CN110059599A - Driving fatigue method for early warning - Google Patents
Driving fatigue method for early warning Download PDFInfo
- Publication number
- CN110059599A CN110059599A CN201910275574.2A CN201910275574A CN110059599A CN 110059599 A CN110059599 A CN 110059599A CN 201910275574 A CN201910275574 A CN 201910275574A CN 110059599 A CN110059599 A CN 110059599A
- Authority
- CN
- China
- Prior art keywords
- data
- opening degree
- fatigue
- personal
- eye closing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 63
- 241001282135 Poromitra oscitans Species 0.000 claims abstract description 8
- 206010048232 Yawning Diseases 0.000 claims abstract description 8
- 230000001815 facial effect Effects 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000013480 data collection Methods 0.000 claims description 3
- 239000012141 concentrate Substances 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims 1
- 238000001514 detection method Methods 0.000 description 8
- 238000012360 testing method Methods 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036461 convulsion Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- 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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a kind of driving fatigue method for early warning, by in driver's face-image eye state and mouth state be monitored and obtain to close one's eyes and duration, nozzle part opening degree and dehisce the duration, and above-mentioned data be compared with default early-warning parameters value or are compared with for personal early-warning parameters value, to judge driver fatigue state, closing one's eyes, the duration, to can reflect driver when accounting for relatively high in a state of fatigue, and nozzle part opening degree, which increases and dehisces to can reflect driver when the duration is longer, is yawning.The method of the present invention driving condition no to driver invades, and the degree of correlation of close one's eyes duration accounting, opening degree and dehisce duration and driving condition is higher.
Description
Technical field
The present invention relates to a kind of driving fatigue method for early warning, belong to mobile unit technical field.
Background technique
Traffic accident amount caused by fatigue driving also once rises therewith.According to investigations, China's traffic thing relevant to fatigue
Therefore 20% of total number of accident or so is accounted for, 40% or more of particularly serious traffic accident is accounted for, is lack of pertinence strong, technology currently on the market
Mature traffic insurance facility is directed to fatigue driving, and fatigue driving state, which issues, makes trouble therefore or close to the wind that accident occurs
Danger is 4 to 6 times under awake driving condition.Driving fatigue be it is a kind of at heart, physiological state change process, it is difficult to as drunk driving one
Sample is measured with quantitative physical signs.
From the point of view of the index that driving fatigue detects, detection method is broadly divided into existing anti-tired mobile unit: subjective tired
Please detection and objective fatigue driving detection are sailed.Subjective detection method mainly has Pearson came fatigue scale, driver self to remember
Record table, Stamford sleep scale table, the detection of knee jerk function etc.；Objective measure is broadly divided into: by being based on vehicle row
For special fatigue driving Testing index, such as vehicle shift and steering wheel angle, a large number of experiments show that vehicle behavior with
The correlation of driver's driving condition is lower；Based on the Testing index of physiological driver's information, such as ECG, pulse, myoelectricity, to the greatest extent
It manages such index and driving condition correlation is higher, but is invasive relatively strong, be affected to driver's driving condition.
Summary of the invention
The purpose of the present invention is to provide a kind of driving fatigue method for early warning, existing driving fatigue detection method is solved to driving
The invasive height of the person of sailing, data and the lower technological deficiency of driving condition correlation of acquisition.
