CN103956028A - Automobile multielement driving safety protection method - Google Patents

Abstract

The invention provides an automobile multielement driving safety protection method and equipment special for the automobile multielement driving safety protection method. The method comprises the steps that the face information and pulse information of a driver are collected, an empirical mode decomposition scheduling algorithm based on information entropy is applied, characteristic quantities capable of effectively reflecting the angry feelings, the fatigue states and the identity information of a human body in the face information and the pulse information are extracted, and the characteristic parameters of various types are combined through an intelligent algorithm so that the angry feelings, the fatigue states and the identity information of the driver can be accurately recognized. The equipment special for the method is achieved based on a DSP, Bluetooth wireless communication and other technologies, and when the device detects the abnormal feeling or driving fatigue or identity changing and other states of the driver, the driving behavior of the driver is interfered through alarming prompts, background recording and other modes, and then the driving safety of the driver is protected from multiple aspects.

Description

The polynary driving safety means of defence of a kind of automobile

Technical field

The present invention relates to the polynary driving safety means of defence of a kind of automobile, relate in particular to a kind of can simultaneously monitoring driver's angry mood, fatigue state and identity information, and then implement the polynary driving safety means of defence of automobile of prompting and safeguard procedures.

Background technology

Along with improving constantly and the fast development of Modern Traffic forwarding business of people's living standard, transport need increases day by day.The vehicles, particularly on-road vehicle are increasing, cause frequent accidents to occur.Statistical data shows, in China, toll on traffic accounts for the more than 3/4 of all kinds of particularly serious security incident death tolls, and traffic hazard has become " the first killer " in various accidents.

In whole traffic system, transport driver, as taxi driver, bus driver, long-distance passenger transportation driver and teamster etc., is playing the part of very important role, and the safety of whole traffic system is had to important impact.It is the important leverage that ensures the transportation system safety at its place that driver's specification is driven, but in real operation, but has following three kinds of nonstandard driving phenomenons:

The first, " road anger " phenomenon ubiquity.In Vehicle Driving Cycle process, driver's mood can be subject to the impact of driving environment.Road anger disease refers to angry, the even aggressive behavior that driver causes because of dysthymia in driving procedure.Likely there is road anger disease in all kinds of drivers, particularly in urban highway traffic, because driving, traffic congestion, new hand or Apprentice 0ffice in unskilled, part driver's startup procedure, there is the bad steering customs such as random intertrack crosstalk, cause other drivers to occur unhealthy emotion, even bring out road anger disease, so cause fighting for signal, joyride or the dangerous traffic behavior such as blow a whistle loudly scramble for roads.Road anger disease had both been unfavorable for building harmonious social environment, also can become the potential risk of traffic safety.

The second, fatigue driving phenomenon often has generation.Taking coach as example, because causing the report of coach generation traffic hazard, fatigue driving again and again occurs.Once there is traffic hazard in coach, not only driver, in car, each passenger's safety of life and property all can be subject to serious threat, brings danger also can to other vehicles simultaneously, causes great casualties and property loss.In taxi and long-haul over-the-highway truck, driver is in order to pursue larger economic interests, and often long-time continuous is driven, and finally causes, because of driving fatigue, traffic hazard occurs.Fatigue driving is as one of main hidden danger of traffic safety, and its identification and warning problem are urgently to be resolved hurrily.

Three, Professional drivers is arbitrarily taken over other's shift phenomenon and is often occurred.Arbitrarily take over other's shift phenomenon the most common in cab driving.Each taxi is interior should driving by the driver who specifies at a fixed time, but in reality, relief person's selection but has very large randomness, even there will be the people who does not possess this car driving qualification to take over other's shift.This has increased the possibility that traffic accidents occurs undoubtedly, and occurs after traffic hazard, is also not easy to the identification of responsibility, makes troubles to traffic administration and law enforcement agency.

