CN106096575A - A kind of driving states monitoring method and system - Google Patents
A kind of driving states monitoring method and system Download PDFInfo
- Publication number
- CN106096575A CN106096575A CN201610473427.2A CN201610473427A CN106096575A CN 106096575 A CN106096575 A CN 106096575A CN 201610473427 A CN201610473427 A CN 201610473427A CN 106096575 A CN106096575 A CN 106096575A
- Authority
- CN
- China
- Prior art keywords
- information
- driver
- image
- eyelid
- face
- 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
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/193—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/197—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The application provides a kind of driving states monitoring method and system, gathers the head image information of driver;Extract the eyelid opening information in described head image information;Whether the similarity of the eyelid feature judging described eyelid opening information and prestore is less than predetermined threshold value, and when described similarity is less than described predetermined threshold value, warns described driver.Visible, the application is by the eyelid opening information in the head image information of extraction driver, when the similarity of eyelid opening information with the eyelid prestored feature is less than predetermined threshold value, driver can be warned, such that it is able to remind safe driving when driver is tired or uninteresting, improve the safety of the dangerous materials carrier vehicles such as oil truck, reduce the accident rate in transportation.
Description
Technical field
The application relates to monitoring technical field, particularly relates to a kind of driving states monitoring method and system.
Background technology
Oil product transports, and is in a requisite link, constantly transports cycle turnover at it in the productive life of the mankind
In promoted greatly human industry society development.
Oil truck transport belongs to hazardous materials transportation, and its safety needs the attention obtained especially.Oil truck driver needs
Can be on duty after strict training test passes, and in transportation, in addition it is also necessary to driving of taking care with caution.
But, due to the fatigue in driving procedure, the reason such as uninteresting, driver is difficult to make oneself moment be maintained at safety and drives
Sailing state, therefore the dangerous materials carrier vehicle accident rate in transportation such as oil truck is the highest.
Summary of the invention
In view of this, the embodiment of the present application provides a kind of driving states monitoring method and system, to improve the danger such as oil truck
The safety of danger product carrier vehicle, reduces the accident rate in transportation.
To achieve these goals, the technical scheme that the embodiment of the present application provides is as follows:
A kind of driving states monitoring method, including:
Gather the head image information of driver;
Extract the eyelid opening information in described head image information;
The similarity of the eyelid feature judging described eyelid opening information and prestore whether less than predetermined threshold value, and
When described similarity is less than described predetermined threshold value, described driver is warned.
Preferably, also include:
Identify the facial characteristics in described head image information;
Judge described facial characteristics whether with the driver's characteristic matching prestored, and at described facial characteristics with in advance
When driver's feature of storage is not mated, described driver is warned.
Preferably, also include:
Range information between collection vehicle and Lane Mark;
Judge whether the rate of change of described range information deviates default safety range with the ratio of the speed of described vehicle,
And when the described safety range that the deviation of described ratio is preset, described driver is warned.
Preferably, also include:
Store described eyelid opening information and described range information, and store the rate of change of described range information and described car
The ratio of speed.
Preferably, also include:
Described eyelid opening information, described range information and the described ratio of storage is inquired about and/or revised.
A kind of driving states monitoring system, including:
First image capture module, image recognizer, image processor and telltale;
Described first image capture module is connected with described image recognizer, for gathering the head image information of driver,
And described head image information is sent to described image recognizer;
Described image recognizer is connected with described image processor, for extracting the eyelid aperture in described head image information
Information, and described eyelid opening information is sent to described image processor;
Described telltale is connected with described image processor, for judging that described eyelid is opened at described image processor
When the similarity of degree information and the eyelid feature prestored is less than predetermined threshold value, described driver is warned.
Preferably, described image recognizer is additionally operable to identify the facial characteristics in described head image information, and by described face
Feature is sent to described image processor;
Described telltale is additionally operable to judge described facial characteristics and the driver prestored at described image processor
When feature is not mated, described driver is warned.
Preferably, also include:
Second image capture module;
Described second image capture module is connected with described image processor, for collection vehicle and Lane Mark it
Between range information, and described range information is sent to described image processor;
Described telltale is additionally operable to judge the rate of change of described range information and described vehicle at described image processor
Speed ratio deviation preset safety range time, described driver is warned.
Preferably, also include:
Server;
Described server is connected with described image processor, for storing the described eyelid that described image processor receives
Opening information and described range information, and store the ratio of the rate of change of described range information and the speed of described vehicle.
Preferably, also include:
Management terminal;
Described management terminal is connected with described server, for the described eyelid aperture letter storing described server
Breath, described range information and described ratio are inquired about and/or are revised.
The technical scheme provided from above the embodiment of the present application, relative to prior art, the application has to be had as follows
Benefit effect:
The driving states monitoring method of application the application offer and system, gather the head image information of driver;Extract described
Eyelid opening information in head image information;Whether the similarity of the eyelid feature judging described eyelid opening information and prestore
Less than predetermined threshold value, and when described similarity is less than described predetermined threshold value, described driver is warned.Visible, this Shen
Please by the eyelid opening information in the head image information of extraction driver, can be at eyelid opening information and the eyelid prestored
When the similarity of feature is less than predetermined threshold value, driver is warned, such that it is able to remind when driver is tired or uninteresting
Safe driving, improves the safety of the dangerous materials carrier vehicles such as oil truck, reduces the accident rate in transportation.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present application or technical scheme of the prior art, below will be to embodiment or existing
In having technology to describe, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is only this
Some embodiments described in application, for those of ordinary skill in the art, on the premise of not paying creative work,
Other accompanying drawing can also be obtained according to these accompanying drawings.
The flow chart of the driving states monitoring method that Fig. 1 provides for one embodiment of the application;
The flow chart of the driving states monitoring method that Fig. 2 provides for another embodiment of the application;
The structure chart of the driving states monitoring system that Fig. 3 provides for one embodiment of the application;
The structure chart of the driving states monitoring system that Fig. 4 provides for another embodiment of the application.
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.
The flow chart of the driving states monitoring method that Fig. 1 provides for one embodiment of the application.