A kind of driving fatigue method for early warning, includes the following steps:
Step 1: obtaining the facial frame image of driver, personal data are obtained from Cloud Server based on facial frame image；
Step 2: obtaining facial frame image, ocular and mouth region are positioned on facial frame image；
Step 3；Eye state is obtained, totalframes adds one, and judges the closed state of eyes in current face frame image,
When eyes are closed states, eye closing frame number adds one；
Mouth state is obtained, judges the open configuration of mouth in current face frame image,
When mouth is open configuration, opening degree is obtained, is stored in opening degree collection, frame number is opened and adds one；
Step 4: totalframes and the variation of mouth open configuration are judged
When totalframes reaches default processing frame number, eye closing accounting, resetting are calculated based on eye closing frame number and frame number sum
Frame number sum, executes step 5；
When not up to default processing frame number, step 2 is executed to step 4；
It when mouth becomes closed state by open configuration, is concentrated from opening degree and obtains maximum opening degree, by opening frame
Number, which calculates, dehisces the duration, resets opening degree collection, and frame number is opened in resetting, executes step 5；
When mouth open configuration does not change, step 2 is executed to step 4；
Step 5: judge whether there are personal fatigue criteria data in personal data,
When there is no personal fatigue criteria data, step A51 is executed；
When there are personal fatigue criteria data, step B51 is executed；
Step A51: by the eye closing accounting in the step 4 compared with default eye closing accounting data,
When eye closing accounting is greater than default eye closing accounting data, judge that driver is in a state of fatigue；
By the maximum opening degree in the step 4 compared with default opening degree normal data, and will dehisce the duration with
The default time of dehiscing compares,
When maximum opening degree be greater than default opening degree normal data and the duration of dehiscing be greater than it is default dehisce the time when,
Judge that driver is yawning；
Step 2 is executed to step 4；
Step B51: personal eye closing accounting data are obtained from personal fatigue criteria data, by the eye closing in the step 4
Accounting compared with personal eye closing accounting data,
When eye closing accounting is greater than personal eye closing accounting data, judge that driver is in a state of fatigue；
Personal opening degree normal data is obtained from personal fatigue criteria data and individual dehisces the time, by the step
Compared with maximum opening degree is compared with personal opening degree normal data in 3, and the duration that will dehisce dehisces the time with individual
When maximum opening degree be greater than personal opening degree normal data and dehisce the duration greater than individual dehisce the time when,
Judge that driver is yawning；
Step 2 is executed to step 4.
Further, the personal fatigue criteria data are the trained Method Using Relevance Vector Machine of fatigue strength,
Judge whether to have in personal data in the step 5 personal fatigue criteria data be judge in personal data whether
There is the trained Method Using Relevance Vector Machine of fatigue strength；
In the step B51, by eye closing accounting be put into the trained Method Using Relevance Vector Machine of fatigue strength or by maximum opening degree and
The mouth duration is put into the trained Method Using Relevance Vector Machine of fatigue strength, and the calculated result based on the trained Method Using Relevance Vector Machine of fatigue strength judges to drive
Member's fatigue state.
Further, further include following steps after the step A51:
Step A52: by corresponding judging result in eye closing accounting, maximum opening degree, dehisce duration and step A51
It is stored in training dataset as training data, when training data concentrates data volume to reach preset data collection amount, passes through training
Data set establishes the trained Method Using Relevance Vector Machine of fatigue strength.
Further, the default eye closing accounting data are 0.4, and the default opening degree normal data is 0.65, described
The default time of dehiscing is 2.1s.
Further, face is tracked by Camshift algorithm in the step 2, passes through Adaboost algorithm
Obtain facial frame image.
Compared with prior art, the beneficial effects of the present invention are:
The method of the present invention mainly by driver's face-image eye state and mouth state be monitored come
Driver fatigue state is obtained, it is in a state of fatigue that the duration of closing one's eyes can reflect driver when accounting for relatively high, nozzle part opening
Degree, which increases and dehisces to can reflect driver when the duration is longer, is yawning, the method for the present invention driving no to driver
State is invaded, and the degree of correlation of close one's eyes duration accounting, opening degree and dehisce duration and driving condition is higher.
The method of the present invention with calculate fatigue strength the trained Method Using Relevance Vector Machine of fatigue strength to eye closing accounting, maximum opening degree with
And the duration of dehiscing carries out the judgement of fatigue state, and judgment accuracy can be improved.The present invention is established tired by real time data
The trained Method Using Relevance Vector Machine of Lao Du, the trained Method Using Relevance Vector Machine of the fatigue strength of foundation are established tired for individual with real time data
The trained Method Using Relevance Vector Machine of Lao Du can establish suitable for personal tired judgment criteria, avoid judging precision caused by individual differences
It is low, make up defect inaccurate when preset normal data judges ownness.
The method of the present invention, which obtains facial frame image with Camshift algorithm combination Adaboost algorithm, can overcome illumination
Influence to face.
Specific embodiment
Below with reference to embodiment, the invention will be further described.