In order to reduce traffic hazard, to ensure traffic safety, people wish to build harmonious traffic environment by laws and regulations or technological means.For this reason, country has put into effect some corresponding laws and regulations, and the development of modern science and technology is also for traffic safety problem has found effective solution route simultaneously.For example, utilize advanced video technique and sensor technology, can obtain easily facial information and the physiologic information of human body.Express one's feelings and the mode identification technology identity of identification of driver easily based on human body face, and can obtain driver's part fatigue and angry information.Human-body fatigue and angry emotional change can reflect better by physiological parameter, and various Wearable sensors also provide possibility for the physiologic information of driver in duty detects.Fusion Features and the recognition technology of research based on human body face information and physiological signal, and be applied in the middle of driver's driving environment, relieving fatigue is driven and road anger disease problem effectively.Meanwhile, itself comprises identity information facial information, also can realize easily driver's identification by face-image.If the angry mood to driver and fatigue state are identified and remind in time, driver's identity is confirmed simultaneously, must play good protective action to driver's driving safety.

Summary of the invention

In order to overcome the problems such as existing driving safety safeguard measure function singleness and detecting and assessing means are too simple; the invention provides the polynary driving safety means of defence of a kind of automobile and specialized equipment thereof; the fusion of the method based on to facial information and pulse information; can realize the comprehensive identification of the fatigue state to driver, angry mood and identity information simultaneously, thus multiple angle protection driver's safe driving.

The present invention is the polynary driving safety means of defence of a kind of automobile, mainly realizes as follows:

Step (1): gather driver's facial information and pulse information by two CMOS cameras and the wireless pulse transducer of Wrist belt-type respectively, and carry out respectively filtering operation to eliminate the interference of noise;

Step (2): in facial information and pulse information, by the empirical mode decomposition algorithm based on information entropy, extract respectively the characteristic parameter that can reflect human body indignation mood, fatigue state and identity information;

Step (3): by Fisher linear classification scheduling algorithm, the corresponding characteristic parameter of various states extracting in step (2) is carried out to fusion treatment, and realize the identification of angry mood, fatigue state and the identity information to driver simultaneously;

Step (4): according to the result of step (3) state recognition, take the mode of alarm or backstage record to respond driver, from multiple angles, driver's driving safety is protected.

As the further improvement of invention, in described step (1), by two CMOS camera collection drivers' facial information, the wide-angle camera that is wherein arranged on A post position is responsible for the head position location to driver, the high-resolution camera that is arranged on windshield upper limb is responsible for gathering driver's face-image, and the position of this camera and shooting angle can be finely tuned; Gather driver's pulse information by Wrist belt-type pulse transducer, adopt lithium battery as power supply, the pulse information collecting outwards transmits in blue teeth wireless mode, thereby avoids line, farthest avoids the interference to the operation of driver's normal driving.To the facial information collecting and pulse information, carry out respectively filtering operation to eliminate the interference of noise.

As the further improvement of invention, in described step (2), required for different state recognitions, from facial image information and pulse information, extract respectively one or more in angry emotional characteristics parameter, fatigue state characteristic parameter and identity characteristic parameter, be specially:

1) angry emotional characteristics parameter,

For facial information, first determine the position of human eye by mixing integration sciagraphy, mixing integration projection formula is:

$H_v\left(x\right)=\frac{1}{2}{{\mathrm{\σ}}_v}^2\left(x\right)+\frac{1}{2}{M}_v\left(x\right),H_h\left(y\right)=\frac{1}{2}{{\mathrm{\σ}}_h}^2\left(y\right)+\frac{1}{2}{M}_h\left(y\right)$

H in formula _vand H (x) _h(y) hybrid projection of difference presentation video in vertical and horizontal direction, M _vand M (x) _h(y) be illustrated in the average integral projection in vertical and horizontal direction, σ _vand σ (x) _h(y) be illustrated in the variance integral projection in vertical and horizontal direction; Determine accurate human face region according to the feature of the statistical law relation between position of human eye and face contour and image itself, and then use Principal Component Analysis Algorithm (PCA) to extract major component vector, major component Z to facial image _icomputing formula be:

Z _i＝(X ₁,X ₂,X ₃,…,X _p)*(L ₁,L ₂,L ₃,…,L _p) ^T

X in formula _i(i=1,2 ..., p) each column vector of presentation video matrix X, L _i(i=1,2 ..., p) each column vector of expression major component loading matrix L, carries out angry Emotion identification taking Zi as characteristic quantity;

For pulse information, in the time obtaining one section of continuous pulse signal, to use method of characteristic point to determine main ripple position, and then obtain pulse frequency and pulse frequency average, the computing formula of pulse frequency is

$h=\frac{60}{\▿t}$

In formula, ▽ t represents the mistiming of adjacent two main ripples, h is carried out to calculus of differences and get final product to obtain HRV HRV; Use FFT that pulse signal is converted to frequency field, and calculate pulse power spectrum energy Ratios r, formula is

