CN103473890B - Based on driver fatigue real-time monitoring system and the monitoring method of multi information - Google Patents

Based on driver fatigue real-time monitoring system and the monitoring method of multi information Download PDF

Info

Publication number
CN103473890B
CN103473890B CN201310415071.3A CN201310415071A CN103473890B CN 103473890 B CN103473890 B CN 103473890B CN 201310415071 A CN201310415071 A CN 201310415071A CN 103473890 B CN103473890 B CN 103473890B
Authority
CN
China
Prior art keywords
driver
moment
fatigue strength
fatigue
information
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.)
Expired - Fee Related
Application number
CN201310415071.3A
Other languages
Chinese (zh)
Other versions
CN103473890A (en
Inventor
黄英
白金蓬
郭小辉
袁海涛
刘彩霞
刘平
蔡文婷
吴思谕
李锐琦
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hefei University of Technology
Original Assignee
Hefei University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hefei University of Technology filed Critical Hefei University of Technology
Priority to CN201310415071.3A priority Critical patent/CN103473890B/en
Publication of CN103473890A publication Critical patent/CN103473890A/en
Application granted granted Critical
Publication of CN103473890B publication Critical patent/CN103473890B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

The invention discloses a kind of driver fatigue real-time monitoring system based on multi information and monitoring method, it is characterized in that: form monitoring system by information acquisition unit, information process unit and alarm unit; Information acquisition unit is provided with: pressure transducer is for extracting the grip information of driver to bearing circle; Angular transducer is for extracting the corner information of bearing circle; Range sensor is for extracting the head position information of driver; The information that information process unit is used for information acquisition unit obtains processes, and obtains the fatigue strength characteristic parameter characterizing driving condition, judges driver fatigue state grade with this; Alarm unit is used for carrying out alarm when information process unit judges that driver is in non-waking state.Reliability of the present invention is high, cost is low, real-time, monitoring effect is desirable, can avoid the traffic hazard because fatigue driving causes to a great extent.

