CN106530623A - Fatigue driving detection device and method - Google Patents
Fatigue driving detection device and method Download PDFInfo
- Publication number
- CN106530623A CN106530623A CN201611264042.1A CN201611264042A CN106530623A CN 106530623 A CN106530623 A CN 106530623A CN 201611264042 A CN201611264042 A CN 201611264042A CN 106530623 A CN106530623 A CN 106530623A
- Authority
- CN
- China
- Prior art keywords
- image
- driver
- state
- face
- fatigue
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/06—Alarms for ensuring the safety of persons indicating a condition of sleep, e.g. anti-dozing alarms
Abstract
The invention discloses a fatigue driving detection device and a fatigue driving detection method. The fatigue driving detection device comprises ARM (Advanced RISC Machines) processor equipment, a SD (Secure Digital) card, a USB (Universal Serial Bus) camera, a data line, a heat dissipation fan and an alarming device, wherein the ARM processor equipment further comprises a human face positioning module, a human eye state identification module and a fatigue judging module; the fatigue driving detection device method comprises the following steps: 1, initializing the camera; 2, acquiring an image and transmitting image information to the ARM processor equipment; 3, pre-processing the image; 4, positioning a human face region through a human face characteristic classifier, and positioning a human eye region 5 through a human eye characteristic classifier; 5, detecting the face of a driver to judge whether the driver is at a fatigue state or not; 6, detecting eyes of the driver to judge whether the driver is at the fatigue state or not; and 7, comprehensively judging whether the driver is at the fatigue state or not and starting corresponding alarming. According to the fatigue driving detection device and method disclosed by the invention, pupil and edge regions can be divided very well through adopting an eye region image binaryzation processing method; and compared with detection of a single method, the identification accuracy is higher.
Description
Technical field
The invention belongs to vehicle security drive technical field, belongs to the technologies such as image procossing, pattern recognition, neutral net neck
Domain, particularly a kind of fatigue driving detecting system.
Background technology
With the fast development of social economy, while transportation develops, the quantity of automobile is also increasingly to come many,
More and more multiple trend is presented by vehicle accident caused by fatigue driving.For this phenomenon, generate various tired
Please detection technique is sailed, contact measurement and non-contact detection is broadly divided into.Contact measurement usually measures driver's
Electrocardiogram, electroencephalogram etc., this metering system can not only hinder the driver behavior of driver, and high cost.When driver it is tired
Lao Shi, can show to bow, the physiological feature such as eye closing frequency increases, and non-contact detection technology is exactly by supervising device detection
These physiological features of driver.The characteristics of contactless fatigue-driving detection technology has low cost, degree of accuracy is high, therefore,
It is widely adopted in current fatigue driving detection device.
The currently existing contactless fatigue detection device based on physiological driver's feature, passes through image procossing skill mostly
Art, locating human face, then the state of eyes is analyzed in the range of face, judge whether fatigue.Chinese invention patent
CN101593425A and CN201681470U disclose a kind of method for detecting fatigue driving, and are by single detection people
The state of eye is judging the fatigue state of people, although this single detection mode can have certain accurate in fatigue detecting
Property, but easily affected to cause to survey by mistake by illumination, the factor such as whether wear glasses.Wherein patent of invention CN101593425A is adopted
Maximum variance between clusters, easily affected by eyelash people, be unfavorable for iris segmentation.
The content of the invention
It is an object of the invention to provide a kind of fatigue driving detection device and detection method, by face state and people
The comprehensive descision result of eye state, carries out final judgement to the fatigue state of driver, can realize that different warnings are corresponding
In mode, and the present invention, ocular image binaryzation processes adaptive approach used and can preferably be partitioned into iris area
Domain.
The technical solution for realizing the object of the invention is：
A kind of fatigue driving detection device, including for depositing the SD card of embedded system, for gathering driver front
The USB camera of image, the data wire powered for equipment, the alarm device for pointing out driver, radiate for processor
Radiator fan；Also include：For image procossing and the fatigue arm processor equipment for judging and the report for carrying out different type of alarms
Alarm device；The alarm device is included can carry out different warning sides according to the Different Results of comprehensive descision driver fatigue state
Loudspeaker alarm device and LED lamp alarm device that formula is reported to the police；
The arm processor equipment includes Face detection module, human eye state identification module, tired determination module；Face
After locating module receives pictorial information, face state is recognized with Adaboost algorithm locating human face and by coordinate difference；Human eye
State recognition module obtains the human face region image in Face detection module, positions human eye area with Adaboost algorithm, passes through
The integral projection identification human eye state of image is processed using eye self-adaption binaryzation；Tired determination module according to face state with
Human eye state carries out tired judgement, then will determine that result is converted to the signal of telecommunication, is conveyed to alarm device by I/O interfaces.
The Face detection module, human eye state identification module, tired determination module are specific as follows：
Face detection module：With the face characteristic grader locating human face region for training, and calculate face center position
Put the deviation value in longitudinal direction with image center, according to the vibration frequency of face center in the time of deviation oscillation and setting come
Judge driver whether in fatigue state；
Human eye state identification module：Behind locating human face region, according to the face distribution proportion of people, by 3/5, face top
It is allocated as region interested, the human eye grader positioning human eye area that use is trained；Feature is carried out to the eye of driver to carry
Take, calculate the width of the maximum and integral domain of the vertically and horizontally integral projection of the image of ocular binary conversion treatment respectively
Degree ratio, with reference to two ratios, synthetic determination goes out the current state of human eye, i.e. human eye closure situation, and sentencing by setting
Fix, whether tired carry out the current mental status of driver；
Tired determination module：According to face state and the judged result of human eye state, the mental status of driver is carried out
Final judgement；
A kind of method for detecting fatigue driving, comprises the steps：
Step 1, initializes photographic head, arranges the property value that photographic head reads in picture；
Image information is conveyed to arm processor equipment by step 2, USB camera collection image；
Step 3, Image semantic classification, i.e. image down, gray processing process；
Step 4, existing face and human eye feature grader in loading OpenCV machine vision storehouse, by training in advance
Face characteristic grader locating human face region；
Step 5, judges fatigue state by face state：Detect that using Adaboost algorithm the face of driver has position
Put, calculate the deviation value of face center position and image center in longitudinal direction, compared with given threshold according to deviation value and one
Fix time the vibration frequency of interior face center, that is, whether frequency of nodding is judging driver in fatigue state；
Step 6, judges fatigue state by human eye state：Detect that using Adaboost algorithm the eye of driver has position
Put, feature extraction is carried out to the eye of driver, calculate the width of the maximum and integral domain of the integral projection of ocular
Ratio, and compare to judge driver whether in fatigue state with given threshold T1；
Step 7, according to step 5,6 tired synthetic determination result, it is determined that returning image acquisition or starting different warning sides
One kind of formula.