$r=\frac{\underset{k=k_1}{\overset{k_2}{\mathrm{\Σ}}}{\left|X\left(k\right)\right|}^2}{\underset{k=k_3}{\overset{k_4}{\mathrm{\Σ}}}{\left|X\left(k\right)\right|}^2}$

Observed reading when X in formula (k) expression pulse signal frequency is k, k1, k2, k3, k4 represent specific frequency values.Finally, pulse information is carried out to mode Energy Decomposition, calculate pulse mode Energy-Entropy, formula is:

$T_{(i-j)/(h-k)}=\frac{\underset{x=i}{\overset{j}{\mathrm{\Σ}}}T\left(x\right)}{\underset{x=h}{\overset{k}{\mathrm{\Σ}}}T\left(x\right)}$

T in formula (x) is the mode energy after the normalization of k natural mode of vibration component of pulse signal, and i, j, k, h represent the sequence number of natural mode of vibration component;

2) fatigue state characteristic parameter,

For facial information, in the time obtaining piece image, determine the position of human eye by mixing integration sciagraphy, use mean-shift algorithm to cut apart pupil part, the computing formula of mean-shift is:

$M_h\left(x\right)\≡\frac{\underset{i=1}{\overset{n}{\mathrm{\Σ}}}G\left(\frac{x_i-x}{h}\right)w\left(x_i\right)(x_i-x)}{\underset{i=1}{\overset{n}{\mathrm{\Σ}}}G\left(\frac{x_i-x}{h}\right)w\left(x_i\right)}$

M in formula _h(x) the mean-shift value of expression sample, x _ifor sample point, point centered by x, G (y) represents kernel function, h represents the window size of kernel function, w (x _i) be sample point x _iweight; Continue to use mean-shift algorithm to follow the trail of pupil position in ensuing image, thereby obtain the continuous pupil image information of some width in a period of time, and then can calculate PERCLOS, frequency of wink and average three parameters of pupil size, in order to carry out fatigue state identification; Wherein PERCLOS refers to the shared ratio of eyes closed within a certain period of time, and computing formula is:

$f=\frac{t_3-t_2}{t_4-t_1}\×100\%$

T in formula ₁, t ₂, t ₃, t ₄be illustrated respectively in the eye movement cycle, eyes aperture is 80%, 20%, 20% and 80% time point; Frequency of wink s refers to the number of times of blinking within the unit interval, and formula is

$s=\frac{n}{\mathrm{\Δt}}$

In formula, n is the picture number that eyes aperture is less than 10%, and Δ t is the time interval; The computing formula of average pupil size q is:

$q=\frac{1}{n}\mathrm{\Σ}{l}_i$

L in formula _irepresent the spacing of lower limb on pupil, n is interior during this period of time pupil image number; For pulse information, first replace heart rate so that pulse frequency is approximate, and then definite HRV parameter, and can be than carrying out fatigue state identification with mode Energy-Entropy in conjunction with pulse spectrum;

3) identity information characteristic parameter, for facial information, first determine the position of human eye by mixing integration sciagraphy, determine accurate human face region according to position of human eye and facial statistical law and characteristics of image, and then facial image is used to PCA algorithm classification major component vector, in order to carry out identity information identification; Because the identity information comprising in the middle of pulse information is less, therefore pulse information does not participate in the identification of identity information.

As the further improvement of invention, in described step (3), information fusion and pattern-recognition refer to by intelligent algorithm, and each category feature parameter is carried out to fusion treatment, and realize the accurate monitoring to corresponding state, are specially:

1) angry mood monitoring, using 5 seconds as the time interval, by the facial information gathering in every 5 seconds and pulse information in order to execution step (2), extract angry emotional characteristics parameter, using the angry emotional characteristics parameter of extracting in step (2) as input quantity, use Fisher linear classifier by its fusion treatment, the process of classification has realized the monitoring to angry mood, judge that if double driver is for angry mood, assert that the current mood of driver is for indignation; Wherein Fisher linear classifier is method common in pattern classification, its thought is that input feature vector is made to linear projection, make between the class of data after projection dispersion reach maximum and in class dispersion reach minimum, linear projection axle used is called discriminant vectors, then by discriminant vectors, sample is carried out to projection, thereby determine the classification under sample, obtain classification results;