Driving fatigue method for early warning of the invention, includes the following steps:
Step 1: obtaining the facial frame image of driver, personal data are obtained from Cloud Server based on facial frame image；
Step 2: obtaining facial frame image, ocular and mouth region are positioned on facial frame image；
Step 3；Eye state is obtained, totalframes adds one, and judges the closed state of eyes in current face frame image,
When eyes are closed states, eye closing frame number adds one；
Mouth state is obtained, judges the open configuration of mouth in current face frame image,
When mouth is open configuration, opening degree is obtained, is stored in opening degree collection, frame number is opened and adds one；
Step 4: totalframes and the variation of mouth open configuration are judged
When totalframes reaches default processing frame number, eye closing accounting, resetting are calculated based on eye closing frame number and frame number sum
Frame number sum, executes step 5；
When not up to default processing frame number, step 2 is executed to step 4；
It when mouth becomes closed state by open configuration, is concentrated from opening degree and obtains maximum opening degree, by opening frame
Number, which calculates, dehisces the duration, resets opening degree collection, and frame number is opened in resetting, executes step 5；
When mouth open configuration does not change, step 2 is executed to step 4；
Step 5: judge whether there are personal fatigue criteria data in personal data,
When there is no personal fatigue criteria data, step A51 is executed；
When there are personal fatigue criteria data, step B51 is executed；
Step A51: by the eye closing accounting in the step 4 compared with default eye closing accounting data,
When eye closing accounting is greater than default eye closing accounting data, judge that driver is in a state of fatigue；
By the maximum opening degree in the step 4 compared with default opening degree normal data, and will dehisce the duration with
The default time of dehiscing compares,
When maximum opening degree be greater than default opening degree normal data and the duration of dehiscing be greater than it is default dehisce the time when,
Judge that driver is yawning；
Step 2 is executed to step 4；
Step B51: personal eye closing accounting data are obtained from personal fatigue criteria data, by the eye closing in the step 4
Accounting compared with personal eye closing accounting data,
When eye closing accounting is greater than personal eye closing accounting data, judge that driver is in a state of fatigue；
Personal opening degree normal data is obtained from personal fatigue criteria data and individual dehisces the time, by the step
Compared with maximum opening degree is compared with personal opening degree normal data in 3, and the duration that will dehisce dehisces the time with individual
When maximum opening degree be greater than personal opening degree normal data and dehisce the duration greater than individual dehisce the time when,
Judge that driver is yawning；
Step 2 is executed to step 4.
Specifically:
The method of the present invention applies to Cloud Server and stores to personal data in step 1, is schemed according to the face of driver
Personal data are obtained as log in, to realize that driver can be according to driver personal data when driving any vehicle
Situation is monitored driving condition.Personal data mainly include personal identity information, personal fatigue criteria data.Driver
When being detected for the first time using the method for the present invention to fatigue strength, it is necessary to improve personal identity information, personal fatigue criteria data
Not nonessential information.
Camshift algorithm is cooperated to obtain to be tracked simultaneously to driver's face by Adabosst algorithm in step 2
Facial frame image is obtained, and identifies ocular and mouth region in facial frame image, facial frame image is continuous surface
The image of a certain frame in portion's image.
First extract eye profile and mouth profile in step 3 in ocular and mouth region, then by eye profile and
The processing of mouth profile coordinatograph.Pass through the folding shape of eye profile coordinate and the available eye of mouth profile coordinate and mouth
State.
When the eye state of acquisition is closure, eye closing frame number is added one, since the method for the present invention is to each frame image
It is handled, so accumulative eye closing frame number is equivalent to the time of eyes closed, accumulative totalframes is equivalent to a certain section continuously
Face-image duration.
When the mouth state of acquisition is to open, whether mouth has opened before first judging the frame image, can pass through
Flag bit is established to realize, mouth does not open before the frame image, then indicates to start new at this time by flag bit
It makes a slip of the tongue journey.Due to the opening degree meeting time to time change that mouth opens, and opening process can continue several frames, so establishing one
Opening degree collection stores several opening degrees that this is dehisced, and by open frame number react this mouth opening it is lasting when
Between.Wherein, the opening degree of mouth is the ratio of the spacing of height and the corners of the mouth that mouth opens.