The present invention compared with prior art, its remarkable advantage：
(1) present invention adopts embedded system, and small volume is easy to use；(2) individual sex differernce is reduced to testing result
Impact, improve fatigue judgement accuracy, with preferable practicality；(3) by the head with reference to people and human eye two
Marked feature carries out compound judgement, is identified detection than single method, and recognition accuracy is higher；(4) ocular image two
Value processes adaptive approach used and can preferably be partitioned into pupil and marginal area, is difficult to be affected by ciliary；(5)
Differentiated by the mental status to driver, start when alarm device reminds driver under fatigue state and stopped not
Breath, can effectively reduce the generation of vehicle accident, and the security of the lives and property for the people provides powerful guarantee.
Below in conjunction with the accompanying drawings the present invention is described in further detail.
Description of the drawings
Fig. 1 is fatigue driving detection device structural representation.
Fig. 2 is arm processor device interior connection diagram.
Fig. 3 is method for detecting fatigue driving FB(flow block).
Fig. 4 is the vertical integral projection figure of the image of eye binary conversion treatment.
Fig. 5 is the horizontal integral projection figure of the image of eye binary conversion treatment.
Fig. 6 is PERCLOS measuring principle figures.
Fig. 7 is eyes image.
Fig. 8 is the image that the self-adaption binaryzation of eyes image is processed.
Specific embodiment
With reference to Fig. 1, a kind of fatigue driving detection device, including for deposit embedded system SD card, for collection drive
The USB camera of the person's of sailing direct picture, the data wire powered for equipment, the alarm device for pointing out driver, for locating
The radiator fan of reason device radiating；Also include：For image procossing and fatigue judge arm processor equipment and carry out different warnings
The alarm device of mode；The alarm device is included and can be carried out not according to the Different Results of comprehensive descision driver fatigue state
The loudspeaker alarm device reported to the police with type of alarm and LED lamp alarm device；
The arm processor equipment includes Face detection module, human eye state identification module, tired determination module；Face
After locating module receives pictorial information, face state is recognized with Adaboost algorithm locating human face and by coordinate difference；Human eye
State recognition module obtains the human face region image in Face detection module, positions human eye area with Adaboost algorithm, passes through
The integral projection identification human eye state of image is processed using eye self-adaption binaryzation；Tired determination module according to face state with
Human eye state carries out tired judgement, then will determine that result is converted to the signal of telecommunication, is conveyed to alarm device by I/O interfaces.
The Face detection module, human eye state identification module, tired determination module are specific as follows：
Face detection module：With the face characteristic grader locating human face region for training, and calculate face center position
Put the deviation value in longitudinal direction with image center, according to the vibration frequency of face center in the time of deviation oscillation and setting come
Judge driver whether in fatigue state；
Human eye state identification module：Behind locating human face region, according to the face distribution proportion of people, by 3/5, face top
It is allocated as region interested, the human eye grader positioning human eye area that use is trained；Feature is carried out to the eye of driver to carry
Take, calculate the width of the maximum and integral domain of the vertically and horizontally integral projection of the image of ocular binary conversion treatment respectively
Degree ratio, with reference to two ratios, synthetic determination goes out the current state of human eye, i.e. human eye closure situation, and sentencing by setting
Fix, whether tired carry out the current mental status of driver；
Tired determination module：According to face state and the judged result of human eye state, the mental status of driver is carried out
Final judgement；
The arm processor equipment includes as shown in Figure 2：Power-switching circuit, usb circuit, crystal oscillating circuit, enable
Signal circuit, SD card reading circuit；
Wherein, power-switching circuit part, first USB power supply circuits realize that power supply interface is changed, by three poles of NXP types
Pipe obtains 5V voltages, and one resettable fuse of middle concatenation makes device have the function of voltage protection, and then USB powers electricity
The output connection mu balanced circuit on road, mu balanced circuit are converted to three kinds of different burning voltages by steady chip；The work of ARM chips
With comprising image procossing and fatigue judgement；Usb circuit is connected with LAN9512 chips, is carried out data transmission, and is received USB and is taken the photograph
As the video information of head is incoming, information is passed in ARM chip processors through Video Decoder；Crystal oscillating circuit passes through crystal
Agitator produces clock signal, provides sequential for processor；Enable signal circuit and pass through 5V input voltages and field-effect transistor
Two kinds of signals being produced, signal and the RUN signals needed for ARM chips being enabled for provide SDRAM, SDRAM provides fortune for system
Row space, while the compression image information of the 3-5 minutes of the nearest collection of storage；LED state display lamp is shown for equipment state；
SD card reading circuit is read into the linux system in SD card in equipment, makes equipment have running environment, and realizes the reading of data
Enter and storage；HDMI is screen display spare interface；I/O interfaces provide the trigger of alarm device.
Video stream information is converted into digital information by change-over circuit and device by USB camera, and ARM chips are used as main place
Reason unit, starts Face detection module, carries out Face detection and state analysiss, and the image information after process is temporarily stored in
In SDRAM, eye recognition module obtains the image information after face recognition module is processed from SDRAM, carries out human eye state knowledge
Not, then tired determination module carries out tired judgement according to the state outcome of Face detection module and human eye state identification module,
Most result of determination is converted into the signal of telecommunication and sends alarm device to from I/O interfaces at last.
With reference to Fig. 3-5, the detection method of the fatigue driving detection device is comprised the steps of：
Step 1, initializes photographic head, arranges the property value that photographic head reads in picture, and the image resolution ratio that will be read in sets
It is set to 640 × 480；
Image information is conveyed to ARM flush bonding processors by step 2, USB camera collection image；
Step 3, Image semantic classification, i.e. image down, gray processing process；
Used as a kind of preferred scheme, image downscaling method is specially：By image down 1/2, the method for employing is local
Averaging method, preferably retains original image information while picture size is reduced, and the image after diminution can reduce operand,
Improve real-time.