Description

Based on driver fatigue real-time monitoring system and the monitoring method of multi information
Technical field
The invention belongs to intelligent transportation and security fields, be specifically related to the driver fatigue real-time monitoring system based on multi information and monitoring method.
Background technology
In recent years, road traffic accident sharply increased, and one of its major reason is exactly fatigue driving, for this reason, scientificlly and effectively monitor the driving condition of driver, and give driver's prompting and report to the police, become the study hotspot in driver's active safety monitoring field.
In current research, a lot of countermeasure is used to the monitoring carrying out fatigue driving state: utilize biosensor to monitor the most invasive of method of physiological driver's index change by force, can cause interference, poor practicability to driver; And using the method reliability of single fatigue characteristic low, practicality is not strong; And utilize the method for machine vision and image processing techniques, affect comparatively greatly by light change and driver's individual factors, cause the high or fatigue characteristic of these monitoring device costs to extract difficult, be difficult to acquisition widespread use; Although also there is many research to merge multiple fatigue characteristic, seldom consider driving fatigue state significantly behavioural characteristic relatively more directly perceived.Current most of monitoring method judges driving condition by the method for setting evaluation index threshold value, and be but subject to the impact of the factor such as individual difference and driving habits, cause evaluation index threshold value difficulty to be determined, monitoring real-time is not high, and effect is undesirable.
Summary of the invention
The present invention seeks to overcome the deficiency that prior art exists, provide that a kind of reliability is high, cost is low, real-time, monitoring effect is desirable, general applicability is high, based on the driver fatigue real-time monitoring system of multi information and monitoring method.
The present invention is that technical solution problem adopts following technical scheme:
The feature that the present invention is based on the driver fatigue real-time monitoring system of multi information is: described monitoring system is made up of information acquisition unit, information process unit and alarm unit;
Described information acquisition unit is provided with: pressure transducer, is arranged on bearing circle top layer, for extracting the grip information of driver to bearing circle; Angular transducer, is arranged on bearing circle rotary column, for extracting the corner information of bearing circle; Range sensor, is arranged on pilot set headrest, for extracting the head position information of driver; With the head position information of described grip information, corner information and driver for driving condition information;
Described information process unit is used for processing described driving condition information, obtains the fatigue strength characteristic parameter characterizing driving condition, judges driver fatigue state grade with described fatigue strength characteristic parameter;
Described alarm unit is used for carrying out alarm when information process unit judges that driver is in non-waking state.
The feature that the present invention is based on the driver fatigue method of real-time of multi information comprises the steps:
Step 1, gather the driving condition information of driver, described driving condition information refer to by pressure transducer detect the driver that obtains to the grip information of bearing circle, detected the corner information of the bearing circle obtained by angular transducer and detected the head position information of the driver obtained by range sensor;
Step 2, the driving condition information described in step 1 to be processed, obtain the fatigue strength characteristic parameter characterizing driving condition;
Step 3, to obtain a sample number by method described in step 1 and step 2 be the sample set of N, and described sample refers to that the fatigue strength characteristic parameter being calculated acquisition by step 2 is formed with determined by subjective assessment and that described fatigue strength characteristic parameter is corresponding driver fatigue state grade; Build three layers of BP network, utilize described sample set to carry out off-line training to described three layers of BP network, obtain the mathematical model characterizing Nonlinear Mapping relation between fatigue strength characteristic parameter and driver fatigue state grade;
Step 4, judge the moment at each, the fatigue strength characteristic parameter in current judgement moment is obtained in real time by method described in step 1 and step 2, with the described current input signal of fatigue strength characteristic parameter as step 3 gained mathematical model judging the moment, described mathematical model is utilized to judge the driver fatigue state grade in current judgement moment.
The feature that the present invention is based on the driver fatigue method of real-time of multi information is also:
In observation process, system take 0.2s as the driving condition information of cycle Real-time Collection driver; With the collection initial period of 30s for presetting the stage, in the described default stage, driver is in abnormal driving state, and presetting the image data of 20s after in the stage with 30s is the initial acquisition data of each driving condition information; The monitoring stage is entered at the end of described 30s presets the stage, in the described monitoring stage, system carries out the judgement of a driver fatigue state grade every 2s, each fatigue strength characteristic parameter judging that the moment adopts be judge the moment with this before and be judge that the moment obtains as the image data of the sampling time window of finish time calculates with this, different fatigue strength characteristic parameters has the sampling time window of identical or different duration.
Described fatigue strength characteristic parameter is grip amplitude fatigue strength FGA, corner standard deviation fatigue strength FASD, corner frequency fatigue strength FAF and biased from fatigue strength FPD;
Described grip amplitude fatigue strength FGA obtains as follows:
After utilizing the stage of presetting, the initial acquisition data of 20s calculate driver's grip initial value F 0for: in formula with be respectively driver's left hand of 20s and the grip average of the right hand after the default stage; The n-th grip value F judging the moment within the monitoring stage nfor: n=1,2,3..., in formula with be respectively n-th judge the moment before and be judge that the moment is as driver's left hand of 3s sampling time window of finish time and the grip average of the right hand with n-th; Then the n-th grip amplitude fatigue strength FGA judging the moment nfor: if FGA nbe less than zero, then by FGA nassignment is zero;
Described corner standard deviation fatigue strength FASD obtains as follows:
After utilizing the stage of presetting, the initial acquisition data of 20s calculate corner standard deviation initial value is SD 0, within the monitoring stage n-th judge the moment before and be judge that the corner standard deviation of moment as the 5s sampling time window of finish time is for SD with n-th n, n=1,2,3..., then the n-th corner standard deviation fatigue strength FASD judging the moment nfor:
Described corner frequency fatigue strength FAF obtains as follows:
After utilizing the stage of presetting, the initial acquisition data of 20s calculate corner correction frequency initial value is AN 0, within the monitoring stage n-th judge the moment before and be judge that the corner correction frequency of moment as the 20s sampling time window of finish time is for AN with n-th n, n=1,2,3..., then the n-th corner frequency fatigue strength FAF judging the moment nfor: if FAF nbe less than zero, then by FAF nassignment is zero;
Described biased obtains as follows from fatigue strength FPD:
Described range sensor is two ultrasonic sensors, described two ultrasonic sensors lay respectively at left side and the right side of pilot set headrest, utilize to preset the initial acquisition data of 20s after the stage and calculate that driver head is peripheral to be respectively with the distance average of described two ultrasonic sensors with the then distance initial value x of center, driver head square section and two ultrasonic sensors 0and y 0be respectively: with r is the cross section mean radius of driver head; The n-th distance value x judging center, moment driver head square section and two ultrasonic sensors within the monitoring stage nand y nbe respectively: with n=1,2,3..., in formula with be respectively n-th judge the moment before and be judge moment distance average with two ultrasonic sensors peripheral as the driver head of the 3s sampling time window of finish time with n-th;
Order: the center of two ultrasonic sensors is respectively an A and some B, presets center, stage driver head square section for some C; N-th judges that center, moment driver head square section is as some D; Then have: α is angle between straight line AC and straight line AB; β is angle between straight line AD and straight line AB; θ is the difference of β and α; L is an A and the spacing putting B.According to the cosine law and trigonometric function formula, have:
cos α = x 0 2 + L 2 - y 0 2 2 x 0 L , sin α = 1 - cos 2 α
cos β = x n 2 + L 2 - y n 2 2 x n L , sin β = 1 - cos 2 β
cosθ=cos(β-α)=cosαcosβ+sinαsinβ
N-th judges that the distance S of default stage driver head position is departed from moment driver head position nfor: S n = x 0 2 + x n 2 - 2 x 0 x n cos θ ; Then n-th judges the biased from fatigue strength FPD of moment nfor: FP D n = S n L .
Three layers of BP network that described step 3 builds are: ground floor is input layer, is made up of 4 input nodes, and 4 described input nodes institute distinguish 4 of correspondence and inputs component x 1, x 2, x 3and x 4be corresponding in turn to as grip amplitude fatigue strength FGA, corner standard deviation fatigue strength FASD, corner frequency fatigue strength FAF and biased from fatigue strength FPD, 4 input components form 1 input vector X and are: X=[x 1, x 2, x 3, x 4] t; The second layer is hidden layer; Third layer is output layer, is made up of 3 output nodes, 3 described output nodes distinguish 3 corresponding output component y 1, y 2and y 3represent waking state, fatigue state and degree of depth fatigue state successively, 3 output components form 1 output vector Y and are: Y=[y 1, y 2, y 3] t, with Y=[1,0,0] tbe characterized by waking state, with Y=[0,1,0] tbe characterized by fatigue state, with Y=[0,0,1] tbe characterized by degree of depth fatigue state; Described fatigue state and degree of depth fatigue state are non-waking state.