Shown in reference Fig. 1, a kind of driving states monitoring method that the application provides, including:
S101: gather the head image information of driver;
In the embodiment of the present application, in driving procedure, photographic head Real-time Collection can be used for showing driver's
The head image information of face state, and the head image information of collection is transmitted by 4G network in real time.
Here 4G refers to forth generation mobile communication technology, and this technology can quickly transmit high-quality audio frequency, video
With data such as images.4G can download with the speed of more than 100Mbps, fast 25 times current of domestic broadband A/D SL (4,000,000) of ratio, and
Disclosure satisfy that nearly all user requirement for wireless service.Additionally, 4G can not have at DSL and Cable Modem
Covered local deployment, expands to whole distract the most again, has incomparable superiority.
S102: extract the eyelid opening information in described head image information;
In the embodiment of the present application, after collecting the head image information of driver, it is possible to use existing recognition of face skill
Art extracts the eyelid opening information in head image information.
Recognition of face refers to utilize com-parison and analysis face visual signature information, and facial feature information based on people carries out identity
A kind of biological identification technology identified, contains image or the video flowing of face with video camera or camera collection, and automatically at figure
Detect and track face in Xiang, and then the face detected is carried out a series of correlation techniques of face feature identification, generally also
It is called Identification of Images, facial recognition.Belonging to the computer technology research field that comparison is popular at present, it is applied and also gets in life
Come the most extensive, solve a case including digital camera face auto-focusing, the fast gate technique of smiling face, police criminal detection, gate control system, shoot and monitor
The aspect such as system and identity identification.
In the embodiment of the present application, the Facial Feature Extraction Technology in face recognition technology can be used to extract head image information
In eyelid opening information.Face characteristic extracts, and also referred to as face characterizes, and it is the process that face carries out feature modeling.Face
Feature extraction is aiming at what some feature of face was carried out, and it is special that spendable feature is generally divided into visual signature, pixels statistics
Levy, facial image conversion coefficient feature, facial image algebraic characteristic etc..The method that face characteristic extracts be summed up be divided into two big
Class: one is Knowledge based engineering characterizing method;Another is characterizing method based on algebraic characteristic.
Knowledge based engineering characterizing method is mainly according to the shape description of human face and the range performance between them
Obtaining the characteristic contributing to face classification, its characteristic component generally includes the Euclidean distance between characteristic point, curvature and angle
Degree etc..Face is made up of the local such as eyes, nose, mouth, chin, to these local and between them the geometry of structural relation retouch
State, can be as the key character of identification face, these features are referred to as geometric properties.Knowledge based engineering face characterizes and mainly includes
Method based on geometric properties and template matching method.
Due to the complexity of facial image, the description shown by face characteristic there be difficulties involved when, the most in recent years, and base
Characterizing method in algebraic characteristic increasingly comes into one's own.The method uses algebraic characteristic characterization vector face.Algebraic characteristic is
First proposed by Hong etc., mainly utilize the intensity profile of image, by gradation of image is carried out various algebraic transformation and square
Battle array decomposition realizes.The advantage of the method is, the original gradation data of image can be used directly to training and identify: can be by low
Dimension space represents the data of image, is effectively compressed image;Identify get up than additive method simple effectively.The most common is several
Method has: PCA (PCA), Fisher face (LDA), independent component analysis method (JCA), and hidden Ma Erke
Husband's method (HMM) etc..
S103: whether judge described eyelid opening information with the similarity of the eyelid feature prestored less than presetting threshold
Value, and when described similarity is less than described predetermined threshold value, described driver is warned.
In the embodiment of the present application, corresponding head image data collecting work can be carried out, in advance every driver is pre-job
First store the head image information of each driver and the information of vehicles of correspondence, then the face in head image information is carried out feature and carry
Take and feature analysis (one of principal character is eyelid feature, for characterizing the state that eyelid is opened) set up a data base,
Prestore the facial characteristics especially eyelid feature of each driver, and by gathering the head portrait of driver in driving procedure
Information, extracts the eyelid opening information in head image information, and relatively described eyelid opening information and the eyelid feature prestored
Similarity, when similarity is less than predetermined threshold value, show that the eyelid aperture of driver is inadequate, be likely to be at tired or uninteresting tired
In the weary stage, now can trigger that driver is warned by telltale such as alarm buzzer etc. etc. and intervene and remind.
It is understood that in order to realize special messenger's special train, it is to avoid people's car does not mates, and is collecting the head image information of driver
After, it is also possible to the facial characteristics in head image information described in Direct Recognition, and judge described facial characteristics whether with prestore
Driver's characteristic matching, when described facial characteristics does not mates with the driver's feature prestored, is carried out described driver
Warn.
When whether judging described facial characteristics with the driver's characteristic matching prestored, existing face can be used
Coupling and the technology of identification, the facial feature data of the facial image of extraction is carried out with driver's feature templates of storage in data base
Search coupling, by setting a threshold value, when similarity exceedes this threshold value, then matches, when similarity is inadequate both explanation
Time, then do not mate both explanation.Recognition of face is exactly to be carried out with the facial characteristics template obtained by facial characteristics to be identified
Relatively, according to similarity degree, the identity information of face is judged.This process is divided into again two classes: a class is to confirm, is one
Carry out the process that image compares to one, another kind of is identification, is the one-to-many process that carries out images match contrast.
The driving states monitoring method that application the embodiment of the present application provides, gathers the head image information of driver;Extract described
Eyelid opening information in head image information;Whether the similarity of the eyelid feature judging described eyelid opening information and prestore
Less than predetermined threshold value, and when described similarity is less than described predetermined threshold value, described driver is warned.Visible, this Shen
Please embodiment by extract driver head image information in eyelid opening information, can eyelid opening information with prestore
The similarity of eyelid feature less than predetermined threshold value time driver is warned, such that it is able to tired or uninteresting driver
Time remind safe driving, improve the safety of the dangerous materials carrier vehicles such as oil truck, reduce the accident rate in transportation.
The flow chart of the driving states monitoring method that Fig. 2 provides for another embodiment of the application.