Step 4, existing face and human eye feature grader in loading OpenCV machine vision storehouse, by training in advance
Face characteristic grader locating human face region, i.e., obtain face key feature points with Harr feature detection modes, according to feature
Point location human face region, and respectively obtain human face region upper left angle point and bottom right angular coordinate (x1,y1)、(x2,y2), calculate people
Center point coordinate (the H of face area imagex,Hy), whereinAccording to (x1,y1)、(x2,y2) two
Point coordinates rectangle frame outlines human face region；
Step 5, judges fatigue state by face state：The face position of driver is detected using Adaboost algorithm
Put, image acquisition is returned if face is not detected by, if after collecting face, calculating human face region image center position (Hx,
Hy) the image center position (I that arrives with initial acquisitionx,Iy) in the deviation value Diff of longitudinal direction, in unit period (10 seconds), system
Amount of images and total number of images amount of the meter deviation value Diff more than given threshold T1 (initial to read in the 1/4 of picture altitude value), meter
Calculate the vibration frequency of face center, that is, frequency of nodding is judging driver whether in fatigue state；
Judge that fatigue state is specifically comprised the steps of by face state：
5.1, after obtaining the center position of human face region, calculate the vertical coordinate H of face centeryWith the vertical coordinate of image
IyDifference Diff=| Hy-Iy|；
5.2, amount of images n and image totalframes of statistical unit cycle (10 seconds) interior difference Diff more than given threshold T1
N；
5.3, the ratio of amount of images n and image totalframes N is calculated, ratio is compared with given threshold T, if ratio
Threshold value T dry greatly, then judge that driver is in fatigue state；Threshold value T is sized to 0.68, by experiment gained.
Step 6, judges fatigue state by human eye state：Detect that using Adaboost algorithm the eye of driver has position
Put, image acquisition is returned if human eye is not detected by, if after collecting human eye, carrying out feature extraction to the eye of driver, meter
Calculate the width ratio of the maximum and integral domain of the integral projection of the image of ocular binary conversion treatment, and and given threshold
T2 compares, if being more than threshold value T2, judges that the eyes of driver are to close, and unit of account cycle (10 seconds) driver closes one's eyes and schemes
As quantity and the ratio of total amount of images, if ratio is more than given threshold T, judge that driver is in fatigue state；Threshold value T2
According to experiment gained, in the present invention, value is 2.0 to value.
Fatigue state is judged by human eye state：It is concrete to include step in detail below：
6.1 position human eye by human eye feature grader in human face region；
Human eye area, position fixing process and people are positioned by the human eye feature grader of training in advance in human face region image
Face zone location is identical, and the feature classifiers for simply loading are different；Calculate the center point coordinate of human eye area image, calculating process
As human face region picture centre point coordinates is calculated, judge human eye central point to the rectangle frame lower boundary in locating human face region
Whether distance meets normal organ distribution proportion with the ratio of rectangle frame height, if judging, error is larger, may detection
To eyebrow, detection is re-started.
6.2 pairs of ocular images carry out gaussian filtering, remove noise, using adaptive binary conversion treatment；
For different threshold values, the image that binary conversion treatment is obtained is different, and the present invention is carried out using adaptive threshold
Image binaryzation process, can preferably be partitioned into pupil region, that is, set minimum threshold low and max-thresholds high, image
Used by binary conversion treatment, threshold tau is gradually incremented by using numerical values recited as 0.05 as step-length, to the continuous two-value again of same piece image
Change is processed, and obtains the image of a series of binary conversion treatment, therefrom finds out the minimum image of non-zero connected domain quantity as to be checked
Altimetric image.The self-adaption binaryzation adopted by step 6.2 is processed, and specific method is：
6.2.1., minimum threshold low=0.1 (0.1 times of image minimum gradation value), max-thresholds high=0.5 are set
(0.5 times of image maximum gradation value), threshold tau incremental steps step=0.05；
6.2.2. by imgs=binary (I, τ) constantly to the process of ocular image binaryzation；
6.2.3. find after the process of non-zero connected region minimum number from a series of image imgs of binary conversion treatment
Image img1 and corresponding threshold tau；
6.2.4. opening operation is carried out to the image img1 of the binary conversion treatment of non-zero connected region minimum number and endoporus is filled out
Fill；
6.2.5 the largest connected domain looked in the image img1 of binary conversion treatment, and other connected domains are removed, obtain final
The image img of binary conversion treatment；
Wherein, imgs represents the image of binary conversion treatment, and bianry represents binary conversion treatment process, and I represents ocular
Image, τ are the binary-state thresholds being progressively incremented by from minimum threshold low by step 6.2.1；Imgs=binary (I, τ) is this
The representation that bright image binaryzation is processed.
The integral projection of the 6.3 image img for calculating binary conversion treatment, the maximum for calculating vertical integral projection are wide with integration
The maximum of ratio r ate1 of degree and horizontal integral projection and ratio r ate2 of integral breadth；
Wherein, the formula that the calculating of vertical integral projection is adopted：
The formula that the calculating of horizontal integral projection is adopted：
As shown in Figure 3, from SvThe maximum V of vertical integral projection is found out in (x)max, from ShLevel integration is found out in (x)
The maximum H of projectionmax, the peak width V of vertical integral projection and horizontal integral projection is calculated respectivelywidth、Hwidth, then
Calculate：
Rate1=Vmax/Vwidth；
Rate2=Hmax/Hwidth；
Wherein, SvX () is the pixel value sum corresponding to the unit width of the image img after binary conversion treatment, ShX () is
Pixel value sum corresponding to the unit height of the image img of binary conversion treatment, Y1=1, Y2Equal to the height of ocular image
Degree, X1=1, X2Equal to the width of ocular image, I (x, y) is that (x, y) is corresponding in ocular binary conversion treatment image
Pixel value, (x, y) are binary conversion treatment image coordinate value, and rate1, rate2 represent vertical integral projection maximum respectively and hang down
The ratio of the ratio of direct integral view field width, horizontal integral projection maximum and horizontal integral projection peak width；
6.4 combine rate1 and rate2, calculateJudge driver whether in tired shape
State；The value of rate is compared with given threshold T2, the opening and closing state of human eye is judged, the even value of rate is more than T2, represents
When the closure degree of human eye reaches 80%, it is regarded as currently closing one's eyes completely；The size of threshold value T2 is by normal to driver
The collection of eyes image data during driving, that is, gather image during different driver's normal drivings in 10 minutes, according to above-mentioned step
Suddenly a series of rate values are calculated, and final value T2 is obtained by way of averaging.
Wherein, rate represents vertical and horizontal integral projection depth-width ratio example relation integrated value,Be rate1 and
The weight coefficient of rate2,WithValue take 0.4 and 0.6 in the present invention respectively, value size is by experiment gained；It is comprehensive
Consider upright projection and floor projection, one is to prevent one direction integral projection parameter from judging that two are with one-sidedness for fatigue
Advantageously close or open in differentiation eyes.
