye areas localization method for fatigue driving detection | |
| KR101706992B1 (en) | Apparatus and method for tracking gaze, recording medium for performing the method | |
| CN109858375A (en) | Living body faces detection method, terminal and computer readable storage medium | |
| JP7197485B2 (en) | Detection system, detection device and method | |
| CN108647708A (en) | Driver evaluation's method, apparatus, equipment and storage medium | |
| CN105740751A (en) | Object detection and identification method and system | |
| CN110543848B (en) | Driver action recognition method and device based on three-dimensional convolutional neural network | |
| CN111062292A (en) | Fatigue driving detection device and method | |
| Davis et al. | Facial recognition using human visual system algorithms for robotic and UAV platforms | |
| US11875603B2 (en) | Facial action unit detection | |
| KR101343623B1 (en) | adaptive color detection method, face detection method and apparatus | |
| CN111314704A (en) | Prediction method, device and equipment of image level JND threshold value and storage medium | |
| Long et al. | Near infrared face image quality assessment system of video sequences | |
| JP6751324B2 (en) | Iris detection device, iris detection method, and program | |
| CN109657550B (en) | Fatigue degree detection method and device | |
| TWI550440B (en) | Method and system for detecting person to use handheld apparatus | |
| CN111881732B (en) | SVM (support vector machine) -based face quality evaluation method | |
| GB2522259A (en) | A method of object orientation detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161207 |
|
| RJ01 | Rejection of invention patent application after publication |