Shown in reference Fig. 2, a kind of driving states monitoring method that the application provides, including:
S201: gather the head image information of driver;
In the embodiment of the present application, in driving procedure, photographic head Real-time Collection can be used for showing driver's
The head image information of face state, and the head image information of collection is transmitted by 4G network in real time.
Here 4G refers to forth generation mobile communication technology, and this technology can quickly transmit high-quality audio frequency, video
With data such as images.4G can download with the speed of more than 100Mbps, fast 25 times current of domestic broadband A/D SL (4,000,000) of ratio, and
Disclosure satisfy that nearly all user requirement for wireless service.Additionally, 4G can not have at DSL and Cable Modem
Covered local deployment, expands to whole distract the most again, has incomparable superiority.
S202: extract the eyelid opening information in described head image information;
In the embodiment of the present application, after collecting the head image information of driver, it is possible to use existing recognition of face skill
Art extracts the eyelid opening information in head image information.
Recognition of face refers to utilize com-parison and analysis face visual signature information, and facial feature information based on people carries out identity
A kind of biological identification technology identified, contains image or the video flowing of face with video camera or camera collection, and automatically at figure
Detect and track face in Xiang, and then the face detected is carried out a series of correlation techniques of face feature identification, generally also
It is called Identification of Images, facial recognition.Belonging to the computer technology research field that comparison is popular at present, it is applied and also gets in life
Come the most extensive, solve a case including digital camera face auto-focusing, the fast gate technique of smiling face, police criminal detection, gate control system, shoot and monitor
The aspect such as system and identity identification.
In the embodiment of the present application, the Facial Feature Extraction Technology in face recognition technology can be used to extract head image information
In eyelid opening information.Face characteristic extracts, and also referred to as face characterizes, and it is the process that face carries out feature modeling.Face
Feature extraction is aiming at what some feature of face was carried out, and it is special that spendable feature is generally divided into visual signature, pixels statistics
Levy, facial image conversion coefficient feature, facial image algebraic characteristic etc..The method that face characteristic extracts be summed up be divided into two big
Class: one is Knowledge based engineering characterizing method;Another is characterizing method based on algebraic characteristic.
Knowledge based engineering characterizing method is mainly according to the shape description of human face and the range performance between them
Obtaining the characteristic contributing to face classification, its characteristic component generally includes the Euclidean distance between characteristic point, curvature and angle
Degree etc..Face is made up of the local such as eyes, nose, mouth, chin, to these local and between them the geometry of structural relation retouch
State, can be as the key character of identification face, these features are referred to as geometric properties.Knowledge based engineering face characterizes and mainly includes
Method based on geometric properties and template matching method.
Due to the complexity of facial image, the description shown by face characteristic there be difficulties involved when, the most in recent years, and base
Characterizing method in algebraic characteristic increasingly comes into one's own.The method uses algebraic characteristic characterization vector face.Algebraic characteristic is
First proposed by Hong etc., mainly utilize the intensity profile of image, by gradation of image is carried out various algebraic transformation and square
Battle array decomposition realizes.The advantage of the method is, the original gradation data of image can be used directly to training and identify: can be by low
Dimension space represents the data of image, is effectively compressed image;Identify get up than additive method simple effectively.The most common is several
Method has: PCA (PCA), Fisher face (LDA), independent component analysis method (JCA), and hidden Ma Erke
Husband's method (HMM) etc..
S203: whether judge described eyelid opening information with the similarity of the eyelid feature prestored less than presetting threshold
Value, and when described similarity is less than described predetermined threshold value, described driver is warned.
In the embodiment of the present application, corresponding head image data collecting work can be carried out, in advance every driver is pre-job
First store the head image information of each driver and the information of vehicles of correspondence, then the face in head image information is carried out feature and carry
Take and feature analysis (one of principal character is eyelid feature, for characterizing the state that eyelid is opened) set up a data base,
Prestore the facial characteristics especially eyelid feature of each driver, and by gathering the head portrait of driver in driving procedure
Information, extracts the eyelid opening information in head image information, and relatively described eyelid opening information and the eyelid feature prestored
Similarity, when similarity is less than predetermined threshold value, show that the eyelid aperture of driver is inadequate, be likely to be at tired or uninteresting tired
In the weary stage, now can trigger that driver is warned by telltale such as alarm buzzer etc. etc. and intervene and remind.
It is understood that in order to realize special messenger's special train, it is to avoid people's car does not mates, and is collecting the head image information of driver
After, it is also possible to the facial characteristics in head image information described in Direct Recognition, and judge described facial characteristics whether with prestore
Driver's characteristic matching, when described facial characteristics does not mates with the driver's feature prestored, is carried out described driver
Warn.
When whether judging described facial characteristics with the driver's characteristic matching prestored, existing face can be used
Coupling and the technology of identification, the facial feature data of the facial image of extraction is carried out with driver's feature templates of storage in data base
Search coupling, by setting a threshold value, when similarity exceedes this threshold value, then matches, when similarity is inadequate both explanation
Time, then do not mate both explanation.Recognition of face is exactly to be carried out with the facial characteristics template obtained by facial characteristics to be identified
Relatively, according to similarity degree, the identity information of face is judged.This process is divided into again two classes: a class is to confirm, is one
Carry out the process that image compares to one, another kind of is identification, is the one-to-many process that carries out images match contrast.
S204: the range information between collection vehicle and Lane Mark;
In the embodiment of the present application, deviation sensor ratio such as infrared camera can be used (to be generally mounted to vehicle body
Side or position of rear view mirror) range information between Real-time Collection vehicle and Lane Mark is after collecting range information, logical
Cross existing image processing techniques and can obtain automobile location parameter in current lane.
S205: judge whether the rate of change of described range information deviates default safety with the ratio of the speed of described vehicle
Scope, and when the described safety range that the deviation of described ratio is preset, described driver is warned.
In the embodiment of the present application, when detecting that vehicle runs during the range information of distance Lane Mark, Ji Kegen
Go out the rate of change of vehicle and the range information of Lane Mark according to Time Calculation, this rate of change can be built in conjunction with the speed of vehicle
Vertical corresponding linear relationship, when the safe model that the rate of change of described range information is preset with the ratio deviation of the speed of described vehicle
When enclosing, show that vehicle is not on safe driving state or has emergency situations, now can trigger telltale and such as report to the police buzzing
Driver is warned etc. to intervene and reminds by devices etc., is beneficial to safe driving.