6.5 carry out tired judgement using the P80 methods of PERCLOS, by counting in the unit period for setting (10 seconds), eye
Eyeball closing time accounts for the percentage ratio of overall time, if ratio has exceeded threshold value T set in advance, that is, has been regarded as current drivers
In fatigue driving；
The P80 methods of PERCLOS are described further with reference to Fig. 6：
PERCLOS has three kinds of standards in the application：P70, P80 and EM, represent that eyes closed degree is 70%, 80% respectively
With 50%.Experiment proves P80 standards effect preferably, therefore, the present invention is passed judgment on to degree of fatigue using the criterion of P80.t1
For people's emmetropia state when initial time, i.e. human eye stretching degree is 80% moment；T2 is human eye in closing course, people
Eye stretching degree is 20% moment；T3 is that human eye stretching degree reaches 20% during human eye is opened after closing completely again
Moment；T4 completes the process that once blink for human eye, returns to moment during normal open configuration；
When t1, t2, t3 is obtained, value f of PERCLOS after t4, is calculated：
F is the percentage rate that the eyes closed time accounts for setting time section；
Statistics is interior in unit period (10 seconds), the number of image frames and image totalframes of eyes closed, the value of the PERCLOS
F is equal to：
In the present invention, if the value of f is more than T, judge that driver is in fatigue state.
Step 7, according to step 5,6 tired synthetic determination result, if it is determined that fatigue does not then return image acquisition, if it is determined that
It is tired then start alarm device.
By step 5 and step 6 synthetic determination result, start corresponding type of alarm：
When step 5 judges that driver is in fatigue state, then start LED lamp alarm device and report to the police；
When step 6 judges that driver is in fatigue state, then start loudspeaker alarm device and report to the police；
When step 5, step 6 judge that driver in fatigue state, then starts LED lamp alarm device and loudspeaker report simultaneously
Alarm device is reported to the police.
Fig. 7,8 be respectively the image that ocular image and self-adaption binaryzation are processed design sketch, binary conversion treatment side
Method is that optimal threshold is found from a series of threshold values, i.e., can make the quantity of the non-zero connected domain of the image of eye binary conversion treatment
At least, endoporus filling is then carried out, largest connected domain is found, the largest connected domain is exactly part to be partitioned into.People's eye pupil
Bore region preferably can be divided out, and not be subject to ciliary impact, the figure of the binary conversion treatment for finally giving
As playing good effect for the follow-up integral projection that calculates.
The fatigue driving detection device of the present invention, appearance design are simple, and small volume is easily installed on automobile.During use,
Image collecting device is preferably mounted on windshield, the roof of the left anterior-superior part or front upper right of position of driver
On, it is also possible to image collecting device is placed in into instrument panel center, the positive image of driver can be captured through steering wheel.Image
Before process and alarm device can be fixed on windshield, it is that alarm device is powered with vehicle-mounted USB charger.
Claims (10)
1. a kind of fatigue driving detection device, including for depositing the SD card of embedded system, for gathering driver's front elevation
The USB camera of picture, the data wire powered for equipment, the alarm device for pointing out driver, for processor radiating
Radiator fan；Characterized in that, also including：For image procossing and fatigue judge arm processor equipment and carry out different reports
The alarm device of police's formula；The alarm device is included and can be carried out according to the Different Results of comprehensive descision driver fatigue state
Loudspeaker alarm device and LED lamp alarm device that different type of alarms are reported to the police；
The arm processor equipment includes Face detection module, human eye state identification module, tired determination module；Face detection
After module receives pictorial information, face state is recognized with Adaboost algorithm locating human face and by coordinate difference；Human eye state
Identification module obtains the human face region image in Face detection module, positions human eye area with Adaboost algorithm, by using
Eye self-adaption binaryzation processes the integral projection identification human eye state of image；Tired determination module is according to face state and human eye
State carries out tired judgement, then will determine that result is converted to the signal of telecommunication, is conveyed to alarm device by I/O interfaces；
The Face detection module, human eye state identification module, tired determination module are specific as follows：
Face detection module：With the face characteristic grader locating human face region for training, and calculate face center position with
Image center is judged according to the vibration frequency of face center in the time of deviation oscillation and setting in the deviation value of longitudinal direction
Whether driver is in fatigue state；
Human eye state identification module：Behind locating human face region, according to the face distribution proportion of people, 3/5 part of face top is made
For region interested, human eye area is positioned with the human eye grader for training；Feature extraction is carried out to the eye of driver, point
Not Ji Suan ocular binary conversion treatment image vertically and horizontally integral projection maximum and integral domain width ratio
Value, with reference to two ratios, synthetic determination goes out the current state of human eye, i.e. human eye closure situation, and accurate by the judgement for setting
It is then whether tired to carry out the current mental status of driver；
Tired determination module：According to face state and the judged result of human eye state, the mental status of driver is carried out finally
Judgement.
2. a kind of fatigue driving detection device as claimed in claim 1, it is characterised in that the arm processor equipment includes：
Power-switching circuit, usb circuit, crystal oscillating circuit, enable signal circuit, SD card reading circuit；
Power-switching circuit part, first USB power supply circuits realize that power supply interface is changed, and obtain 5V by the audion of NXP types
Voltage, one resettable fuse of middle concatenation, the then output of USB power supply circuits connect mu balanced circuit, and mu balanced circuit passes through
Steady chip is converted to three kinds of different burning voltages；The effect of ARM chips includes image procossing and fatigue judgement；USB interface
Circuit is connected with LAN9512 chips, is carried out data transmission, and the video information for receiving USB camera is incoming, through Video Decoder
Information is passed in ARM chip processors；Crystal oscillating circuit produces clock signal by crystal oscillator, when providing for processor
Sequence；Enable signal circuit and pass through 5V input voltages and field-effect transistor two kinds of signals of generation, the enable for providing SDRAM is believed
Number and ARM chips needed for RUN signals, SDRAM provides running space for system, while storage 3-5 minutes of collection recently
Compression image information；LED state display lamp is shown for equipment state；Linux system in SD card is read by SD card reading circuit
Enter in equipment, make equipment that there is running environment, and realize the reading and storage of data；HDMI is screen display spare interface；
I/O interfaces provide the trigger of alarm device；
Video stream information is converted into digital information by change-over circuit and device by USB camera, and ARM chips are used as main process task list
Unit, starts Face detection module, carries out Face detection and state analysiss, and the image information after process is temporarily stored in SDRAM,
Eye recognition module obtains the image information after face recognition module is processed from SDRAM, carries out human eye state identification, then tired
Labor determination module carries out tired judgement according to the state outcome of Face detection module and human eye state identification module, most judges at last
As a result be converted into the signal of telecommunication alarm device is sent to from I/O interfaces.