2) fatigue state monitoring, using 1 minute as the time interval, by the facial information gathering in each minute and pulse information in order to execution step (2), extract fatigue state characteristic parameter, using the fatigue state characteristic parameter extracting in step (2) as input quantity, use SVM algorithm by its fusion treatment, the process of classification has realized the monitoring to fatigue state, judge that if double driver, for fatigue state, assert the current fatigue state that entered of driver; Wherein SVM algorithm is a kind of two conventional sorting algorithms, its step is, by inner product function by input feature vector linear transformation to higher dimensional space, and in higher dimensional space, find optimal classification face by the mode of training, then in this space, determine classification results with the position relationship of optimal classification face according to sample;

3) identity information monitoring, using 5 minutes as the time interval, by the facial information gathering in every 5 minutes and pulse information in order to execution step (2), extract identity characteristic parameter, using the identity information characteristic parameter extracting in step (2) as input quantity, use Fisher linear classifier by its fusion treatment, the process of classification has realized the monitoring to identity information, if double judgement driver's identity information is not inconsistent, assert that current driver is not the driver who specifies;

As the further improvement of invention, in described step (4), the specific implementation of feedback measure is: in the time monitoring driver and occur fatigue state or angry mood, feed back to driver by the mode of playing alarm sound, thereby proofread and correct driver's bad steering state, ensure driving safety; When monitoring driver's identity information when wrong, preserve driver's face-image now by a memory storage with access rights, wait until supvr and make regular check on processing, thereby stop arbitrarily to take over other's shift phenomenon, ensure driving safety.

The invention has the beneficial effects as follows: by the accurate collection to facial information and pulse information, use intelligent algorithm to carry out effective fusion treatment to two kinds of information, realize the comprehensive identification of angry mood, fatigue state and the identity information to driver simultaneously, there is the feature of multifunctionality, accuracy and simplification, can protect driver's driving safety from multiple angles, thereby the generation avoiding traffic accident, reduces casualties and property loss.

Brief description of the drawings

Fig. 1 is hardware structure diagram of the present invention.

Fig. 2 is process flow diagram of the present invention.

Fig. 3 is that Wrist belt type sensor is worn schematic diagram.

Fig. 4 is that real vehicle is installed front view.

Fig. 5 is that real vehicle is installed vertical view.

In Fig. 4-5, the representative of circle frame is decided to be camera, and oval frame represents acquisition camera, and rectangle frame represents main computer unit.

Embodiment

Below in conjunction with accompanying drawing and embodiment, the invention will be further described.

The invention provides the car assisted polynary driving safety means of defence of a kind of automobile multifunctional and specialized equipment thereof, its specific implementation step is as follows:

Step 1: the collection of facial information and pulse information;

(1) by two CMOS camera collection drivers' facial information, the wide-angle camera that is wherein arranged on A post position positions driver's head position, the high-resolution camera that is arranged on windshield upper limb is responsible for gathering driver's face-image details, and the position of this camera and shooting angle can be finely tuned;

(2) by Wrist belt-type pulse transducer collection driver's pulse information, adopt lithium battery as power supply, the pulse information collecting outwards transmits in blue teeth wireless mode, thereby avoids line, farthest reduces the interference to the operation of driver's normal driving;

Step 2: information processing;

Facial information and pulse information are respectively in wired and mode blue teeth wireless, be sent to and be arranged on copilot glove box place, central processing module using DSP as MCU, processing module is by realizing the state recognition to driver to the fusion treatment of two kinds of signals, and processing procedure comprises:

(1) pre-service, carries out filtering to facial image information and pulse information respectively, to eliminate the impact of noise;

(2) feature extraction, required for different state recognitions, from facial image information and pulse information, extract respectively angry emotional characteristics parameter, fatigue state characteristic parameter and identity characteristic parameter, be specially:

A) angry emotional characteristics parameter, for facial information, first determine the position of human eye in conjunction with template matches and mixing integration sciagraphy, determine accurate human face region according to the feature of the statistical law relation between position of human eye and face contour and image itself, and then use PCA algorithm to extract major component vector to facial image, in order to carry out angry Emotion identification; For pulse information, in the time obtaining one section of continuous pulse signal, to use respectively method of characteristic point to determine main ripple position, and then obtain pulse frequency and pulse frequency average, the computing formula of pulse frequency is