Further, the embodiment of the present application can also store described eyelid opening information and described range information, and stores
The ratio of the speed of the rate of change of described range information and described vehicle, then can to the described eyelid opening information of storage,
Described range information and described ratio are inquired about, and at described eyelid opening information, described range information and described ratio
Differ serious with general knowledge, hence it is evident that when not meeting normal condition, it is also possible to do not meet normal condition described eyelid opening information,
Described range information and described ratio are modified.
The embodiment of the present application can utilize sensor and face recognition technology, in real time monitoring driver and the reality of vehicle
Transport condition, it is possible to the various information gathered are transferred to outside and store, in case the later stage calls use.Manager is permissible
By managing the detailed driving condition information of terminal inquiry driver, it is possible to the driving condition information to obvious mismatch state
(comprise personnel do not mate, human eye aperture less than threshold value, between vehicle to Lane Mark, range rate becomes under corresponding speed
Rate misfits safety range) it is modified, with more preferable specification safety, improve efficiency.
Can show, in management terminal, the form handled well, manager can be to differing serious driving in form with general knowledge
Status information artificially revises that (daily artificial expert judgments belongs to abnormal driving state, and such as speed, acceleration, human eye are opened
Conjunction degree, automotive run-off-road tag line distance, vehicle be the speed of automotive run-off-road tag line during corresponding speed of operation
Rate etc.), and again store.
The present invention carries out recognition of face to driver in the road driving cycle, it is achieved the monitoring to driving states, and can
To realize being automatically reminded to evade to the improper driving condition of driver, it is also possible to the various information that storage gathers, in case the later stage
Inquire about or provide specific aim data for safety training, improving the work of safe driving further, there is important reality meaning
Justice.
The structure chart of the driving states monitoring system that Fig. 3 provides for one embodiment of the application.
With reference to shown in Fig. 3, a kind of driving states that the application provides monitors system, including:
First image capture module 1, image recognizer 2, image processor 3 and telltale 4;
Described first image capture module 1 is connected with described image recognizer 2, for gathering the head portrait letter of driver
Breath, and described head image information is sent to described image recognizer 2;
In the embodiment of the present application, the first image capture module 1 can be photographic head, in driving procedure, can use
Photographic head Real-time Collection is for showing the head image information of the facial state of driver, and the head image information of collection is passed through 4G in real time
Network is transmitted.
Here 4G refers to forth generation mobile communication technology, and this technology can quickly transmit high-quality audio frequency, video
With data such as images.4G can download with the speed of more than 100Mbps, fast 25 times current of domestic broadband A/D SL (4,000,000) of ratio, and
Disclosure satisfy that nearly all user requirement for wireless service.Additionally, 4G can not have at DSL and Cable Modem
Covered local deployment, expands to whole distract the most again, has incomparable superiority.
Described image recognizer 2 is connected with described image processor 3, opens for the eyelid extracted in described head image information
Degree information, and described eyelid opening information is sent to described image processor 3;
In the embodiment of the present application, image recognizer 2 can use existing image recognition apparatus, is collecting driver
Head image information after, image recognizer 2 can utilize existing face recognition technology to extract the eyelid aperture letter in head image information
Breath.
Recognition of face refers to utilize com-parison and analysis face visual signature information, and facial feature information based on people carries out identity
A kind of biological identification technology identified, contains image or the video flowing of face with video camera or camera collection, and automatically at figure
Detect and track face in Xiang, and then the face detected is carried out a series of correlation techniques of face feature identification, generally also
It is called Identification of Images, facial recognition.Belonging to the computer technology research field that comparison is popular at present, it is applied and also gets in life
Come the most extensive, solve a case including digital camera face auto-focusing, the fast gate technique of smiling face, police criminal detection, gate control system, shoot and monitor
The aspect such as system and identity identification.
In the embodiment of the present application, the Facial Feature Extraction Technology in face recognition technology can be used to extract head image information
In eyelid opening information.Face characteristic extracts, and also referred to as face characterizes, and it is the process that face carries out feature modeling.Face
Feature extraction is aiming at what some feature of face was carried out, and it is special that spendable feature is generally divided into visual signature, pixels statistics
Levy, facial image conversion coefficient feature, facial image algebraic characteristic etc..The method that face characteristic extracts be summed up be divided into two big
Class: one is Knowledge based engineering characterizing method;Another is characterizing method based on algebraic characteristic.
Knowledge based engineering characterizing method is mainly according to the shape description of human face and the range performance between them
Obtaining the characteristic contributing to face classification, its characteristic component generally includes the Euclidean distance between characteristic point, curvature and angle
Degree etc..Face is made up of the local such as eyes, nose, mouth, chin, to these local and between them the geometry of structural relation retouch
State, can be as the key character of identification face, these features are referred to as geometric properties.Knowledge based engineering face characterizes and mainly includes
Method based on geometric properties and template matching method.
Due to the complexity of facial image, the description shown by face characteristic there be difficulties involved when, the most in recent years, and base
Characterizing method in algebraic characteristic increasingly comes into one's own.The method uses algebraic characteristic characterization vector face.Algebraic characteristic is
First proposed by Hong etc., mainly utilize the intensity profile of image, by gradation of image is carried out various algebraic transformation and square
Battle array decomposition realizes.The advantage of the method is, the original gradation data of image can be used directly to training and identify: can be by low
Dimension space represents the data of image, is effectively compressed image;Identify get up than additive method simple effectively.The most common is several
Method has: PCA (PCA), Fisher face (LDA), independent component analysis method (JCA), and hidden Ma Erke
Husband's method (HMM) etc..
Described telltale 4 is connected with described image processor 3, for judging described eye at described image processor 3
When the similarity of skin opening information and the eyelid feature prestored is less than predetermined threshold value, described driver is warned.