3. a kind of fatigue driving detection device as claimed in claim 1, it is characterised in that under the Face detection module passes through
Whether state step realizes passing judgment on driver in fatigue state：
3.1 face locations that driver is detected using Adaboost algorithm, obtain the center position (H of human face regionx,Hy)
Image center position (the I arrived with initial acquisitionx,Iy) in the deviation value Diff of longitudinal direction；
After 3.2 center positions for obtaining human face region, the vertical coordinate H of face center is calculatedyWith the vertical coordinate I of imageyDifference
Value Diff=| Hy-Iy|；
Amount of images n and image totalframes N of difference Diff more than given threshold T1 in 3.3 statistical unit cycles；
3.4 ratios for calculating amount of images n and image totalframes N, ratio are compared with given threshold T, if ratio is done greatly
Threshold value T, then judge that driver is in fatigue state.
4. a kind of fatigue driving detection device as claimed in claim 1, it is characterised in that the human eye state identification module leads to
Whether cross following step realizes passing judgment on driver in fatigue state：
The 4.1 eye existence positions that driver is detected using Adaboost algorithm, pass through human eye feature grader in human face region
Positioning human eye；
4.2 pairs of ocular images carry out gaussian filtering, remove noise, using adaptive binary conversion treatment；
The integral projection of the image img after 4.3 calculating eye binary conversion treatment, calculates the maximum and integration of vertical integral projection
The maximum of ratio r ate1 of width and horizontal integral projection and ratio r ate2 of integral breadth；
Wherein, the formula that the calculating of vertical integral projection is adopted：
The formula that the calculating of horizontal integral projection is adopted：
The maximum V of vertical integral projection and horizontal integral projection is found out respectivelymax、Hmax, vertical integral projection is calculated respectively
With the peak width V of horizontal integral projectionwidth、Hwidth, then calculate：
Rate1=Vmax/Vwidth；
Rate2=Hmax/Hwidth；
Wherein, SvX () is the pixel value sum corresponding to the unit width of the image img after binary conversion treatment, ShX () is two-value
Change the pixel value sum corresponding to the unit height of the image img for processing, Y1=1, Y2Equal to the height of ocular image, X1
=1, X2Equal to the width of ocular image, I (x, y) represents (x, y) corresponding picture in ocular binary conversion treatment image
Element value, (x, y) is binary conversion treatment image coordinate value, and rate1, rate2 represent the ratio of integral projection height and the width respectively
Relation；
4.4 combine rate1 and rate2, calculateJudge driver whether in fatigue state；Will
The value of rate is compared with given threshold T2, judges the opening and closing state of human eye, and the even value of rate is more than T2, represents human eye
When closure degree reaches 80%, it is regarded as currently closing one's eyes completely；Wherein rate represents vertical and horizontal integral projection depth-width ratio
Example relation integrated value,It is the weight coefficient of rate1 and rate2；
4.5 carry out tired judgement using the P80 methods of PERCLOS, by counting in the unit period for setting, the eyes closed time
The percentage ratio of overall time is accounted for, if ratio has exceeded threshold value T set in advance, that is, current drivers is regarded as already at fatigue
Drive；Calculate value f of PERCLOS：
Within the unit interval, the number of image frames and image totalframes of eyes closed are counted, and value f of the PERCLOS is equal to：
F is the percentage rate that the eyes closed time accounts for setting time section；In the present invention, if the value of f is more than T, judge at driver
In fatigue state.
5. a kind of fatigue driving detection device as claimed in claim 1, it is characterised in that under the tired determination module passes through
Stating synthesis result carries out final judgement to the mental status of driver：
By the comprehensive descision result of Face detection module and human eye state identification module, three kinds of type of alarms are carried out：Work as face
Locating module judges that driver is in fatigue state, then start LED lamp alarm device and report to the police；When human eye state identification module judges
Driver is in fatigue state, then start loudspeaker alarm device and report to the police；When Face detection module and human eye state identification module it is equal
Judge that driver is in fatigue state, then start LED lamp alarm device simultaneously and loudspeaker alarm device is reported to the police.
6. the method for detecting fatigue driving that a kind of fatigue driving detection device based on described in claim 1 is realized, its feature exist
In comprising the steps：
Step 1, initializes photographic head, arranges the property value that photographic head reads in picture；
Image information is conveyed to arm processor equipment by step 2, USB camera collection image；
Step 3, Image semantic classification, i.e. image down, gray processing process；
Step 4, existing face and human eye feature grader in loading OpenCV machine vision storehouse, by the face of training in advance
Feature classifiers locating human face region, i.e., obtain face key feature points with Harr feature detection modes, fixed according to characteristic point
Position human face region, and respectively obtain human face region upper left angle point and bottom right angular coordinate (x1,y1)、(x2,y2), calculate face area
Center point coordinate (the H of area imagex,Hy), whereinAccording to (x1,y1)、(x2,y2) 2 points sit
Mark rectangle frame outlines human face region；
Step 5, judges fatigue state by face state：Face's existence position of driver is detected using Adaboost algorithm,
Face center position is calculated with image center in the deviation value of longitudinal direction, is compared with given threshold according to deviation value and a timing
In face center vibration frequency, that is, whether frequency of nodding judging driver in fatigue state；
Step 6, judges fatigue state by human eye state：The eye existence position of driver is detected using Adaboost algorithm,
Feature extraction is carried out to the eye of driver, the width ratio of the maximum and integral domain of the integral projection of ocular is calculated
Value, and compare to judge driver whether in fatigue state with given threshold T1；
Step 7, according to step 5,6 tired synthetic determination result, it is determined that returning image acquisition or starting different type of alarms
It is a kind of.
7. method for detecting fatigue driving as claimed in claim 6, it is characterised in that being sentenced by face state described in step 5
Determine fatigue state specifically to comprise the steps of：
5.1 face locations that driver is detected using Adaboost algorithm, obtain the center position (H of human face regionx,Hy)
Image center position (the I arrived with initial acquisitionx,Iy) in the deviation value Diff of longitudinal direction；
After 5.2 center positions for obtaining human face region, the vertical coordinate H of face center is calculatedyWith the vertical coordinate I of imageyDifference
Value Diff=| Hy-Iy|；
Amount of images n and image totalframes N of difference Diff more than given threshold T1 in 5.3 statistical unit cycles；
5.4 ratios for calculating amount of images n and image totalframes N, ratio are compared with given threshold T, if ratio is done greatly
Threshold value T, then judge that driver is in fatigue state.