$h=\frac{60}{\▿t}$

In formula, ▽ t represents the mistiming of adjacent two main ripples, h is carried out to calculus of differences and get final product to obtain HRV HRV; Use FFT that pulse signal is converted to frequency field, and calculate pulse power spectrum energy Ratios r, formula is

$r=\frac{\underset{k=k_1}{\overset{k_2}{\mathrm{\Σ}}}{\left|X\left(k\right)\right|}^2}{\underset{k=k_3}{\overset{k_4}{\mathrm{\Σ}}}{\left|X\left(k\right)\right|}^2}$

Observed reading when X in formula (k) expression pulse signal frequency is k, k1, k2, k3, k4 represent specific frequency values.Finally, pulse information is carried out to mode Energy Decomposition, calculate pulse mode Energy-Entropy, formula is:

$T_{(i-j)/(h-k)}=\frac{\underset{x=i}{\overset{j}{\mathrm{\Σ}}}T\left(x\right)}{\underset{x=h}{\overset{k}{\mathrm{\Σ}}}T\left(x\right)}$

T in formula (x) is the mode energy after the normalization of k natural mode of vibration component of pulse signal, and i, j, k, h represent the sequence number of natural mode of vibration component;

B) fatigue state characteristic parameter, for facial information, in the time obtaining piece image, determine the position of human eye in conjunction with template matches and mixing integration sciagraphy, use mean-shift algorithm to cut apart pupil part, continue to use mean-shift algorithm to follow the trail of pupil position in ensuing image, thereby obtain the continuous pupil image information of some width in a period of time, and then can calculate PERCLOS, frequency of wink and average three parameters of pupil size, in order to carry out fatigue state identification; Wherein PERCLOS refers to the shared ratio of eyes closed within a certain period of time, and computing formula is:

$f=\frac{t_3-t_2}{t_4-t_1}\×100\%$

T in formula ₁, t ₂, t ₃, t ₄be illustrated respectively in the eye movement cycle, eyes aperture is 80%, 20%, 20% and 80% time point; Frequency of wink refers within the unit interval, and eyes aperture is less than 10% picture number n and the ratio of time span t.Average pupil size referred in a period of time, the mean value of the upper and lower Distances Between Neighboring Edge Points of pupil in each image; For pulse information, first replace heart rate so that pulse frequency is approximate, and then definite HRV parameter, and can be than carrying out fatigue state identification with mode Energy-Entropy in conjunction with pulse spectrum;

C) identity information characteristic parameter, for facial information, first determine the position of human eye in conjunction with template matches and mixed integral projection method, determine accurate human face region according to position of human eye and facial statistical law and characteristics of image, and then facial image is used to PCA algorithm classification major component vector, in order to carry out identity information identification; Because the identity information comprising in the middle of pulse information is less, therefore pulse information does not participate in the identification of identity information.

(3) information fusion and pattern-recognition, uses intelligent algorithm, and each category feature parameter is carried out to fusion treatment, and realizes the accurate monitoring to corresponding state, is specially:

A) angry mood monitoring, using the angry emotional characteristics parameter of extracting in step (2) as input quantity, uses Fisher linear classifier by its fusion treatment, and the process of classification has realized the monitoring to angry mood;

B) fatigue state monitoring, using the fatigue state characteristic parameter extracting in step (2) as input quantity, uses SVM algorithm by its fusion treatment, and the process of classification has realized the monitoring to fatigue state;

C) identity information monitoring, using the identity information characteristic parameter extracting in step (2) as input quantity, uses Fisher linear classifier by its fusion treatment, and the process of classification has realized the monitoring to identity information;

Step 3: condition responsive;

(1) in the time monitoring driver and occur angry mood or fatigue state, feed back to driver by the mode of playing alarm, thereby proofread and correct driver's bad steering state, ensure driving safety;

(2) when monitoring driver's identity information when wrong, preserve driver's face-image now by a memory storage with access rights, wait until supvr and make regular check on processing, thereby stop arbitrarily to take over other's shift phenomenon, ensure driving safety.

By reference to the accompanying drawings the specific embodiment of the present invention is described although above-mentioned; but not limiting the scope of the invention; one of ordinary skill in the art should be understood that; on the basis of technical scheme of the present invention, those skilled in the art do not need to pay various amendments that creative work can make or distortion still in protection scope of the present invention.

Claims (5)

1. the polynary driving safety means of defence of automobile, is characterized in that, mainly realizes as follows:

Step (1): gather driver's facial information and pulse information by two CMOS cameras and the wireless pulse transducer of Wrist belt-type respectively, and carry out respectively filtering operation to eliminate the interference of noise;

Step (2): in facial information and pulse information, by the empirical mode decomposition algorithm based on information entropy, extract respectively the characteristic parameter that can reflect human body indignation mood, fatigue state and identity information;

Step (3): by Fisher linear classification scheduling algorithm, the corresponding characteristic parameter of various states extracting in step (2) is carried out to fusion treatment, and realize the identification of angry mood, fatigue state and the identity information to driver simultaneously;

Step (4): according to the result of step (3) state recognition, take the mode of alarm or backstage record to respond driver.

2. the polynary driving safety means of defence of automobile according to claim 1, it is characterized in that, in described step (1), by two CMOS camera collection drivers' facial information, the camera that is wherein arranged on A post position is responsible for the head position location to driver, the camera that is arranged on windshield upper limb is responsible for gathering driver's face-image, and the position of this camera and shooting angle can be finely tuned; The pulse information that gathers driver by Wrist belt-type pulse transducer, the pulse information collecting outwards transmits in blue teeth wireless mode.

3. the polynary driving safety means of defence of automobile according to claim 1, it is characterized in that, in described step (2), from facial image information and pulse information, extract respectively one or more in angry emotional characteristics parameter, fatigue state characteristic parameter and identity characteristic parameter, be specially:

1) angry emotional characteristics parameter,

For facial information, first determine the position of human eye by mixing integration sciagraphy, mixing integration projection formula is:

$H_v\left(x\right)=\frac{1}{2}{{\mathrm{\σ}}_v}^2\left(x\right)+\frac{1}{2}{M}_v\left(x\right),H_h\left(y\right)=\frac{1}{2}{{\mathrm{\σ}}_h}^2\left(y\right)+\frac{1}{2}{M}_h\left(y\right)$

H in formula _vand H (x) _h(y) hybrid projection of difference presentation video in vertical and horizontal direction, M _vand M (x) _h(y) be illustrated in the average integral projection in vertical and horizontal direction, σ _vand σ (x) _h(y) be illustrated in the variance integral projection in vertical and horizontal direction; Determine accurate human face region according to the feature of the statistical law relation between position of human eye and face contour and image itself, and then use Principal Component Analysis Algorithm (PCA) to extract major component vector, major component Z to facial image _icomputing formula be:

Z _i＝(X ₁,X ₂,X ₃,…,X _p)*(L ₁,L ₂,L ₃,…,L _p) ^T

X in formula _i(i=1,2 ..., p) each column vector of presentation video matrix X, L _i(i=1,2 ..., p) each column vector of expression major component loading matrix L, with Z _ifor characteristic quantity carries out angry Emotion identification;

For pulse information, in the time obtaining one section of continuous pulse signal, to use method of characteristic point to determine main ripple position, and then obtain pulse frequency and pulse frequency average, the computing formula of pulse frequency is

$h=\frac{60}{\▿t}$

In formula, ▽ t represents the mistiming of adjacent two main ripples, h is carried out to calculus of differences and get final product to obtain HRV HRV; Use FFT that pulse signal is converted to frequency field, and calculate pulse power spectrum energy Ratios r, formula is

$r=\frac{\underset{k=k_1}{\overset{k_2}{\mathrm{\Σ}}}{\left|X\left(k\right)\right|}^2}{\underset{k=k_3}{\overset{k_4}{\mathrm{\Σ}}}{\left|X\left(k\right)\right|}^2}$

Observed reading when X in formula (k) expression pulse signal frequency is k, k1, k2, k3, k4 represent specific frequency values; Finally, pulse information is carried out to mode Energy Decomposition, calculate pulse mode Energy-Entropy, formula is:

$T_{(i-j)/(h-k)}=\frac{\underset{x=i}{\overset{j}{\mathrm{\Σ}}}T\left(x\right)}{\underset{x=h}{\overset{k}{\mathrm{\Σ}}}T\left(x\right)}$

T in formula (x) is the mode energy after the normalization of k natural mode of vibration component of pulse signal, and i, j, k, h represent the sequence number of natural mode of vibration component;

2) fatigue state characteristic parameter,

For facial information, in the time obtaining piece image, determine the position of human eye by mixing integration sciagraphy, use mean-shift algorithm to cut apart pupil part, the computing formula of mean-shift is:

$M_h\left(x\right)\≡\frac{\underset{i=1}{\overset{n}{\mathrm{\Σ}}}G\left(\frac{x_i-x}{h}\right)w\left(x_i\right)(x_i-x)}{\underset{i=1}{\overset{n}{\mathrm{\Σ}}}G\left(\frac{x_i-x}{h}\right)w\left(x_i\right)}$

M in formula _h(x) the mean-shift value of expression sample, x _ifor sample point, point centered by x, G (y) represents kernel function, h represents the window size of kernel function, w (x _i) be sample point x _iweight; Continue to use mean-shift algorithm to follow the trail of pupil position in ensuing image, thereby obtain the continuous pupil image information of some width in a period of time, and then can calculate PERCLOS, frequency of wink and average three parameters of pupil size, in order to carry out fatigue state identification; Wherein PERCLOS refers to the shared ratio of eyes closed within a certain period of time, and computing formula is:

$f=\frac{t_3-t_2}{t_4-t_1}\×100\%$

T in formula ₁, t ₂, t ₃, t ₄be illustrated respectively in the eye movement cycle, eyes aperture is 80%, 20%, 20% and 80% time point; Frequency of wink s refers to the number of times of blinking within the unit interval, and formula is

$s=\frac{n}{\mathrm{\Δt}}$

In formula, n is the picture number that eyes aperture is less than 10%, and Δ t is the time interval; The computing formula of average pupil size q is:

$q=\frac{1}{n}\mathrm{\Σ}{l}_i$

L in formula _irepresent the spacing of lower limb on pupil, n is interior during this period of time pupil image number; For pulse information, first replace heart rate so that pulse frequency is approximate, and then definite HRV parameter, and can be than carrying out fatigue state identification with mode Energy-Entropy in conjunction with pulse spectrum;

3) identity information characteristic parameter, for facial information, first determine the position of human eye by mixing integration sciagraphy, determine accurate human face region according to position of human eye and facial statistical law and characteristics of image, and then facial image is used to PCA algorithm classification major component vector, in order to carry out identity information identification.

4. the polynary driving safety means of defence of automobile according to claim 1, is characterized in that, in described step (3), information fusion and pattern-recognition refer to passes through intelligent algorithm, each category feature parameter is carried out to fusion treatment, and realizes the accurate monitoring to corresponding state, be specially:

1) angry mood monitoring, using 5 seconds as the time interval, by the facial information gathering in every 5 seconds and pulse information in order to execution step (2), extract angry emotional characteristics parameter, using the angry emotional characteristics parameter of extracting in step (2) as input quantity, use Fisher linear classifier by its fusion treatment, the process of classification has realized the monitoring to angry mood, judge that if double driver is for angry mood, assert that the current mood of driver is for indignation;

2) fatigue state monitoring, using 1 minute as the time interval, by the facial information gathering in each minute and pulse information in order to execution step (2), extract fatigue state characteristic parameter, using the fatigue state characteristic parameter extracting in step (2) as input quantity, use SVM algorithm by its fusion treatment, the process of classification has realized the monitoring to fatigue state, judge that if double driver, for fatigue state, assert the current fatigue state that entered of driver;

3) identity information monitoring, using 5 minutes as the time interval, by the facial information gathering in every 5 minutes and pulse information in order to execution step (2), extract identity characteristic parameter, using the identity information characteristic parameter extracting in step (2) as input quantity, use Fisher linear classifier by its fusion treatment, the process of classification has realized the monitoring to identity information, if double judgement driver's identity information is not inconsistent, assert that current driver is not the driver who specifies.

5. the polynary driving safety means of defence of automobile according to claim 1, it is characterized in that, in described step (4), the specific implementation of feedback measure is: in the time monitoring driver and occur fatigue state or angry mood, feed back to driver by the mode of playing alarm sound, thereby proofread and correct driver's bad steering state, ensure driving safety; When monitoring driver's identity information when wrong, preserve driver's face-image now by a memory storage with access rights, wait until supvr and make regular check on processing, thereby stop arbitrarily to take over other's shift phenomenon, ensure driving safety.