In the embodiment of the present application, corresponding head image data collecting work can be carried out, in advance every driver is pre-job
First store the head image information of each driver and the information of vehicles of correspondence, then the face in head image information is carried out feature and carry
Take and feature analysis (one of principal character is eyelid feature, for characterizing the state that eyelid is opened) set up a data base,
Prestore the facial characteristics especially eyelid feature of each driver, and by gathering the head portrait of driver in driving procedure
Information, extracts the eyelid opening information in head image information, and by image processor 3 relatively described eyelid opening information with in advance
The similarity of the eyelid feature of storage, when similarity is less than predetermined threshold value, shows that the eyelid aperture of driver is inadequate, at possibility
In the tired or uninteresting tired stage, the intervention such as now can trigger that driver is warned by telltale 4 such as alarm buzzer etc.
Remind.
Preferably, described image recognizer 2 is additionally operable to identify the facial characteristics in described head image information, and by described face
Feature is sent to described image processor 3;
Described telltale 4 is additionally operable to judge described facial characteristics and the driving prestored at described image processor 3
When person's feature is not mated, described driver is warned.
It is understood that in order to realize special messenger's special train, it is to avoid people's car does not mates, and is collecting the head image information of driver
After, it is also possible to the facial characteristics in head image information described in Direct Recognition, and judge that described facial characteristics is by image processor 3
Driver's characteristic matching that is no and that prestore is when described facial characteristics does not mates with the driver's feature prestored, right
Described driver warns.
When whether judging described facial characteristics with the driver's characteristic matching prestored, image processor 3 can be adopted
With existing face coupling and the technology of identification, the facial feature data of the facial image of extraction and the driver of storage in data base
Feature templates scans for coupling, by setting a threshold value, when similarity exceedes this threshold value, then matches both explanation,
When similarity is inadequate, then do not mate both explanation.Recognition of face is exactly by facial characteristics to be identified and the face obtained
Feature templates compares, and judges the identity information of face according to similarity degree.This process is divided into again two classes: a class
Being to confirm, be the process that image compares that carries out one to one, another kind of is identification, is the one-to-many mistake that carries out images match contrast
Journey.
In the embodiment of the present application, image processor 3 can use existing processor to realize, as long as can realize described
The comparison of eyelid opening information and the similarity of the eyelid feature prestored, and to described facial characteristics whether with deposit in advance
The judgement of driver's characteristic matching of storage.
The driving states monitoring system that application the embodiment of the present application provides, gathers the head image information of driver;Extract described
Eyelid opening information in head image information;Whether the similarity of the eyelid feature judging described eyelid opening information and prestore
Less than predetermined threshold value, and when described similarity is less than described predetermined threshold value, described driver is warned.Visible, this Shen
Please embodiment by extract driver head image information in eyelid opening information, can eyelid opening information with prestore
The similarity of eyelid feature less than predetermined threshold value time driver is warned, such that it is able to tired or uninteresting driver
Time remind safe driving, improve the safety of the dangerous materials carrier vehicles such as oil truck, reduce the accident rate in transportation.
The driving states monitoring system that the embodiment of the present application provides, can use the driving states in said method embodiment
Monitoring method, the step that concrete function is referred in any of the above-described embodiment of the method describes, and here is omitted.
The structure chart of the driving states monitoring system that Fig. 4 provides for another embodiment of the application.
With reference to shown in Fig. 4, a kind of driving states that the application provides monitors system, including:
First image capture module 1, image recognizer 2, image processor 3, telltale 4 and the second image capture module 5;
Described first image capture module 1 is connected with described image recognizer 2, for gathering the head portrait letter of driver
Breath, and described head image information is sent to described image recognizer 2;
In the embodiment of the present application, the first image capture module 1 can be photographic head, in driving procedure, can use
Photographic head Real-time Collection is for showing the head image information of the facial state of driver, and the head image information of collection is passed through 4G in real time
Network is transmitted.
Here 4G refers to forth generation mobile communication technology, and this technology can quickly transmit high-quality audio frequency, video
With data such as images.4G can download with the speed of more than 100Mbps, fast 25 times current of domestic broadband A/D SL (4,000,000) of ratio, and
Disclosure satisfy that nearly all user requirement for wireless service.Additionally, 4G can not have at DSL and Cable Modem
Covered local deployment, expands to whole distract the most again, has incomparable superiority.
Described image recognizer 2 is connected with described image processor 3, opens for the eyelid extracted in described head image information
Degree information, and described eyelid opening information is sent to described image processor 3;
In the embodiment of the present application, image recognizer 2 can use existing image recognition apparatus, is collecting driver
Head image information after, image recognizer 2 can utilize existing face recognition technology to extract the eyelid aperture letter in head image information
Breath.
Recognition of face refers to utilize com-parison and analysis face visual signature information, and facial feature information based on people carries out identity
A kind of biological identification technology identified, contains image or the video flowing of face with video camera or camera collection, and automatically at figure
Detect and track face in Xiang, and then the face detected is carried out a series of correlation techniques of face feature identification, generally also
It is called Identification of Images, facial recognition.Belonging to the computer technology research field that comparison is popular at present, it is applied and also gets in life
Come the most extensive, solve a case including digital camera face auto-focusing, the fast gate technique of smiling face, police criminal detection, gate control system, shoot and monitor
The aspect such as system and identity identification.
In the embodiment of the present application, the Facial Feature Extraction Technology in face recognition technology can be used to extract head image information
In eyelid opening information.Face characteristic extracts, and also referred to as face characterizes, and it is the process that face carries out feature modeling.Face
Feature extraction is aiming at what some feature of face was carried out, and it is special that spendable feature is generally divided into visual signature, pixels statistics
Levy, facial image conversion coefficient feature, facial image algebraic characteristic etc..The method that face characteristic extracts be summed up be divided into two big
Class: one is Knowledge based engineering characterizing method;Another is characterizing method based on algebraic characteristic.
Knowledge based engineering characterizing method is mainly according to the shape description of human face and the range performance between them
Obtaining the characteristic contributing to face classification, its characteristic component generally includes the Euclidean distance between characteristic point, curvature and angle
Degree etc..Face is made up of the local such as eyes, nose, mouth, chin, to these local and between them the geometry of structural relation retouch
State, can be as the key character of identification face, these features are referred to as geometric properties.Knowledge based engineering face characterizes and mainly includes
Method based on geometric properties and template matching method.
Due to the complexity of facial image, the description shown by face characteristic there be difficulties involved when, the most in recent years, and base
Characterizing method in algebraic characteristic increasingly comes into one's own.The method uses algebraic characteristic characterization vector face.Algebraic characteristic is
First proposed by Hong etc., mainly utilize the intensity profile of image, by gradation of image is carried out various algebraic transformation and square
Battle array decomposition realizes.The advantage of the method is, the original gradation data of image can be used directly to training and identify: can be by low
Dimension space represents the data of image, is effectively compressed image;Identify get up than additive method simple effectively.The most common is several
Method has: PCA (PCA), Fisher face (LDA), independent component analysis method (JCA), and hidden Ma Erke
Husband's method (HMM) etc..
Described telltale 4 is connected with described image processor 3, for judging described eye at described image processor 3
When the similarity of skin opening information and the eyelid feature prestored is less than predetermined threshold value, described driver is warned.
In the embodiment of the present application, corresponding head image data collecting work can be carried out, in advance every driver is pre-job
First store the head image information of each driver and the information of vehicles of correspondence, then the face in head image information is carried out feature and carry
Take and feature analysis (one of principal character is eyelid feature, for characterizing the state that eyelid is opened) set up a data base,
Prestore the facial characteristics especially eyelid feature of each driver, and by gathering the head portrait of driver in driving procedure
Information, extracts the eyelid opening information in head image information, and by image processor 3 relatively described eyelid opening information with in advance
The similarity of the eyelid feature of storage, when similarity is less than predetermined threshold value, shows that the eyelid aperture of driver is inadequate, at possibility
In the tired or uninteresting tired stage, the intervention such as now can trigger that driver is warned by telltale 4 such as alarm buzzer etc.
Remind.
Preferably, described image recognizer 2 is additionally operable to identify the facial characteristics in described head image information, and by described face
Feature is sent to described image processor 3;
Described telltale 4 is additionally operable to judge described facial characteristics and the driving prestored at described image processor 3
When person's feature is not mated, described driver is warned.
It is understood that in order to realize special messenger's special train, it is to avoid people's car does not mates, and is collecting the head image information of driver
After, it is also possible to the facial characteristics in head image information described in Direct Recognition, and judge that described facial characteristics is by image processor 3
Driver's characteristic matching that is no and that prestore is when described facial characteristics does not mates with the driver's feature prestored, right
Described driver warns.
When whether judging described facial characteristics with the driver's characteristic matching prestored, image processor 3 can be adopted
With existing face coupling and the technology of identification, the facial feature data of the facial image of extraction and the driver of storage in data base
Feature templates scans for coupling, by setting a threshold value, when similarity exceedes this threshold value, then matches both explanation,
When similarity is inadequate, then do not mate both explanation.Recognition of face is exactly by facial characteristics to be identified and the face obtained
Feature templates compares, and judges the identity information of face according to similarity degree.This process is divided into again two classes: a class
Being to confirm, be the process that image compares that carries out one to one, another kind of is identification, is the one-to-many mistake that carries out images match contrast
Journey.
In the embodiment of the present application, image processor 3 can use existing processor to realize, as long as can realize described
The comparison of eyelid opening information and the similarity of the eyelid feature prestored, and to described facial characteristics whether with deposit in advance
The judgement of driver's characteristic matching of storage.
Described second image capture module 5 is connected with described image processor 3, for collection vehicle and Lane Mark
Between range information, and described range information is sent to described image processor 3;
In the embodiment of the present application, the second image capture module 5 can use the such as infrared photography of deviation sensor ratio
Head (being generally mounted to vehicle body side or position of rear view mirror), the range information between Real-time Collection vehicle and Lane Mark,
After collecting range information, automobile location parameter in current lane can be obtained by existing image processing techniques.
Described telltale 4 is additionally operable to judge the rate of change of described range information and described car at described image processor 3
Speed ratio deviation preset safety range time, described driver is warned.
In the embodiment of the present application, when detecting that vehicle runs during the range information of distance Lane Mark, Ji Kegen
Go out the rate of change of vehicle and the range information of Lane Mark according to Time Calculation, this rate of change can be built in conjunction with the speed of vehicle
Vertical corresponding linear relationship, when the safe model that the rate of change of described range information is preset with the ratio deviation of the speed of described vehicle
When enclosing, show that vehicle is not on safe driving state or has emergency situations, now can trigger telltale and such as report to the police buzzing
Driver is warned etc. to intervene and reminds by devices etc., is beneficial to safe driving.
Preferably, it is also possible to including:
Server (not shown in Fig. 4);
Described server is connected with described image processor, for storing the described eyelid that described image processor receives
Opening information and described range information, and store the ratio of the rate of change of described range information and the speed of described vehicle.
Preferably, it is also possible to including:
Management terminal (not shown in Fig. 4);
Described management terminal is connected with described server, for the described eyelid aperture letter storing described server
Breath, described range information and described ratio are inquired about and/or are revised.
Further, the embodiment of the present application can also store described eyelid opening information and described distance letter by server
Breath, and store the ratio of the rate of change of described range information and the speed of described vehicle, may then pass through management terminal to depositing
Described eyelid opening information, described range information and the described ratio of storage are inquired about, and in described eyelid opening information, institute
State range information and described ratio and differ serious with general knowledge, hence it is evident that when not meeting normal condition, it is also possible to not meeting normal shape
The described eyelid opening information of condition, described range information and described ratio are modified.
The embodiment of the present application can utilize sensor and face recognition technology, in real time monitoring driver and the reality of vehicle
Transport condition, it is possible to the various information gathered are transferred to outside and store, in case the later stage calls use.Manager is permissible
By managing the detailed driving condition information of terminal inquiry driver, it is possible to the driving condition information to obvious mismatch state
(comprise personnel do not mate, human eye aperture less than threshold value, between vehicle to Lane Mark, range rate becomes under corresponding speed
Rate misfits safety range) it is modified, with more preferable specification safety, improve efficiency.
Can show, in management terminal, the form handled well, manager can be to differing serious driving in form with general knowledge
Status information artificially revises that (daily artificial expert judgments belongs to abnormal driving state, and such as speed, acceleration, human eye are opened
Conjunction degree, automotive run-off-road tag line distance, vehicle be the speed of automotive run-off-road tag line during corresponding speed of operation
Rate etc.), and again store.
The present invention carries out recognition of face to driver in the road driving cycle, it is achieved the monitoring to driving states, and can
To realize being automatically reminded to evade to the improper driving condition of driver, it is also possible to the various information that storage gathers, in case the later stage
Inquire about or provide specific aim data for safety training, improving the work of safe driving further, there is important reality meaning
Justice.
The driving states monitoring system that the embodiment of the present application provides, can use the driving states in said method embodiment
Monitoring method, the step that concrete function is referred in any of the above-described embodiment of the method describes, and here is omitted.
The technical scheme provided from above the embodiment of the present application, relative to prior art, the application has to be had as follows
Benefit effect:
The driving states monitoring method of application the application offer and system, gather the head image information of driver;Extract described
Eyelid opening information in head image information;Whether the similarity of the eyelid feature judging described eyelid opening information and prestore
Less than predetermined threshold value, and when described similarity is less than described predetermined threshold value, described driver is warned.Visible, this Shen
Please by the eyelid opening information in the head image information of extraction driver, can be at eyelid opening information and the eyelid prestored
When the similarity of feature is less than predetermined threshold value, driver is warned, such that it is able to remind when driver is tired or uninteresting
Safe driving, improves the safety of the dangerous materials carrier vehicles such as oil truck, reduces the accident rate in transportation.
For convenience of description, it is divided into various unit to be respectively described with function when describing apparatus above.Certainly, this is being implemented
The function of each unit can be realized in same or multiple softwares and/or hardware during application.
Each embodiment in this specification all uses the mode gone forward one by one to describe, identical similar portion between each embodiment
Dividing and see mutually, what each embodiment stressed is the difference with other embodiments.Especially for device or
For system embodiment, owing to it is substantially similar to embodiment of the method, so describing fairly simple, relevant part sees method
The part of embodiment illustrates.Apparatus and system embodiment described above is only schematically, wherein said conduct
The unit of separating component explanation can be or may not be physically separate, the parts shown as unit can be or
Person may not be physical location, i.e. may be located at a place, or can also be distributed on multiple NE.Can root
Factually border need select some or all of module therein to realize the purpose of the present embodiment scheme.Ordinary skill
Personnel, in the case of not paying creative work, are i.e. appreciated that and implement.
Professional further appreciates that, in conjunction with the unit of each example that the embodiments described herein describes
And algorithm steps, it is possible to electronic hardware, computer software or the two be implemented in combination in, in order to clearly demonstrate hardware and
The interchangeability of software, the most generally describes composition and the step of each example according to function.These
Function performs with hardware or software mode actually, depends on application-specific and the design constraint of technical scheme.Specialty
Technical staff specifically should can be used for using different methods to realize described function to each, but this realization should not
Think beyond the scope of this invention.
The method described in conjunction with the embodiments described herein or the step of algorithm can direct hardware, processor be held
The software module of row, or the combination of the two implements.Software module can be placed in random access memory (RAM), internal memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, depositor, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Described above to the disclosed embodiments, makes professional and technical personnel in the field be capable of or uses the present invention.
Multiple amendment to these embodiments will be apparent from for those skilled in the art, as defined herein
General Principle can realize without departing from the spirit or scope of the present invention in other embodiments.Therefore, the present invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and principles disclosed herein and features of novelty phase one
The widest scope caused.
Claims (10)
1. a driving states monitoring method, it is characterised in that including:
Gather the head image information of driver;
Extract the eyelid opening information in described head image information;
Whether the similarity of the eyelid feature judging described eyelid opening information and prestore is less than predetermined threshold value, and described
When similarity is less than described predetermined threshold value, described driver is warned.
Method the most according to claim 1, it is characterised in that also include:
Identify the facial characteristics in described head image information;
Judge described facial characteristics whether with the driver's characteristic matching prestored, and described facial characteristics with prestore
Driver's feature when not mating, described driver is warned.
Method the most according to claim 1, it is characterised in that also include:
Range information between collection vehicle and Lane Mark;
Judge whether the ratio of the rate of change of described range information and the speed of described vehicle deviates default safety range, and
During the described safety range that the deviation of described ratio is preset, described driver is warned.
Method the most according to claim 3, it is characterised in that also include:
Store described eyelid opening information and described range information, and store the rate of change of described range information and described vehicle
The ratio of speed.
Method the most according to claim 4, it is characterised in that also include:
Described eyelid opening information, described range information and the described ratio of storage is inquired about and/or revised.
6. a driving states monitoring system, it is characterised in that including:
First image capture module, image recognizer, image processor and telltale;
Described first image capture module is connected with described image recognizer, for gathering the head image information of driver, and will
Described head image information is sent to described image recognizer;
Described image recognizer is connected with described image processor, for extracting the eyelid aperture letter in described head image information
Breath, and described eyelid opening information is sent to described image processor;
Described telltale is connected with described image processor, for judging that described eyelid aperture is believed at described image processor
When the similarity of the eyelid feature ceased and prestore is less than predetermined threshold value, described driver is warned.
System the most according to claim 6, it is characterised in that:
Described image recognizer is additionally operable to identify the facial characteristics in described head image information, and described facial characteristics is sent to institute
State image processor;
Described telltale is additionally operable to judge described facial characteristics and the driver's feature prestored at described image processor
When not mating, described driver is warned.
System the most according to claim 6, it is characterised in that also include:
Second image capture module;
Described second image capture module is connected with described image processor, between collection vehicle and Lane Mark
Range information, and described range information is sent to described image processor;
Described telltale is additionally operable to the speed of rate of change and the described vehicle judging described range information at described image processor
During the safety range that the ratio deviation of degree is preset, described driver is warned.
System the most according to claim 8, it is characterised in that also include:
Server;
Described server is connected with described image processor, for storing the described eyelid aperture that described image processor receives
Information and described range information, and store the ratio of the rate of change of described range information and the speed of described vehicle.
System the most according to claim 9, it is characterised in that also include:
Management terminal;
Described management terminal is connected with described server, for the described eyelid opening information storing described server, institute
State range information and described ratio is inquired about and/or revised.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610473427.2A CN106096575A (en) | 2016-06-24 | 2016-06-24 | A kind of driving states monitoring method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610473427.2A CN106096575A (en) | 2016-06-24 | 2016-06-24 | A kind of driving states monitoring method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106096575A true CN106096575A (en) | 2016-11-09 |
Family
ID=57253479
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610473427.2A Pending CN106096575A (en) | 2016-06-24 | 2016-06-24 | A kind of driving states monitoring method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106096575A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109190515A (en) * | 2018-08-14 | 2019-01-11 | 深圳壹账通智能科技有限公司 | A kind of method for detecting fatigue driving, computer readable storage medium and terminal device |
CN109700472A (en) * | 2019-02-21 | 2019-05-03 | 北京七鑫易维信息技术有限公司 | A kind of fatigue detection method, device, equipment and storage medium |
CN110443119A (en) * | 2019-06-25 | 2019-11-12 | 中车工业研究院有限公司 | Cargo state recognition methods and device in compartment |
CN113830092A (en) * | 2021-01-25 | 2021-12-24 | 西安睿博智能股份有限公司 | Driving safety management method and device and computer readable storage medium |
CN114998979A (en) * | 2022-08-01 | 2022-09-02 | 中国通信建设第三工程局有限公司 | Intelligent Internet of vehicles system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202615569U (en) * | 2012-04-17 | 2012-12-19 | 大连民族学院 | Fatigue driving-based detection and prompting apparatus |
CN105151049A (en) * | 2015-08-27 | 2015-12-16 | 嘉兴艾特远信息技术有限公司 | Early warning system based on driver face features and lane departure detection |
CN105354987A (en) * | 2015-11-26 | 2016-02-24 | 南京工程学院 | Vehicle fatigue driving detection and identity authentication apparatus, and detection method thereof |
CN206039557U (en) * | 2016-06-24 | 2017-03-22 | 苏州大学 | Driving situation monitoring system |
-
2016
- 2016-06-24 CN CN201610473427.2A patent/CN106096575A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202615569U (en) * | 2012-04-17 | 2012-12-19 | 大连民族学院 | Fatigue driving-based detection and prompting apparatus |
CN105151049A (en) * | 2015-08-27 | 2015-12-16 | 嘉兴艾特远信息技术有限公司 | Early warning system based on driver face features and lane departure detection |
CN105354987A (en) * | 2015-11-26 | 2016-02-24 | 南京工程学院 | Vehicle fatigue driving detection and identity authentication apparatus, and detection method thereof |
CN206039557U (en) * | 2016-06-24 | 2017-03-22 | 苏州大学 | Driving situation monitoring system |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109190515A (en) * | 2018-08-14 | 2019-01-11 | 深圳壹账通智能科技有限公司 | A kind of method for detecting fatigue driving, computer readable storage medium and terminal device |
CN109700472A (en) * | 2019-02-21 | 2019-05-03 | 北京七鑫易维信息技术有限公司 | A kind of fatigue detection method, device, equipment and storage medium |
CN110443119A (en) * | 2019-06-25 | 2019-11-12 | 中车工业研究院有限公司 | Cargo state recognition methods and device in compartment |
CN113830092A (en) * | 2021-01-25 | 2021-12-24 | 西安睿博智能股份有限公司 | Driving safety management method and device and computer readable storage medium |
CN113830092B (en) * | 2021-01-25 | 2023-04-18 | 西安睿博智能股份有限公司 | Driving safety management method and device and computer readable storage medium |
CN114998979A (en) * | 2022-08-01 | 2022-09-02 | 中国通信建设第三工程局有限公司 | Intelligent Internet of vehicles system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108791299B (en) | Driving fatigue detection and early warning system and method based on vision | |
CN106096575A (en) | A kind of driving states monitoring method and system | |
CN106335432B (en) | Intelligent back vision mirror, control system and processing method with driving auxiliary system | |
CN104751600B (en) | Anti-fatigue-driving safety means and its application method based on iris recognition | |
CN103839379B (en) | Automobile and driver fatigue early warning detecting method and system for automobile | |
CN108053615B (en) | Method for detecting fatigue driving state of driver based on micro-expression | |
CN104637246B (en) | Driver multi-behavior early warning system and danger evaluation method | |
CN102263937B (en) | Driver's driving behavior monitoring device and monitoring method based on video detection | |
CN104238732B (en) | Device, method and computer readable recording medium for detecting facial movements to generate signals | |
TWI715958B (en) | Assessing method for a driver's fatigue score | |
CN104408878B (en) | Vehicle fleet fatigue driving early warning monitoring system and method | |
CN202130312U (en) | Driver fatigue driving monitoring device | |
CN202257856U (en) | Driver fatigue-driving monitoring device | |
WO2019127274A1 (en) | Alarm method and device for criminal activity, storage medium and server | |
CN103824420A (en) | Fatigue driving identification system based on heart rate variability non-contact measuring | |
CN109389806A (en) | Fatigue driving detection method for early warning, system and medium based on multi-information fusion | |
CN101587544A (en) | Automotive on-vehicle antitracking device based on computer vision | |
CN106295474B (en) | Fatigue detection method, system and the server of deck officer | |
CN109977771A (en) | Verification method, device, equipment and the computer readable storage medium of driver identification | |
CN109977930A (en) | Method for detecting fatigue driving and device | |
CN109543577A (en) | A kind of fatigue driving detection method for early warning based on facial expression feature | |
CN103198618A (en) | Mobile phone capable of preventing fatigue driving and warning method | |
CN206363345U (en) | A kind of vehicle-mounted vocal print and face recognition device | |
CN108133573A (en) | Drowsy driving warning system | |
CN206039557U (en) | Driving situation monitoring system |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161109 |