8. method for detecting fatigue driving as claimed in claim 6, it is characterised in that judged by human eye state described in step 6
Fatigue state is specifically comprised the steps of：
The 6.1 eye existence positions that driver is detected using Adaboost algorithm, pass through human eye feature grader in human face region
Positioning human eye；
6.2 pairs of ocular images carry out gaussian filtering, remove noise, using adaptive binary conversion treatment；
The integral projection of the 6.3 image img for calculating binary conversion treatment, calculates the maximum and integral breadth of vertical integral projection
The maximum of ratio r ate1 and horizontal integral projection and ratio r ate2 of integral breadth；
Wherein, the formula that the calculating of vertical integral projection is adopted：
The formula that the calculating of horizontal integral projection is adopted：
The maximum V of vertical integral projection and horizontal integral projection is found out respectivelymax、Hmax, vertical integral projection is calculated respectively
With the peak width V of horizontal integral projectionwidth、Hwidth, then calculate：
Rate1=Vmax/Vwidth；
Rate2=Hmax/Hwidth；
Wherein, SvX () is the pixel value sum corresponding to the unit width of the image img of binary conversion treatment, ShX () is binaryzation
Pixel value sum corresponding to the unit height of the image img of process, Y1=1, Y2Equal to the height of ocular image, X1=
1, X2Equal to the width of ocular image, I (x, y) is (x, y) corresponding pixel value in ocular binary conversion treatment image,
(x, y) is binary conversion treatment image coordinate value, and rate1, rate2 represent that vertical integral projection maximum and vertical integration are thrown respectively
The ratio of the ratio of shadow peak width, horizontal integral projection maximum and horizontal integral projection peak width；
6.4 combine rate1 and rate2, calculateJudge driver whether in fatigue state；Will
The value of rate is compared with given threshold T2, judges the opening and closing state of human eye, and the even value of rate is more than T2, represents human eye
When closure degree reaches 80%, it is regarded as currently closing one's eyes completely；
Wherein, rate represents vertical and horizontal integral projection depth-width ratio example relation integrated value,It is rate1 and rate2
Weight coefficient；
6.5 carry out tired judgement using the P80 methods of PERCLOS, by counting in the unit period for setting, the eyes closed time
The percentage ratio of overall time is accounted for, if ratio has exceeded threshold value T set in advance, that is, current drivers is regarded as already at fatigue
Drive；Calculate value f of PERCLOS：
Within the unit interval, the number of image frames and unit interval image totalframes of eyes closed, value f of the PERCLOS are counted
It is equal to：
F is the percentage rate that the eyes closed time accounts for setting time section；In the present invention, if the value of f is more than T, judge at driver
In fatigue state.
9. method for detecting fatigue driving as claimed in claim 8, it is characterised in that the binary conversion treatment described in step 6.2, tool
The method of body is：
6.2.1., minimum threshold low=0.1, max-thresholds high=0.5, threshold tau incremental steps step=0.05 are set；
6.2.2. by imgs=binary (I, τ) constantly to the process of ocular image binaryzation；
6.2.3. the binary conversion treatment of non-zero connected region minimum number is found from a series of image imgs of binary conversion treatment
Image img1 and corresponding threshold tau；
6.2.4. opening operation endoporus filling are carried out to the image img1 of the binary conversion treatment of non-zero connected region minimum number；
6.2.5 the largest connected domain looked in the image img1 of binary conversion treatment, and other connected domains are removed, obtain final two-value
Change the image img for processing；
Wherein, imgs represents the image of binary conversion treatment, and bianry represents binary conversion treatment process, and I represents ocular image,
τ is the binary-state threshold being progressively incremented by from minimum threshold low by step 6.2.1；Imgs=binary (I, τ) is image of the present invention
The representation of binary conversion treatment.
10. fatigue detection method as claimed in claim 6, its decision method are specially：Comprehensively sentenced by step 5 and step 6
It is disconnected, it is characterised in that the different type of alarms described in step 7 are：When step 5 judges that driver is in fatigue state, then start
LED lamp alarm device is reported to the police；When step 6 judges that driver is in fatigue state, then start loudspeaker alarm device and report to the police；Work as step
5th, step 6 judges that driver in fatigue state, then starts LED lamp alarm device simultaneously and loudspeaker alarm device is reported to the police.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611264042.1A CN106530623B (en) | 2016-12-30 | 2016-12-30 | A kind of fatigue driving detection device and detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611264042.1A CN106530623B (en) | 2016-12-30 | 2016-12-30 | A kind of fatigue driving detection device and detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106530623A true CN106530623A (en) | 2017-03-22 |
| CN106530623B CN106530623B (en) | 2019-06-07 |
Family
ID=58336475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611264042.1A Expired - Fee Related CN106530623B (en) | 2016-12-30 | 2016-12-30 | A kind of fatigue driving detection device and detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106530623B (en) |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107085715A (en) * | 2017-05-19 | 2017-08-22 | 武汉理工大学 | A kind of television set intelligently detects the dormant system and method for user |
| CN107392153A (en) * | 2017-07-24 | 2017-11-24 | 中国科学院苏州生物医学工程技术研究所 | Human-body fatigue degree decision method |