Compared with prior art, beneficial effect of the present invention is embodied in:
1, monitoring system of the present invention is preset in the stage at the 30s of observation process, every driver must be in abnormal driving state, for the fatigue strength characteristic parameter of aided solving every driver in the monitoring stage, compare the method that fixed value is set, improve the general applicability of system, practicality strengthens;
2, monitoring system of the present invention is in the monitoring stage, system carries out the judgement of a driver fatigue state grade every 2s, each fatigue strength characteristic parameter judging that the moment adopts be judge the moment with this before and be judge that the moment obtains as the image data of the sampling time window of finish time calculates with this, different fatigue strength characteristic parameters has the sampling time window of identical or different duration, both improve the utilization factor of data resource, also improve the real-time of system;
3, the head position information of driver to the grip information of bearing circle, the corner information of bearing circle and driver is utilized to carry out Multi-information acquisition in the present invention, use the monitoring method of single fatigue characteristic to compare with complex appts with other, reliability is high, fatigue characteristic extracts easily and monitoring device cost is low;
4, adopt BP network to identify in the present invention, set up the mathematical model of Nonlinear Mapping relation between fatigue strength characteristic parameter and driver fatigue state grade, adopt the determination methods of evaluation index threshold value compared to existing technology, more effectively accurately.
Accompanying drawing explanation
Fig. 1 is the schematic diagram that monitoring system of the present invention extracts fatigue strength characteristic parameter;
Fig. 2 is ultrasonic sensor Cleaning Principle schematic diagram in the present invention.
Specific embodiments
Driver fatigue real-time monitoring system based on multi information in the present embodiment is made up of information acquisition unit, information process unit and alarm unit; Wherein information acquisition unit is provided with: pressure transducer, is arranged on bearing circle top layer, for extracting the grip information of driver to bearing circle; Angular transducer, is arranged on bearing circle rotary column, for extracting the corner information of bearing circle; Range sensor, is arranged on pilot set headrest, for extracting the head position information of driver; With the head position information of grip information, corner information and driver for driving condition information; Information process unit is used for processing driving condition information, obtains the fatigue strength characteristic parameter characterizing driving condition, judges driver fatigue state grade with fatigue strength characteristic parameter; Alarm unit is used for carrying out alarm when information process unit judges that driver is in non-waking state.
In the present embodiment, the collection for driving condition information can use existing multiple sensing technology.In concrete enforcement, driver can be obtained by softness haptic perception pressure transducer the grip information of bearing circle; The corner information of bearing circle can be obtained by analog angular transducer; The head position information of driver can be obtained by ultrasonic sensor.
In the present embodiment, softness haptic perception pressure transducer is the sensor prepared as flexible pressure-sensitive material using carbon black filled silicon rubber, correlation technique is in " functional material " the 2nd phase in 2010, existing open in " conducing composite material for composite flexible touch sensor is studied " that the people such as Zhao Xing, Huang Ying deliver.In the present embodiment, 16 softness haptic perception pressure transducers are distributed in bearing circle top layer equally spacedly, are in bearing circle periphery; Warning device in softness haptic perception pressure transducer, analog angular transducer, ultrasonic sensor, alarm unit is all connected with information process unit hardware unit with digitizing LCD automobile Displaying Meter.
Driver fatigue method of real-time based on multi information in the present embodiment comprises the steps:
Step 1, gather the driving condition information of driver, driving condition information refer to by pressure transducer detect the driver that obtains to the grip information of bearing circle, detected the corner information of the bearing circle obtained by angular transducer and detected the head position information of the driver obtained by range sensor;
Step 2, information process unit process driving condition information, obtain fatigue strength characteristic parameter for judging driver fatigue state grade, fatigue strength characteristic parameter comprises: grip amplitude fatigue strength FGA, corner standard deviation fatigue strength FASD, corner frequency fatigue strength FAF and biased from fatigue strength FPD;
Step 3, to obtain a sample number by step 1 and step 2 method be the sample set of N, and sample refers to that the fatigue strength characteristic parameter being calculated acquisition by step 2 is formed with by the determined driver fatigue state grade corresponding with fatigue strength characteristic parameter of subjective assessment; Build three layers of BP network, utilize sample set to carry out off-line training to three layers of BP network, obtain the mathematical model characterizing Nonlinear Mapping relation between fatigue strength characteristic parameter and driver fatigue state grade;
In concrete enforcement, building three layers of BP network is: ground floor is input layer, is made up of 4 input nodes, 4 input nodes distinguish 4 corresponding input component x 1, x 2, x 3and x 4be corresponding in turn to as grip amplitude fatigue strength FGA, corner standard deviation fatigue strength FASD, corner frequency fatigue strength FAF and biased from fatigue strength FPD, 4 input components form 1 input vector X and are: X=[x 1, x 2, x 3, x 4] t; The second layer is hidden layer, and hidden layer node number is determined by training; Third layer is output layer, is made up of 3 output nodes, 3 output nodes distinguish 3 corresponding output component y 1, y 2and y 3represent waking state, fatigue state and degree of depth fatigue state successively, 3 output components form 1 output vector Y and are: Y=[y 1, y 2, y 3] t, with Y=[1,0,0] tbe characterized by waking state, with Y=[0,1,0] tbe characterized by fatigue state, with Y=[0,0,1] tbe characterized by degree of depth fatigue state, wherein fatigue state and degree of depth fatigue state are non-waking state.
For obtaining the citing of sample set: to 14 male sex and 6 women totally 20 drivers test, age is 24-55 year, 6.1 years average driving ages, test period is afternoon 11 up to 13 time, night 24 up to morning 2 time and 4 up to 6 time this three periods process of the test is recorded a video, take 30s as interval to video to mark to tested personnel's driving condition by 5 trained testing crews are independent, get the subjective assessment of its mean value as tested personnel's driving condition, the classification grade of subjective assessment is identical with driver fatigue state grade, wherein 300 groups of samples comprising various driver fatigue state grade are selected to form sample set.
Step 4, judge the moment at each, the fatigue strength characteristic parameter in current judgement moment is obtained in real time by step 1 and step 2 method, with the current input signal of fatigue strength characteristic parameter as step 3 gained mathematical model judging the moment, mathematical model is utilized to judge the driver fatigue state grade in current judgement moment.
In concrete enforcement:
In observation process, system take 0.2s as the driving condition information of cycle Real-time Collection driver; With the collection initial period of 30s for presetting the stage, in the default stage, driver is in abnormal driving state, and presetting the image data of 20s after in the stage with 30s is the initial acquisition data of each driving condition information, and front 10s is used for driver and adjusts driving condition; The monitoring stage is entered at the end of 30s presets the stage, in the monitoring stage, system carries out the judgement of a driver fatigue state grade every 2s, each fatigue strength characteristic parameter judging that the moment adopts be judge the moment with this before and be judge that the moment obtains as the image data of the sampling time window of finish time calculates with this, different fatigue strength characteristic parameters has the sampling time window of identical or different duration.Fig. 1 is the schematic diagram that monitoring system of the present invention extracts fatigue strength characteristic parameter.
Grip amplitude fatigue strength FGA obtains as follows:
Driver holds bearing circle and namely touches two softness haptic perception pressure transducers, and after utilizing the stage of presetting, the initial acquisition data of 20s calculate driver's grip initial value F 0for: in formula with be respectively driver's left hand of 20s and the grip average of the right hand after the default stage; The n-th grip value F judging the moment within the monitoring stage nfor: n=1,2,3..., in formula with be respectively n-th judge the moment before and be judge that the moment is as driver's left hand of 3s sampling time window of finish time and the grip average of the right hand with n-th; When driver is in fatigue state, the grip of bearing circle is increased with degree of fatigue and reduces gradually, then the n-th grip amplitude fatigue strength FGA judging the moment nfor: if FGA nbe less than zero, then by FGA nassignment is zero;
Corner standard deviation fatigue strength FASD obtains as follows:
After utilizing the stage of presetting, the initial acquisition data of 20s calculate corner standard deviation initial value is SD 0, within the monitoring stage n-th judge the moment before and be judge that the corner standard deviation of moment as the 5s sampling time window of finish time is for SD with n-th n, n=1,2,3..., when driver is in fatigue state, with the feature significantly revising bearing circle, when degree of fatigue is deepened, steering wheel angle amplitude also shows in a long time without the feature of significant change, then the n-th corner standard deviation fatigue strength FASD judging the moment nfor: FASD n = | 1 - SD n SD 0 | ;
Corner frequency fatigue strength FAF obtains as follows:
After utilizing the stage of presetting, the initial acquisition data of 20s calculate corner correction frequency initial value is AN 0, within the monitoring stage n-th judge the moment before and be judge that the corner correction frequency of moment as the 20s sampling time window of finish time is for AN with n-th n, n=1,2,3..., when driver is in fatigue state, the correction frequency of driver to bearing circle obviously reduces, then the n-th corner frequency fatigue strength FAF judging the moment nfor: if FAF nbe less than zero, then by FAF nassignment is zero;
Biased to obtain as follows from fatigue strength FPD:
Two ultrasonic sensors are set, lay respectively at left side and the right side of pilot set headrest, utilize and preset the initial acquisition data of 20s after the stage and calculate that driver head is peripheral to be respectively with the distance average of two ultrasonic sensors with the then distance initial value x of center, driver head square section and two ultrasonic sensors 0and y 0be respectively: with r is the cross section mean radius of driver head; The n-th distance value x judging center, moment driver head square section and two ultrasonic sensors within the monitoring stage nand y nbe respectively: with n=1,2,3..., in formula with be respectively n-th judge the moment before and be judge moment distance average with two ultrasonic sensors peripheral as the driver head of the 3s sampling time window of finish time with n-th;
Order: the center of two ultrasonic sensors is respectively an A and some B, presets center, stage driver head square section for some C; N-th judges that center, moment driver head square section is as some D; Then have: α is angle between straight line AC and straight line AB; β is angle between straight line AD and straight line AB; θ is the difference of β and α; L is an A and the spacing putting B.Fig. 2 is ultrasonic sensor Cleaning Principle schematic diagram in the present invention.According to the cosine law and trigonometric function formula, have:
cos α = x 0 2 + L 2 - y 0 2 2 x 0 L , sin α = 1 - cos 2 α
cos β = x n 2 + L 2 - y n 2 2 x n L , sin β = 1 - cos 2 β
cosθ=cos(β-α)=cosαcosβ+sinαsinβ
N-th judges that the distance S of default stage driver head position is departed from moment driver head position nfor: when driver is in fatigue state, head position is compared with head position during waking state, and the larger degree of fatigue of departure degree is darker, then n-th judges the biased from fatigue strength FPD of moment nfor:
Sampling time window in the present embodiment selected by each fatigue strength characteristic parameter is preferred value, chooses decision by lot of experiments analysis.
In the present embodiment, the mathematical model of Nonlinear Mapping relation between the sign fatigue strength characteristic parameter obtained and driver fatigue state grade is embedded information process unit; Information process unit processes the fatigue strength characteristic parameter in driving condition information acquisition current judgement moment in real time, judges the driver fatigue state grade of current time; Within the default stage, grip amplitude fatigue strength FGA, corner standard deviation fatigue strength FASD, corner frequency fatigue strength FAF and a biased initial value from fatigue strength FPD are 0.
In the present embodiment, information process unit is hardware unit, be arranged on by digitizing LCD automobile Displaying Meter, the selection window that driver provides by the operation push-button on information process unit hardware unit and digitizing LCD automobile Displaying Meter, according to the traffic conditions grade of present road, trackside environmental rating and road quality classification, timing early warning indicating mode is set voluntarily.
In the present embodiment, alarm unit uses digitizing LCD automobile Displaying Meter, the monitoring information of real-time display system: driver fatigue state grade, grip, corner, head position, system operation time.When monitoring driver and being in fatigue state, carry out voice reminder and light flash warning; When being in degree of depth fatigue state, carrying out voice reminder, light flash, injection irritative gas and vibrating device and report to the police, realize the multifunction type of alarm of the sense of hearing, vision, sense of smell, sense of touch; All there is distribution warning device multiple position in car of this cover monitoring system, can improve the safety of other occupants and remind consciousness, realizing multi-facetedization type of alarm; In addition, when driver is in degree of depth fatigue state, the external alert mode of two flashing light that carries out blowing a whistle to front vehicles, front vehicle is opened, make real-time monitoring system more effectively, more in real time, more extensive.

Claims (2)

1., based on a driver fatigue method of real-time for multi information, it is characterized in that, comprise the steps:
Step 1, gather the driving condition information of driver, described driving condition information refer to by pressure transducer detect the driver that obtains to the grip information of bearing circle, detected the corner information of the bearing circle obtained by angular transducer and detected the head position information of the driver obtained by range sensor;
Step 2, the driving condition information described in step 1 to be processed, obtain the fatigue strength characteristic parameter characterizing driving condition;
Step 3, to obtain a sample number by method described in step 1 and step 2 be the sample set of N, and described sample refers to that the fatigue strength characteristic parameter being calculated acquisition by step 2 is formed with determined by subjective assessment and that described fatigue strength characteristic parameter is corresponding driver fatigue state grade; Build three layers of BP network, utilize described sample set to carry out off-line training to described three layers of BP network, obtain the mathematical model characterizing Nonlinear Mapping relation between fatigue strength characteristic parameter and driver fatigue state grade;
Step 4, judge the moment at each, the fatigue strength characteristic parameter in current judgement moment is obtained in real time by method described in step 1 and step 2, with the described current input signal of fatigue strength characteristic parameter as step 3 gained mathematical model judging the moment, described mathematical model is utilized to judge the driver fatigue state grade in current judgement moment;
Described fatigue strength characteristic parameter is grip amplitude fatigue strength FGA, corner standard deviation fatigue strength FASD, corner frequency fatigue strength FAF and biased from fatigue strength FPD;
Described grip amplitude fatigue strength FGA obtains as follows:
The initial acquisition data of 20s after in the stage of presetting are utilized to calculate driver's grip initial value F 0for: in formula with be respectively driver's left hand of 20s and the grip average of the right hand after in the default stage; The n-th grip value F judging the moment within the monitoring stage nfor: n=1,2,3..., in formula with be respectively n-th judge the moment before and be judge that the moment is as driver's left hand of 3s sampling time window of finish time and the grip average of the right hand with n-th; Then the n-th grip amplitude fatigue strength FGA judging the moment nfor: if FGA nbe less than zero, then by FGA nassignment is zero;
Described corner standard deviation fatigue strength FASD obtains as follows:
Utilizing the initial acquisition data of rear 20s in the stage of presetting to calculate corner standard deviation initial value is SD 0, within the monitoring stage n-th judge the moment before and be judge that the corner standard deviation of moment as the 5s sampling time window of finish time is for SD with n-th n, n=1,2,3..., then the n-th corner standard deviation fatigue strength FASD judging the moment nfor:
Described corner frequency fatigue strength FAF obtains as follows:
Utilizing the initial acquisition data of rear 20s in the stage of presetting to calculate corner correction frequency initial value is AN 0, within the monitoring stage n-th judge the moment before and be judge that the corner correction frequency of moment as the 20s sampling time window of finish time is for AN with n-th n, n=1,2,3..., then the n-th corner frequency fatigue strength FAF judging the moment nfor: if FAF nbe less than zero, then by FAF nassignment is zero;
Described biased obtains as follows from fatigue strength FPD:
Described range sensor is two ultrasonic sensors, described two ultrasonic sensors lay respectively at left side and the right side of pilot set headrest, utilize the initial acquisition data of 20s after in the stage of presetting to calculate driver head periphery and are respectively with the distance average of described two ultrasonic sensors with the then distance initial value x of center, driver head square section and two ultrasonic sensors 0and y 0be respectively: with r is the cross section mean radius of driver head; The n-th distance value x judging center, moment driver head square section and two ultrasonic sensors within the monitoring stage nand y nbe respectively: with n=1,2,3..., in formula with be respectively n-th judge the moment before and be judge moment distance average with two ultrasonic sensors peripheral as the driver head of the 3s sampling time window of finish time with n-th;
Order: the center of two ultrasonic sensors is respectively an A and some B, presets center, stage driver head square section for some C; N-th judges that center, moment driver head square section is as some D; Then have: α is angle between straight line AC and straight line AB; β is angle between straight line AD and straight line AB; θ is the difference of β and α; L is an A and the spacing putting B; According to the cosine law and trigonometric function formula, have:
cos α = x 0 2 + L 2 - y 0 2 2 x 0 L , sin α = 1 - cos 2 α
cos β = x n 2 + L 2 - y n 2 2 x n L , sin β = 1 - cos 2 β
cosθ＝cos(β-α)＝cosαcosβ+sinαsinβ
N-th judges that the distance S of default stage driver head position is departed from moment driver head position nfor:
then n-th judges the biased from fatigue strength FPD of moment nfor:
In observation process, system take 0.2s as the driving condition information of cycle Real-time Collection driver; With the collection initial period of 30s for presetting the stage, in the described default stage, driver is in abnormal driving state, and presetting the image data of 20s after in the stage with 30s is the initial acquisition data of each driving condition information; The monitoring stage is entered at the end of described 30s presets the stage, in the described monitoring stage, system carries out the judgement of a driver fatigue state grade every 2s, each fatigue strength characteristic parameter judging that the moment adopts be judge the moment with this before and be judge that the moment obtains as the image data of the sampling time window of finish time calculates with this, different fatigue strength characteristic parameters has the sampling time window of identical or different duration.
2. the driver fatigue method of real-time based on multi information according to claim 1, it is characterized in that, three layers of BP network that described step 3 builds are: ground floor is input layer, is made up of 4 input nodes, and 4 described input nodes institute distinguish 4 of correspondence and inputs component x 1, x 2, x 3and x 4be corresponding in turn to as grip amplitude fatigue strength FGA, corner standard deviation fatigue strength FASD, corner frequency fatigue strength FAF and biased from fatigue strength FPD, 4 input components form 1 input vector X and are: X=[x 1, x 2, x 3, x 4] t; The second layer is hidden layer; Third layer is output layer, is made up of 3 output nodes, 3 described output nodes distinguish 3 corresponding output component y 1, y 2and y 3represent waking state, fatigue state and degree of depth fatigue state successively, 3 output components form 1 output vector Y and are: Y=[y 1, y 2, y 3] t, with Y=[1,0,0] tbe characterized by waking state, with Y=[0,1,0] tbe characterized by fatigue state, with Y=[0,0,1] tbe characterized by degree of depth fatigue state; Described fatigue state and degree of depth fatigue state are non-waking state.
CN201310415071.3A 2013-09-12 2013-09-12 Based on driver fatigue real-time monitoring system and the monitoring method of multi information Expired - Fee Related CN103473890B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310415071.3A CN103473890B (en) 2013-09-12 2013-09-12 Based on driver fatigue real-time monitoring system and the monitoring method of multi information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310415071.3A CN103473890B (en) 2013-09-12 2013-09-12 Based on driver fatigue real-time monitoring system and the monitoring method of multi information

Publications (2)

Publication Number Publication Date
CN103473890A CN103473890A (en) 2013-12-25
CN103473890B true CN103473890B (en) 2015-09-16

Family

ID=49798719

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310415071.3A Expired - Fee Related CN103473890B (en) 2013-09-12 2013-09-12 Based on driver fatigue real-time monitoring system and the monitoring method of multi information

Country Status (1)

Country Link
CN (1) CN103473890B (en)

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6372388B2 (en) * 2014-06-23 2018-08-15 株式会社デンソー Driver inoperability detection device
CN104112335A (en) * 2014-07-25 2014-10-22 北京机械设备研究所 Multi-information fusion based fatigue driving detecting method
CN105786362B (en) * 2014-12-26 2019-08-27 中国移动通信集团公司 A kind of based reminding method and device based on pose information
CN105282717B (en) * 2015-06-29 2019-12-03 维沃移动通信有限公司 Based reminding method and mobile terminal
CN106251615B (en) * 2015-07-21 2019-10-08 北京智谷睿拓技术服务有限公司 Driver determines method and apparatus, car-mounted terminal and dispatch server
CN105701972A (en) * 2016-04-14 2016-06-22 苏州清研微视电子科技有限公司 System for detecting fatigue driving by using driving behavior variability characteristics
CN105943052A (en) * 2016-05-30 2016-09-21 深圳先进技术研究院 A fatigue driving detection method and device
CN106274671B (en) * 2016-08-04 2019-05-24 观致汽车有限公司 The based reminding method and system of non-security driving condition
CN106114604A (en) * 2016-08-16 2016-11-16 四川绿创环阅环保科技有限公司 With alcohol detection and the steering wheel of fatigue detecting
CN106585490A (en) * 2016-12-16 2017-04-26 盐城工学院 Fatigue driving detection method and system and steering wheel
WO2018165901A1 (en) * 2017-03-15 2018-09-20 廖建强 Driver state monitoring apparatus and monitoring method
CN110709903B (en) * 2017-05-30 2021-08-06 松下知识产权经营株式会社 Wake guidance control device and wake guidance system
CN107248263A (en) * 2017-08-08 2017-10-13 京东方科技集团股份有限公司 A kind of fatigue driving detecting system
CN107802274A (en) * 2017-11-23 2018-03-16 山东科技大学 Fatigue strength detection method and system based on physical signs
FR3078407A1 (en) * 2018-02-23 2019-08-30 Airbus Operations (S.A.S.) METHOD FOR MEASURING THE STATUS OF VIGILANCE OF A PILOT
CN108839658B (en) * 2018-05-07 2021-03-26 威马智慧出行科技（上海）有限公司 Fatigue driving monitoring system and method
CN109044379A (en) * 2018-06-26 2018-12-21 深圳市元征科技股份有限公司 A kind of fatigue driving judgment method, system, equipment and computer storage medium
CN110796207B (en) * 2019-11-08 2023-05-30 中南大学 Fatigue driving detection method and system
CN112183216A (en) * 2020-09-02 2021-01-05 温州大学 Auxiliary system for communication of disabled people
CN115626171B (en) * 2022-12-07 2023-03-21 小米汽车科技有限公司 Automatic vehicle driving method and device, electronic equipment and storage medium

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7427924B2 (en) * 2005-02-11 2008-09-23 Triodyne Inc. System and method for monitoring driver fatigue
US20090308679A1 (en) * 2008-06-16 2009-12-17 Ion Murgu Driver fatigue status detector device
CN101540090B (en) * 2009-04-14 2011-06-15 华南理工大学 Driver fatigue monitoring method based on multivariate information fusion
CN101872171B (en) * 2009-04-24 2012-06-27 中国农业大学 Driver fatigue state recognition method and system based on information fusion
CN101746269B (en) * 2010-01-08 2013-04-03 东南大学 Fatigue driving fusion detection method based on soft computing
CN102765352B (en) * 2012-07-27 2015-06-03 浙江吉利汽车研究院有限公司杭州分公司 System for monitoring vehicle driving state

Also Published As

Publication number Publication date
CN103473890A (en) 2013-12-25

Similar Documents

Publication Publication Date Title
CN103473890B (en) Based on driver fatigue real-time monitoring system and the monitoring method of multi information
Peng et al. Multi-parameter prediction of drivers' lane-changing behaviour with neural network model
Chai Drowsiness monitoring based on steering wheel status
CN104112334B (en) Fatigue driving method for early warning and system
CN103680246B (en) The drive safety examination evaluation system distributing based on vision attention
CN103770733B (en) Method and device for detecting safety driving states of driver
CN105564436A (en) Advanced driver assistance system
CN107972671A (en) A kind of driving behavior analysis system
CN104207791A (en) Fatigue driving detection method
CN206938738U (en) A kind of automobile brake sheet detection means
CN102208125B (en) Fatigue driving monitoring system and method thereof
CN104112335A (en) Multi-information fusion based fatigue driving detecting method
CN105513405B (en) A kind of track of vehicle analysis method and device
CN106875510A (en) A kind of vehicle rollover method for early warning and system
CN102961126A (en) Drive early-warning method based on pulse condition diagnosis mode
CN106611505A (en) Driving behavior based traveling assistance method
CN106073712A (en) Driving based on heart physiological signal warning direction indicators cover device and signal detecting method
CN109367539A (en) A kind of intelligence system detecting fatigue driving
CN108711204B (en) Driving abnormity detection system and method integrating human-vehicle-road multi-source information
CN105243789A (en) Fatigue driving detection method of fusing electrocardiosignal and steering wheel holding pressure
CN103622682A (en) System and method for detecting health state of driver
CN101843496A (en) Driving work-load kit detection method
CN111009137A (en) Interval speed measurement prompting method and system based on camera and navigation data fusion and automobile
CN103854539A (en) Electronic road test monitoring system based on video analysis
CN207008876U (en) A kind of ice and snow weather highway trip real-time early warning device

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20150916

Termination date: 20190912