The method of the present invention is that fatigue is reacted by the accounting to eye closing frame number in one section of continuous face-image in step 4
State, i.e., when the totalframes for reacting continuous facial picture duration has reached default processing frame number, calculate eye closing frame
Several ratios with totalframes, as eye closing accounting.
Due to being to be charged to when mouth is opened to opening degree and opening frame number, and mouth opening is one in step 3
A duration process, so illustrating to have completed an opening and closing when detecting that mouth becomes closed state from open configuration
Journey, concentrating the maximum opening degree of acquisition and the duration by opening frame number acquisition opening and closing process in opening degree at this time is
The mouth duration.
Since face-image acquires in real time, and the method for the present invention is handled each frame of acquisition image,
Step 2 to step 4 is the treatment process to a certain frame image, so the process can be repeated when the condition in step 4 is not reached,
Until condition, which meets, starts subsequent the step of judging fatigue strength.
It is tired to driver according to the eye closing accounting, maximum opening degree and the duration of dehiscing that are obtained in step 4 in step 5
Lao Du is judged.Judgement uses two ways, and one is being compared with preset parameter value, another kind is and is directed to individual
Parameter value be compared, parameter value includes eye closing accounting data, opening degree normal data and dehisces the time.Preset parameter
Value is a general value, is for public threshold values.
When in personal data without individual's fatigue criteria data, using above-mentioned first method, wherein default close one's eyes accounts for
Than data preferably 0.4, presetting opening degree normal data is 0.65, and the default time of dehiscing is 2.1s, and above-mentioned data are by comparing examination
Test acquisition.When the data obtained in step 4 reach preset value, determine that driver is in a state of fatigue.
When there is personal fatigue criteria data in personal data, when using second method, wherein eye closing accounting data, open
Mouth degree normal data and time of dehiscing are to carry out specific aim setting for personal situation.When the data obtained in step 4 reach
When to personal preset value, determine that driver is in a state of fatigue.
It is preferably that the fatigue strength for calculating fatigue strength is trained in step 5 using trained Method Using Relevance Vector Machine feature with strong points
Method Using Relevance Vector Machine carries out the judgement of fatigue strength as personal fatigue strength normal data to the data obtained in step 4.As long as will step
The data obtained in rapid 4 are put into the trained Method Using Relevance Vector Machine of fatigue strength, judge driver fatigue state according to output result.
The trained Method Using Relevance Vector Machine of fatigue strength can be established by way of hand input-data.The eye closing accounting being manually entered
Data, opening degree normal data dehisce the time and corresponding judging result is tested under experimental situation by the driver
It obtains, data accuracy is lower.
The trained Method Using Relevance Vector Machine of fatigue strength is preferably built when driver detects fatigue strength using the method for the present invention in real time
Vertical, after step A51, by eye closing accounting, maximum opening degree used in step A51, dehisce duration and correspondence
Training parameter of the judging result as vector machine, gradually establish corresponding trained phase to be input to characteristic parameter data matrix
Close vector machine.Trained Method Using Relevance Vector Machine processing knot can be improved in the trained Method Using Relevance Vector Machine of fatigue strength established by real time data
The accuracy of fruit.
Since detection process is a continuity process, so can be again since step 2 after step 5 is finished
It executes, the step cycle is until detection terminates.
Can by and be not limited to existing image acquisition device the method for the present invention cooperated to obtain needed for the method for the present invention
Facial frame image.The method of the present invention can be run in Cloud Server, by Cloud Server to needed for the method for the present invention
Personal data is stored, and can also be run in native processor, be stored in local storage medium to personal data.Fortune
The applicability and convenience of the method for the present invention can be improved with Cloud Server.
In addition to the implementation, the present invention can also have other embodiments, all to use equivalent substitution or equivalent transformation shape
At technical solution, be all fallen within the protection domain of application claims.
Claims (5)
1. a kind of driving fatigue method for early warning, which comprises the steps of:
Step 1: obtaining the facial frame image of driver, personal data are obtained from Cloud Server based on facial frame image；
Step 2: obtaining facial frame image, ocular and mouth region are positioned on facial frame image；
Step 3；Eye state is obtained, totalframes adds one, and judges the closed state of eyes in current face frame image,
When eyes are closed states, eye closing frame number adds one；
Mouth state is obtained, judges the open configuration of mouth in current face frame image,
When mouth is open configuration, opening degree is obtained, is stored in opening degree collection, frame number is opened and adds one；
Step 4: totalframes and the variation of mouth open configuration are judged
When totalframes reaches default processing frame number, eye closing accounting is calculated based on eye closing frame number and frame number sum, resets frame number
Sum executes step 5；
When not up to default processing frame number, step 2 is executed to step 4；
It when mouth becomes closed state by open configuration, is concentrated from opening degree and obtains maximum opening degree, by opening frame number meter
Calculation is dehisced the duration, and opening degree collection is reset, and frame number is opened in resetting, executes step 5；
When mouth open configuration does not change, step 2 is executed to step 4；
Step 5: judge whether there are personal fatigue criteria data in personal data,
When there is no personal fatigue criteria data, step A51 is executed；
When there are personal fatigue criteria data, step B51 is executed；
Step A51: by the eye closing accounting in the step 4 compared with default eye closing accounting data,
When eye closing accounting is greater than default eye closing accounting data, judge that driver is in a state of fatigue；
By the maximum opening degree in the step 4 compared with default opening degree normal data, and the duration and default of dehiscing
Time of dehiscing compares,
When maximum opening degree be greater than default opening degree normal data and the duration of dehiscing be greater than it is default dehisce the time when, judgement
Driver is yawning；
Step 2 is executed to step 4；
Step B51: personal eye closing accounting data are obtained from personal fatigue criteria data, by the eye closing accounting in the step 4
Compared with personal eye closing accounting data,
When eye closing accounting is greater than personal eye closing accounting data, judge that driver is in a state of fatigue；
Personal opening degree normal data is obtained from personal fatigue criteria data and individual dehisces the time, it will be in the step 3
Maximum opening degree is compared with personal opening degree normal data, and compared with the duration that will dehisce dehisces the time with individual
When maximum opening degree be greater than personal opening degree normal data and dehisce the duration greater than individual dehisce the time when, judgement
Driver is yawning；
Step 2 is executed to step 4.
2. driving fatigue method for early warning as described in claim 1, which is characterized in that individual's fatigue criteria data are fatigue
Trained Method Using Relevance Vector Machine is spent,
Judge whether to have in personal data in the step 5 personal fatigue criteria data be judge whether to have in personal data it is tired
The trained Method Using Relevance Vector Machine of Lao Du；
In the step B51, eye closing accounting is put into the trained Method Using Relevance Vector Machine of fatigue strength or by maximum opening degree and dehisces to hold
The continuous time is put into the trained Method Using Relevance Vector Machine of fatigue strength, and the calculated result based on the trained Method Using Relevance Vector Machine of fatigue strength judges that driver is tired
Labor state.
3. driving fatigue method for early warning as claimed in claim 1 or 2, which is characterized in that after the step A51 further include as
Lower step:
Step A52: using corresponding judging result in eye closing accounting, maximum opening degree, dehisce duration and step A51 as
Training is stored in training dataset with data, when training data concentrates data volume to reach preset data collection amount, passes through training data
Collection establishes the trained Method Using Relevance Vector Machine of fatigue strength.
4. driving fatigue method for early warning as described in claim 1, which is characterized in that the default eye closing accounting data are 0.4,
The default opening degree normal data is 0.65, and the default time of dehiscing is 2.1s.
5. driving fatigue method for early warning as described in claim 1, which is characterized in that calculated in the step 2 by Camshift
Method tracks face, obtains facial frame image by Adaboost algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910275574.2A CN110059599A (en) | 2019-04-08 | 2019-04-08 | Driving fatigue method for early warning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910275574.2A CN110059599A (en) | 2019-04-08 | 2019-04-08 | Driving fatigue method for early warning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110059599A true CN110059599A (en) | 2019-07-26 |
Family
ID=67318491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910275574.2A Pending CN110059599A (en) | 2019-04-08 | 2019-04-08 | Driving fatigue method for early warning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110059599A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111784973A (en) * | 2020-07-30 | 2020-10-16 | 广州敏视数码科技有限公司 | MDVR equipment integration fatigue detection method of fleet management platform |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809445A (en) * | 2015-05-07 | 2015-07-29 | 吉林大学 | Fatigue driving detection method based on eye and mouth states |
| CN108446600A (en) * | 2018-02-27 | 2018-08-24 | 上海汽车集团股份有限公司 | A kind of vehicle driver's fatigue monitoring early warning system and method |
| CN108545080A (en) * | 2018-03-20 | 2018-09-18 | 北京理工大学 | Driver Fatigue Detection and system |
| CN108875642A (en) * | 2018-06-21 | 2018-11-23 | 长安大学 | A kind of method of the driver fatigue detection of multi-index amalgamation |
-
2019
- 2019-04-08 CN CN201910275574.2A patent/CN110059599A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809445A (en) * | 2015-05-07 | 2015-07-29 | 吉林大学 | Fatigue driving detection method based on eye and mouth states |
| CN108446600A (en) * | 2018-02-27 | 2018-08-24 | 上海汽车集团股份有限公司 | A kind of vehicle driver's fatigue monitoring early warning system and method |
| CN108545080A (en) * | 2018-03-20 | 2018-09-18 | 北京理工大学 | Driver Fatigue Detection and system |
| CN108875642A (en) * | 2018-06-21 | 2018-11-23 | 长安大学 | A kind of method of the driver fatigue detection of multi-index amalgamation |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111784973A (en) * | 2020-07-30 | 2020-10-16 | 广州敏视数码科技有限公司 | MDVR equipment integration fatigue detection method of fleet management platform |
| CN111784973B (en) * | 2020-07-30 | 2021-12-14 | 广州敏视数码科技有限公司 | MDVR equipment integration fatigue detection method of fleet management platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yan et al. | Real-time driver drowsiness detection system based on PERCLOS and grayscale image processing | |
| US9286515B2 (en) | Doze detection method and apparatus thereof | |
| JP4743137B2 (en) | Sleepiness determination apparatus and program | |
| CN107798318A (en) | The method and its device of a kind of happy micro- expression of robot identification face | |
| CN108596087B (en) | Driving fatigue degree detection regression model based on double-network result | |
| CN110334600A (en) | A kind of multiple features fusion driver exception expression recognition method | |
| CN104809445A (en) | Fatigue driving detection method based on eye and mouth states | |
| CN108053615A (en) | Driver tired driving condition detection method based on micro- expression | |
| CN105224285A (en) | Eyes open and-shut mode pick-up unit and method | |
| CN106919913A (en) | Method for detecting fatigue driving and device based on computer vision | |
| CN105117681A (en) | Multi-characteristic fatigue real-time detection method based on Android | |
| CN107563346A (en) | One kind realizes that driver fatigue sentences method for distinguishing based on eye image processing | |
| CN103617421A (en) | Fatigue detecting method and system based on comprehensive video feature analysis | |
| CN105373767A (en) | Eye fatigue detection method for smart phones | |
| Chen | Research on driver fatigue detection strategy based on human eye state | |
| CN106548132A (en) | The method for detecting fatigue driving of fusion eye state and heart rate detection | |
| US20230237694A1 (en) | Method and system for detecting children's sitting posture based on face recognition of children | |
| CN108108651B (en) | Method and system for detecting driver non-attentive driving based on video face analysis | |
| CN110097012B (en) | Fatigue detection method for monitoring eye movement parameters based on N-range image processing algorithm | |
| CN110059599A (en) | Driving fatigue method for early warning | |
| CN107315997B (en) | Sight orientation judgment method and system based on rapid feature point positioning | |
| CN109907756A (en) | Driving Fatigue Monitoring System based on head pose information and eye information | |
| CN111104817A (en) | Fatigue detection method based on deep learning | |
| Tabrizi et al. | Drowsiness detection based on brightness and numeral features of eye image | |
| CN105894732A (en) | Fatigue driving monitoring system |
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 |
Application publication date: 20190726 |
|
| RJ01 | Rejection of invention patent application after publication |