| CN107562199A (en) * | 2017-08-31 | 2018-01-09 | 北京金山安全软件有限公司 | Page object setting method and device, electronic equipment and storage medium |
| CN107571735A (en) * | 2017-10-13 | 2018-01-12 | 苏州小黄人汽车科技有限公司 | A kind of vehicle drivers status monitoring system and monitoring method |
| CN107730834A (en) * | 2017-08-07 | 2018-02-23 | 西北工业大学 | A kind of antifatigue Intelligent worn device being combined based on attitude detection with image recognition |
| CN108022256A (en) * | 2017-12-25 | 2018-05-11 | 虹德科技（杭州）有限公司 | A kind of video intelligent analyzer |
| CN108021911A (en) * | 2018-01-04 | 2018-05-11 | 重庆公共运输职业学院 | A kind of driver tired driving monitoring method |
| CN108446644A (en) * | 2018-03-26 | 2018-08-24 | 刘福珍 | A kind of virtual display system for New-energy electric vehicle |
| CN108805049A (en) * | 2018-05-25 | 2018-11-13 | 郑州目盼智能科技有限公司 | A kind of embedded human face detection terminal |
| CN109063686A (en) * | 2018-08-29 | 2018-12-21 | 安徽华元智控科技有限公司 | A kind of fatigue of automobile driver detection method and system |
| CN109340607A (en) * | 2018-10-23 | 2019-02-15 | 电子科技大学 | A kind of anti-visual fatigue multi-function desk lamp |
| CN109513112A (en) * | 2018-12-03 | 2019-03-26 | 李鹏 | A kind of defibrillator and pacemaker full-automatic test system and test method |
| CN109977930A (en) * | 2019-04-29 | 2019-07-05 | 中国电子信息产业集团有限公司第六研究所 | Method for detecting fatigue driving and device |
| CN110194174A (en) * | 2019-05-24 | 2019-09-03 | 江西理工大学 | A kind of fatigue driving monitoring system |
| CN110879973A (en) * | 2019-10-31 | 2020-03-13 | 安徽普华灵动机器人科技有限公司 | Driver fatigue state facial feature recognition and detection method |
| CN111062292A (en) * | 2019-12-10 | 2020-04-24 | 哈尔滨工程大学 | Fatigue driving detection device and method |
| CN111209833A (en) * | 2019-12-31 | 2020-05-29 | 广东科学技术职业学院 | Fatigue driving detection method and unmanned driving equipment |
| CN111274963A (en) * | 2020-01-20 | 2020-06-12 | 西南科技大学 | Fatigue driving early warning system based on image processing |
| CN111291590A (en) * | 2018-12-06 | 2020-06-16 | 广州汽车集团股份有限公司 | Driver fatigue detection method, driver fatigue detection device, computer equipment and storage medium |
| CN112418002A (en) * | 2020-11-05 | 2021-02-26 | 中国航空工业集团公司西安飞行自动控制研究所 | Method for identifying own airport by unmanned aerial vehicle |
| CN112406881A (en) * | 2019-08-21 | 2021-02-26 | 美光科技公司 | Fatigue driving detection for vehicle control |
| CN112528906A (en) * | 2020-12-18 | 2021-03-19 | 武汉理工大学 | Driver state detection equipment |
| CN112668393A (en) * | 2020-11-30 | 2021-04-16 | 海纳致远数字科技(上海)有限公司 | Fatigue degree detection device and method based on face recognition and key point detection |
| CN112966664A (en) * | 2021-04-01 | 2021-06-15 | 科世达(上海)机电有限公司 | Fatigue driving detection method, system and device and readable storage medium |
| CN113066264A (en) * | 2021-02-22 | 2021-07-02 | 广州铁路职业技术学院（广州铁路机械学校） | Fatigue state identification method and desk lamp |
| CN113468956A (en) * | 2021-05-24 | 2021-10-01 | 北京迈格威科技有限公司 | Attention judging method, model training method and corresponding device |
| CN114140865A (en) * | 2022-01-29 | 2022-03-04 | 深圳市中讯网联科技有限公司 | Intelligent early warning method and device, storage medium and electronic equipment |
| CN114572330A (en) * | 2022-02-22 | 2022-06-03 | 深圳飞亮智能科技有限公司 | Electric motor car intelligence vehicle mounted terminal based on millimeter wave radar |
| CN116805405A (en) * | 2023-08-25 | 2023-09-26 | 南通大学 | Intelligent protection method and system for milling machine equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102436715A (en) * | 2011-11-25 | 2012-05-02 | 大连海创高科信息技术有限公司 | Detection method for fatigue driving |
| US20140055569A1 (en) * | 2012-08-22 | 2014-02-27 | Samsung Electro-Mechanics Co., Ltd. | Apparatus and method for sensing drowsy driving |
| CN204576754U (en) * | 2015-03-27 | 2015-08-19 | 孙建利 | A kind of vehicle-mounted car steering giving fatigue pre-warning equipment |
| CN106205052A (en) * | 2016-07-21 | 2016-12-07 | 上海仰笑信息科技有限公司 | A kind of driving recording method for early warning |
-
2016
- 2016-12-30 CN CN201611264042.1A patent/CN106530623B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102436715A (en) * | 2011-11-25 | 2012-05-02 | 大连海创高科信息技术有限公司 | Detection method for fatigue driving |
| US20140055569A1 (en) * | 2012-08-22 | 2014-02-27 | Samsung Electro-Mechanics Co., Ltd. | Apparatus and method for sensing drowsy driving |
| CN204576754U (en) * | 2015-03-27 | 2015-08-19 | 孙建利 | A kind of vehicle-mounted car steering giving fatigue pre-warning equipment |
| CN106205052A (en) * | 2016-07-21 | 2016-12-07 | 上海仰笑信息科技有限公司 | A kind of driving recording method for early warning |
Non-Patent Citations (1)
| Title |
|---|
| 陈萍: "基于Kinect的疲劳驾驶检测系统的设计与实现", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107085715A (en) * | 2017-05-19 | 2017-08-22 | 武汉理工大学 | A kind of television set intelligently detects the dormant system and method for user |
| CN107392153B (en) * | 2017-07-24 | 2020-09-29 | 中国科学院苏州生物医学工程技术研究所 | Human body fatigue degree judging method |
| CN107392153A (en) * | 2017-07-24 | 2017-11-24 | 中国科学院苏州生物医学工程技术研究所 | Human-body fatigue degree decision method |
| CN107730834A (en) * | 2017-08-07 | 2018-02-23 | 西北工业大学 | A kind of antifatigue Intelligent worn device being combined based on attitude detection with image recognition |
| CN107562199A (en) * | 2017-08-31 | 2018-01-09 | 北京金山安全软件有限公司 | Page object setting method and device, electronic equipment and storage medium |
| CN107571735A (en) * | 2017-10-13 | 2018-01-12 | 苏州小黄人汽车科技有限公司 | A kind of vehicle drivers status monitoring system and monitoring method |
| CN108022256A (en) * | 2017-12-25 | 2018-05-11 | 虹德科技（杭州）有限公司 | A kind of video intelligent analyzer |
| CN108021911A (en) * | 2018-01-04 | 2018-05-11 | 重庆公共运输职业学院 | A kind of driver tired driving monitoring method |
| CN108446644A (en) * | 2018-03-26 | 2018-08-24 | 刘福珍 | A kind of virtual display system for New-energy electric vehicle |
| CN108805049A (en) * | 2018-05-25 | 2018-11-13 | 郑州目盼智能科技有限公司 | A kind of embedded human face detection terminal |
| CN109063686A (en) * | 2018-08-29 | 2018-12-21 | 安徽华元智控科技有限公司 | A kind of fatigue of automobile driver detection method and system |
| CN109340607A (en) * | 2018-10-23 | 2019-02-15 | 电子科技大学 | A kind of anti-visual fatigue multi-function desk lamp |
| CN109513112A (en) * | 2018-12-03 | 2019-03-26 | 李鹏 | A kind of defibrillator and pacemaker full-automatic test system and test method |
| CN111291590A (en) * | 2018-12-06 | 2020-06-16 | 广州汽车集团股份有限公司 | Driver fatigue detection method, driver fatigue detection device, computer equipment and storage medium |
| CN109977930A (en) * | 2019-04-29 | 2019-07-05 | 中国电子信息产业集团有限公司第六研究所 | Method for detecting fatigue driving and device |
| CN110194174A (en) * | 2019-05-24 | 2019-09-03 | 江西理工大学 | A kind of fatigue driving monitoring system |
| CN110194174B (en) * | 2019-05-24 | 2021-02-12 | 江西理工大学 | Fatigue driving monitoring system |
| CN112406881A (en) * | 2019-08-21 | 2021-02-26 | 美光科技公司 | Fatigue driving detection for vehicle control |
| CN110879973A (en) * | 2019-10-31 | 2020-03-13 | 安徽普华灵动机器人科技有限公司 | Driver fatigue state facial feature recognition and detection method |
| CN111062292B (en) * | 2019-12-10 | 2022-07-29 | 哈尔滨工程大学 | Fatigue driving detection device and method |
| CN111062292A (en) * | 2019-12-10 | 2020-04-24 | 哈尔滨工程大学 | Fatigue driving detection device and method |
| CN111209833A (en) * | 2019-12-31 | 2020-05-29 | 广东科学技术职业学院 | Fatigue driving detection method and unmanned driving equipment |
| CN111209833B (en) * | 2019-12-31 | 2023-06-30 | 广东科学技术职业学院 | Fatigue driving detection method and unmanned equipment |
| CN111274963A (en) * | 2020-01-20 | 2020-06-12 | 西南科技大学 | Fatigue driving early warning system based on image processing |
| CN112418002A (en) * | 2020-11-05 | 2021-02-26 | 中国航空工业集团公司西安飞行自动控制研究所 | Method for identifying own airport by unmanned aerial vehicle |
| CN112418002B (en) * | 2020-11-05 | 2023-10-24 | 中国航空工业集团公司西安飞行自动控制研究所 | Method for identifying own airport by unmanned aerial vehicle |
| CN112668393A (en) * | 2020-11-30 | 2021-04-16 | 海纳致远数字科技(上海)有限公司 | Fatigue degree detection device and method based on face recognition and key point detection |
| CN112528906A (en) * | 2020-12-18 | 2021-03-19 | 武汉理工大学 | Driver state detection equipment |
| CN113066264A (en) * | 2021-02-22 | 2021-07-02 | 广州铁路职业技术学院（广州铁路机械学校） | Fatigue state identification method and desk lamp |
| CN112966664A (en) * | 2021-04-01 | 2021-06-15 | 科世达(上海)机电有限公司 | Fatigue driving detection method, system and device and readable storage medium |
| CN113468956A (en) * | 2021-05-24 | 2021-10-01 | 北京迈格威科技有限公司 | Attention judging method, model training method and corresponding device |
| CN114140865A (en) * | 2022-01-29 | 2022-03-04 | 深圳市中讯网联科技有限公司 | Intelligent early warning method and device, storage medium and electronic equipment |
| CN114572330A (en) * | 2022-02-22 | 2022-06-03 | 深圳飞亮智能科技有限公司 | Electric motor car intelligence vehicle mounted terminal based on millimeter wave radar |
| CN114572330B (en) * | 2022-02-22 | 2024-03-08 | 深圳飞亮智能科技有限公司 | Electric vehicle intelligent vehicle-mounted terminal based on millimeter wave radar |
| CN116805405A (en) * | 2023-08-25 | 2023-09-26 | 南通大学 | Intelligent protection method and system for milling machine equipment |
| CN116805405B (en) * | 2023-08-25 | 2023-10-27 | 南通大学 | Intelligent protection method and system for milling machine equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106530623B (en) | 2019-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106530623A (en) | Fatigue driving detection device and method | |
| CN106846734B (en) | A kind of fatigue driving detection device and method | |
| CN107704805B (en) | Method for detecting fatigue driving, automobile data recorder and storage device | |
| Mbouna et al. | Visual analysis of eye state and head pose for driver alertness monitoring | |
| CN106965675B (en) | A kind of lorry swarm intelligence safety work system | |
| CN104809445B (en) | method for detecting fatigue driving based on eye and mouth state | |
| CN103714660B (en) | System for achieving fatigue driving judgment on basis of image processing and fusion between heart rate characteristic and expression characteristic | |
| Nguyen et al. | Eye tracking system to detect driver drowsiness | |
| CN109389806B (en) | Fatigue driving detection early warning method, system and medium based on multi-information fusion | |
| CN107292251B (en) | Driver fatigue detection method and system based on human eye state | |
| CN101593425A (en) | A kind of fatigue driving monitoring method and system based on machine vision | |
| Tayab Khan et al. | Smart real-time video surveillance platform for drowsiness detection based on eyelid closure | |
| CN108309311A (en) | A kind of real-time doze of train driver sleeps detection device and detection algorithm | |
| CN106250801A (en) | Based on Face datection and the fatigue detection method of human eye state identification | |
| US20140062704A1 (en) | Sleepiness-estimating device and sleepiness-estimating method | |
| CN102201059A (en) | Pedestrian detection method and device | |
| CN111062292B (en) | Fatigue driving detection device and method | |
| CN104680124A (en) | Device And Method For Detecting Pedestrains | |
| CN108647708A (en) | Driver evaluation's method, apparatus, equipment and storage medium | |
| CN104318237A (en) | Fatigue driving warning method based on face identification | |
| CN103093210A (en) | Method and device for glasses identification in face identification | |
| CN109815842A (en) | A kind of method and device of the attribute information of determining object to be identified | |
| CN109977930A (en) | Method for detecting fatigue driving and device | |
| JP2012084068A (en) | Image analyzer | |
| CN107563346A (en) | One kind realizes that driver fatigue sentences method for distinguishing based on eye image processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190607 Termination date: 20201230 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |