CN107742103A - A kind of video frequency monitoring method and system - Google Patents
A kind of video frequency monitoring method and system Download PDFInfo
- Publication number
- CN107742103A CN107742103A CN201710955526.9A CN201710955526A CN107742103A CN 107742103 A CN107742103 A CN 107742103A CN 201710955526 A CN201710955526 A CN 201710955526A CN 107742103 A CN107742103 A CN 107742103A
- Authority
- CN
- China
- Prior art keywords
- image
- eye
- white
- face
- eye socket
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000012544 monitoring process Methods 0.000 title claims abstract description 14
- 210000001508 eye Anatomy 0.000 claims abstract description 111
- 210000004279 orbit Anatomy 0.000 claims abstract description 70
- 210000001747 pupil Anatomy 0.000 claims abstract description 23
- 230000001960 triggered effect Effects 0.000 claims abstract description 6
- 238000001514 detection method Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000009825 accumulation Methods 0.000 abstract description 6
- 230000001815 facial effect Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 8
- 239000000284 extract Substances 0.000 description 5
- 206010039203 Road traffic accident Diseases 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 210000003128 head Anatomy 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000000887 face Anatomy 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 208000020564 Eye injury Diseases 0.000 description 1
- 241000593989 Scardinius erythrophthalmus Species 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000027455 binding Effects 0.000 description 1
- 238000009739 binding Methods 0.000 description 1
- 210000005252 bulbus oculi Anatomy 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 210000000744 eyelid Anatomy 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 201000005111 ocular hyperemia Diseases 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 210000001525 retina Anatomy 0.000 description 1
- 230000004256 retinal image Effects 0.000 description 1
- 210000001202 rhombencephalon Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/193—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/197—Matching; Classification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Ophthalmology & Optometry (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Signal Processing (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Emergency Alarm Devices (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of video frequency monitoring method and system, including：The face image of collection detected object in real time；The eye socket image of eyes and the white of the eye image positioned at pupil both sides are extracted from face image；Calculate position shape information of the white of the eye image in eye socket image；Judge whether position shape information meets preset alarm information, alarm is triggered if meeting；Wherein, position shape information includes：Accounting of the area of white of the eye image in the area of eye socket image, the central point of white of the eye image is located at the position in eye socket image, the color distortion of the white of the eye and eye socket and facial skin is big, common camera is only needed to may recognize that the shape of the white of the eye under lamp, the color distortion of the white of the eye and pupil is big, the center of place's pupil can be calculated by the shape of the white of the eye in eye socket, so as to the sight accumulation point of driver at identification, if the target accumulation point of driver is mobile in setting range to represent that driver is normally travel, otherwise triggering alarm.
Description
Technical field
The present invention relates to monitoring technology field, more specifically, it relates to a kind of video frequency monitoring method and system.
Background technology
In the control loop that people, car, road form, driver is the maximum inducement of traffic accident.Wherein, most things
Therefore caused by being due to driver's operational error and fatigue driving.Due to age, physiology or mental health state, mood etc.
Change, also differ even if outstanding driver and surely muchly keep its original good driving condition, but driver
It is difficult to recognize this gradual decay or regression.Therefore, monitor the driving behavior of driver and give police to unlawful practice
Report, to improving the driving ability of driver and reducing its driver workload, coordinate between driver and vehicle and traffic environment
Relation, inherently reduce traffic accident situation generation, it is significant.Fatigue detecting is to reduce traffic accident
A kind of common method of probability, it is that the fatigue phenomenon occurred to driver in driving is detected and imposed and suitably alerts in real time
Process, it has following requirement：（1）Must be glitch-free；（2）Must be real-time；（3）Must be influenceed by illumination compared with
It is small；（4）There can not be harmful radiation；（5）Mobile device can not be included.In existing various detection methods, it can meet above
Ask and effect with video camera it is preferable that carry out captured in real-time, the thing of driver eye is then detected by image procossing
Reason reaction.
The method at present for driver's monitoring is to utilize infrared light supply in the prior art so that human eye is in infrared light action
Lower generation red-eye effect, in use infrared light supply and in the case of same illumination, using a beam splitter complete phase
Same image gives two video cameras, and obtains the infrared figure of different wave length by 850nm and 950nm wavelength filters respectively
Picture, two images are subtracted each other, just obtain only including the image of retina, so as to by judging that retinal images state is driven
The driving condition of member, this method is very high to hardware requirement, and infrared light is larger to eye injury.
The content of the invention
The technical problem that technical solution of the present invention solves is, existing to be regarded using infrared light supply and video camera shooting driver
Nethike embrane image can injure the eyes of driver after driver's driving condition to monitor.
To achieve the above object, technical solution of the present invention provides a kind of video frequency monitoring method, including：
The face image of collection detected object in real time；
The eye socket image of eyes and the white of the eye image positioned at pupil both sides are extracted from the face image；
Calculate position shape information of the white of the eye image in the eye socket image；
Judge whether the position shape information meets preset alarm information, alarm is triggered if meeting；
Wherein, the position shape information includes：Accounting of the area of the white of the eye image in the area of the eye socket image,
The central point of the white of the eye image is located at the position in the eye socket image.
Further, the face image of the detected object of collection in real time, including：
The face image of the detection object is compared with default multiple face images, determines that the detected object is
No is target detected object, if it is, preset alarm condition is not met, if it is not, then triggering alarm.
Further, the position shape information for calculating white of the eye image in the eye socket image, including：
The distance difference of the central point of central point and the face image using between the eye socket image of eyes is described in
Face's deflection angle of detected object；
Judge whether face's deflection angle is maintained in default face's range of deflection angles in preset time, if it is,
Preset alarm condition is not met then, if it is not, then triggering alarm.
Further, it is described to judge whether the position shape information meets preset alarm information, including：
Judge the distance difference of the white of the eye image center and the eye socket image center where it and whether default
Time is maintained in default distance difference and scope, if it is, preset alarm condition is not met, if it is not, then triggering report
It is alert；
It is pre- to judge whether accounting of the area of the white of the eye image in the area of the eye socket image maintains in preset time
If accounting in the range of, if it is, do not meet preset alarm condition, if it is not, then triggering alarm.
Further, the position shape information also includes：The shape that the white of the eye image is presented.
In order to solve the above-mentioned technical problem, technical solution of the present invention additionally provides a kind of video monitoring system, including：
Real-time acquisition module, for gathering the face image of detected object in real time；
Image zooming-out module, for extracting the eye socket image of eyes and the white of the eye positioned at pupil both sides from the face image
Image；
Image computing module, for calculating position shape information of the white of the eye image in the eye socket image；
Signal judgement module, for judging whether the position shape information meets preset alarm information, report is triggered if meeting
It is alert, wherein, the position shape information includes：Accounting of the area of the white of the eye image in the area of the eye socket image,
The central point of the white of the eye image is located at the position in the eye socket image.
Further, the acquisition module in real time also includes：
Comparing unit, for the face image of the detection object to be compared with default multiple face images, determine institute
State whether detected object is target detected object, if it is, preset alarm condition is not met, if it is not, then triggering report
It is alert.
Further, described image computing module also includes：
Deflection calculation unit, for the central point of the central point between the eye socket image with eyes and the face image
Face deflection angle of the distance difference as the detected object；
Judging unit is deflected, for judging whether face's deflection angle in preset time maintains default face's deflection angle
In the range of degree, if it is, preset alarm condition is not met, if it is not, then triggering alarm.
Further, described information judge module also includes：
Center judging unit, for judging the distance of the white of the eye image center and the eye socket image center where it
Difference and whether maintained in preset time in default distance difference and scope, if it is, preset alarm condition is not met,
If it is not, then triggering alarm；
Accounting judging unit, for judge accounting of the area of the white of the eye image in the area of the eye socket image whether
Preset time is maintained in the range of default accounting, if it is, preset alarm condition is not met, if it is not, then triggering alarm.
Further, in addition to：
Alarm module, for proposing to alarm to driver.
The beneficial effect of technical solution of the present invention comprises at least：
By identifying that eye socket and the white of the eye can determine whether the driving condition of driver, the white of the eye and eye socket and face on face image
The color distortion of skin is big, it is only necessary to which common camera may recognize that the shape of the white of the eye, the white of the eye and pupil under lamp
Color distortion it is big, the center of place's pupil can be calculated by the shape of the white of the eye in eye socket, so as to driver at identification
Sight accumulation point, if the target accumulation point of driver is mobile in setting range to represent that driver is normally travel, otherwise touch
Transmit messages police.
The shape that technical solution of the present invention is presented by judging white of the eye image, by the shape with setting form fit,
The current driving behavior of driver is obtained, is alarmed if driving behavior is unfavorable for driving safety.
Technical solution of the present invention is by the way that the face image of detection object is compared with default multiple face images, really
Determine whether detected object is target detected object, can interpolate that whether driver is setting personnel, if not then sending report
It is alert, so as to ensure the safety of vehicle, moreover it is possible to avoid driver from being substituted in violation of rules and regulations during driving.
Brief description of the drawings
Fig. 1 is the method flow schematic diagram of the embodiment of the present invention one；
Fig. 2 is the S1 of the embodiment of the present invention one method flow schematic diagram；
Fig. 3 is the S3 of the embodiment of the present invention one method flow schematic diagram；
Fig. 4 is the S4 of the embodiment of the present invention one method flow schematic diagram；
Fig. 5 is the block diagram of the embodiment of the present invention two；
Fig. 6 is the block diagram of two real-time acquisition module of the embodiment of the present invention；
Fig. 7 is the block diagram of the image computing module of the embodiment of the present invention two；
Fig. 8 is the block diagram of the signal judgement module of the embodiment of the present invention two；
Reference：100th, real-time acquisition module；110th, comparing unit；200th, image zooming-out module；300th, image computing module；
310th, deflection calculation unit；320th, judging unit is deflected；400th, signal judgement module；410th, center judging unit；420th, accounting
Judging unit；500th, alarm module.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Embodiment one
With reference to the foregoing invention thinking of technical solution of the present invention, a kind of video frequency monitoring method, as shown in figure 1, comprising the following steps：
Step S1：The face image of collection detected object in real time.The equipment for gathering face image is to need the coloured silk of lamp
Color camera, camera are fixed on the front of driver and shoot the face of driver.
As shown in Fig. 2 wherein step S1 also includes step S11：By the face image of detection object and default multiple faces
Portion's image is compared, and determines whether detected object is target detected object, if it is, not meeting preset alarm bar
Part, if it is not, then triggering alarm.
Wherein, the face image of tested side object is analyzed, i.e., face image positioned, use Haar features
And iterative algorithm Adaboost detection program, it is wrong that Adaboost algorithm can adaptively adjust hypothesis according to the feedback of weak study
Rate by mistake, it is more prominent in the degree of accuracy and efficiency, therefore directly select.And human eye positioning is easily by the appendicular shadow such as eyebrow
Ring, therefore propose to carry out Adaboost detections using textural characteristics and Haar characteristic bindings, its False Rate of the results show exists
It is 1% to be refused when 0.001% sincere, disclosure satisfy that the requirement further identified.
Step S2：The eye socket image of eyes and the white of the eye image positioned at pupil both sides are extracted from face image.
Using big specific of the white of the eye and eye socket and facial skin color distortion, extracted from face image eye socket image with
White of the eye image.In the facial image of the yellow colour of skin, white of the eye image is white, and pupil is the black relative with the white of the eye, and eye socket figure
As being then the white of the eye and the black border on pupil periphery, first extraction white of the eye image, then find pupil, eye socket image is finally extracted.
In fair-complexioned facial image, white of the eye image is white, and pupil is the dark color relative with the white of the eye, but skin causes eye socket more in vain
Seem more black, first extract eye socket image, then extract pupil, finally extract white of the eye image.In black facial image, the white of the eye
Image is white, and pupil is the dark color relative with the white of the eye, but skin is more black so that eye socket can not be identified first, first extracts eye
White image, then pupil is extracted, finally extract eye socket image.Said extracted order can improve the identification of eye socket image and white of the eye image
Accuracy rate.
Step S3：Calculate position shape information of the white of the eye image in eye socket image.
As shown in figure 3, wherein step S3 also includes step S31 and step S32.
Step S31：The distance difference of the central point of central point and face image using between the eye socket image of eyes as
Face's deflection angle of detected object.
Central point between the eye socket image of eyes in the positive direction of driver head, and the central point of face image with
Generally circular driver head is turned to without changing, because the part that face image is blocked is mended by driver's hindbrain
Fill, the face image is projection of the driver head that photographs of camera in camera.Between the eye socket image of eyes
The distance difference of the central point of central point and face image is the angle for representing the deflection of driver face.
Step S32：Judge whether face's deflection angle is maintained in default face's range of deflection angles in preset time,
If it is, preset alarm condition is not met, if it is not, then triggering alarm.Represent and drive if face's deflection angle angle is excessive
The person of sailing does not pay attention to the road of vehicle front, and accident easily occurs, it is therefore desirable to alarm driver.
Step S4：Judge whether position shape information meets preset alarm information, alarm is triggered if meeting, wherein, position
Putting shape information includes：Accounting of the area of white of the eye image in the area of eye socket image, the central point of white of the eye image are located at eye
Position in socket of the eye image, and the shape that white of the eye image is presented.
As shown in figure 4, wherein step S4 also includes step S41 and step S42.
Step S41：Judge white of the eye image center with its where eye socket image center distance difference and whether
Preset time is maintained in default distance difference and scope, if it is, preset alarm condition is not met, if it is not, then touching
Transmit messages police.
White of the eye image center is the blinkpunkt of the eyeball, the central point of two white of the eye images and the eye socket image where it
The distance difference of central point is the deflection of the central point of white of the eye image, that is, the sight of facing for representing driver faces sight with it
Deflection.Distance difference is substantially of pixel between the central point of white of the eye image and eye socket image center where it
Number, a side draw positive direction, another side draw negative direction of eye socket image.The distance difference of two white of the eye images and then there is amplification single
The effect of white of the eye picture deflection degree, the deflection of single white of the eye image is amplified without using extra algorithm.Distance difference
With maintain in default distance difference and scope, and within the range carry out small range fluctuation, then represent driver and be in
Normal driving condition, otherwise need alarm driver.
Step S42：Judge whether accounting of the area of white of the eye image in the area of eye socket image maintains in preset time
In the range of default accounting, if it is, preset alarm condition is not met, if it is not, then triggering alarm.
Pupil in the white of the eye is rounded, when driver close one's eyes or open eyes during, pupil can be blocked by upper eyelid from
And accounting of the white of the eye image in the area of eye socket image is set constantly to change.Its accounting is maximum when driver will close one's eyes, and reveals
Accounting is minimum when going out half pupil.During driver opens eyes, accounting sports maximum by zero, is then reduced to minimum, most
Slowly become big afterwards, but last accounting is no more than maximum.During driver closes one's eyes, accounting becomes as low as minimum, slowly finally
Become big, sport zero after reaching a maximum value.Judge whether driver can not keep eyes because of fatigue according to accounting
The state of normal driving, the requirement to hardware is reduced, avoid using injury of the infrared light supply to human eye, expand answering for monitoring
Use scope.
By identifying that eye socket and the white of the eye are the driving condition that can determine whether driver on face image, the white of the eye and eye socket and
The color distortion of facial skin is big, it is only necessary to common camera may recognize that the shape of the white of the eye under lamp, the white of the eye with
The color distortion of pupil is big, can calculate the center of place's pupil by the shape of the white of the eye in eye socket, so as to be driven at identification
The sight accumulation point for the person of sailing, it is no if the target accumulation point of driver is mobile in setting range to represent that driver is normally travel
Then triggering alarm.
The shape that technical solution of the present invention is presented by judging white of the eye image, by the shape with setting form fit,
The current driving behavior of driver is obtained, is alarmed if driving behavior is unfavorable for driving safety.
Technical solution of the present invention is by the way that the face image of detection object is compared with default multiple face images, really
Determine whether detected object is target detected object, can interpolate that whether driver is setting personnel, if not then sending report
It is alert, so as to ensure the safety of vehicle, moreover it is possible to avoid driver from being substituted in violation of rules and regulations during driving.
Embodiment two
With reference to the foregoing invention thinking of technical solution of the present invention, a kind of video monitoring system, as shown in figure 5, including：
Real-time acquisition module 100, for gathering the face image of detected object in real time.The hardware of real-time acquisition module 100 is adopted
Formed with by the camera that vehicle power supply is powered and microcomputer, face of the collection detected object under the conditions of lamp
Image.
As shown in fig. 6, acquisition module 100 also includes in real time：Comparing unit 110, for by the face image of detection object
It is compared with default multiple face images, determines whether detected object is target detected object, if it is, not being inconsistent
Preset alarm condition is closed, if it is not, then triggering alarm.Default multiple face images are stored in the memory unit of microcomputer
It is interior.
Image zooming-out module 200, for extracting the eye socket image of eyes from face image with being located at pupil both sides
White of the eye image.
Image computing module 300, for calculating position shape information of the white of the eye image in eye socket image.Image calculates mould
Block 300 is the image recognition algorithm component that microcomputer calls.
As shown in fig. 7, image computing module 300 also includes deflection calculation unit 310 and deflection judging unit 320.
Deflection calculation unit 310, for the central point between the eye socket image with eyes and the central point of face image
Face deflection angle of the distance difference as detected object；
Judging unit 320 is deflected, for judging whether face's deflection angle in preset time maintains default face's deflection angle
In the range of degree, if it is, preset alarm condition is not met, if it is not, then triggering alarm.
Signal judgement module 400, for judging whether position shape information meets preset alarm information, triggered if meeting
Alarm, wherein, position shape information includes：Accounting of the area of white of the eye image in the area of eye socket image, white of the eye image
Central point is located at the position in eye socket image.
As shown in figure 8, signal judgement module 400 also includes center judging unit 410 and accounting judging unit 420.
Center judging unit 410, for judging the distance of white of the eye image center and the eye socket image center where it
Difference and whether maintained in preset time in default distance difference and scope, if it is, preset alarm condition is not met,
If it is not, then triggering alarm；
Accounting judging unit 420, for judging accounting of the area of white of the eye image in the area of eye socket image whether default
Time is maintained in the range of default accounting, if it is, preset alarm condition is not met, if it is not, then triggering alarm.
System also includes being used for the alarm module 500 for proposing driver alarm, and alarm module 500 is and microcomputer
The buzzer or indicator lamp of controlled connection, microcomputer can be to alarm module after above-mentioned module or unit triggers alarm
500 send alarm signal, and alarm module 500 sends alarm after receiving alarm signal.It is convenient to remind person on duty, it can improve
The accuracy rate of monitoring.
Each embodiment is described by the way of progressive in this specification, what each embodiment stressed be and other
The difference of embodiment, between each embodiment identical similar portion mutually referring to.For device disclosed in embodiment
For, because it is corresponded to the method disclosed in Example, so description is fairly simple, related part is said referring to method part
It is bright.
Described above is only the preferred embodiment of the present invention, and protection scope of the present invention is not limited merely to above-mentioned implementation
Example, all technical schemes belonged under thinking of the present invention belong to protection scope of the present invention.It should be pointed out that for the art
Those of ordinary skill for, some improvements and modifications without departing from the principles of the present invention, these improvements and modifications
It should be regarded as protection scope of the present invention.
Claims (10)
- A kind of 1. video frequency monitoring method, it is characterised in that including：The face image of collection detected object in real time；The eye socket image of eyes and the white of the eye image positioned at pupil both sides are extracted from the face image；Calculate position shape information of the white of the eye image in the eye socket image；Judge whether the position shape information meets preset alarm information, alarm is triggered if meeting；Wherein, the position shape information includes：Accounting of the area of the white of the eye image in the area of the eye socket image, The central point of the white of the eye image is located at the position in the eye socket image.
- 2. according to the method for claim 1, it is characterised in that the face image of the detected object of collection in real time, bag Include：The face image of the detection object is compared with default multiple face images, determines that the detected object is No is target detected object, if it is, preset alarm condition is not met, if it is not, then triggering alarm.
- 3. according to the method for claim 2, it is characterised in that the calculating white of the eye image is in the position of the eye socket image Shape information, including：The distance difference of the central point of central point and the face image using between the eye socket image of eyes is described in Face's deflection angle of detected object；Judge whether face's deflection angle is maintained in default face's range of deflection angles in preset time, if it is, Preset alarm condition is not met then, if it is not, then triggering alarm.
- 4. according to the method for claim 3, it is characterised in that described to judge whether the position shape information meets default Warning message, including：Judge the distance difference of the white of the eye image center and the eye socket image center where it and whether default Time is maintained in default distance difference and scope, if it is, preset alarm condition is not met, if it is not, then triggering report It is alert；It is pre- to judge whether accounting of the area of the white of the eye image in the area of the eye socket image maintains in preset time If accounting in the range of, if it is, do not meet preset alarm condition, if it is not, then triggering alarm.
- 5. according to the method for claim 4, it is characterised in that the position shape information also includes：The white of the eye image The shape presented.
- A kind of 6. video monitoring system, it is characterised in that including：Real-time acquisition module（100）, for gathering the face image of detected object in real time；Image zooming-out module（200）, for extracting the eye socket image of eyes from the face image and being located at pupil both sides White of the eye image；Image computing module（300）, for calculating position shape information of the white of the eye image in the eye socket image；Signal judgement module（400）, for judging whether the position shape information meets preset alarm information, touched if meeting Transmit messages police, wherein, the position shape information includes：The area of the white of the eye image accounting in the area of the eye socket image Than the central point of the white of the eye image is located at the position in the eye socket image.
- 7. system according to claim 6, it is characterised in that the real-time acquisition module（100）Also include：Comparing unit（110）, for the face image of the detection object to be compared with default multiple face images, really Whether the fixed detected object is target detected object, if it is, preset alarm condition is not met, if it is not, then touching Transmit messages police.
- 8. system according to claim 7, it is characterised in that described image computing module（300）Also include：Deflection calculation unit（310）, in the central point between the eye socket image with eyes and the face image Face deflection angle of the distance difference of heart point as the detected object；Deflect judging unit（320）, for judging whether face's deflection angle in preset time maintains default face In range of deflection angles, if it is, preset alarm condition is not met, if it is not, then triggering alarm.
- 9. system according to claim 8, it is characterised in that described information judge module（400）Also include：Center judging unit（410）, for judging the white of the eye image center and the eye socket image center where it Distance difference and whether maintained in preset time in default distance difference and scope, if it is, not meeting default report Alert condition, if it is not, then triggering alarm；Accounting judging unit（420）, for judging accounting of the area of the white of the eye image in the area of the eye socket image Whether maintained in preset time in the range of default accounting, if it is, preset alarm condition is not met, if it is not, then touching Transmit messages police.
- 10. system according to claim 9, it is characterised in that also include：Alarm module（500）, for proposing to alarm to driver.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710955526.9A CN107742103A (en) | 2017-10-14 | 2017-10-14 | A kind of video frequency monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710955526.9A CN107742103A (en) | 2017-10-14 | 2017-10-14 | A kind of video frequency monitoring method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107742103A true CN107742103A (en) | 2018-02-27 |
Family
ID=61237609
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710955526.9A Pending CN107742103A (en) | 2017-10-14 | 2017-10-14 | A kind of video frequency monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107742103A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110148275A (en) * | 2019-04-20 | 2019-08-20 | 上海科信建筑智能化工程有限公司 | A kind of video monitoring method and its system |
| CN114187631A (en) * | 2021-11-30 | 2022-03-15 | 北京百度网讯科技有限公司 | Object behavior detection method, device, camera and storage medium |
| WO2022110917A1 (en) * | 2020-11-26 | 2022-06-02 | 亿咖通（湖北）科技有限公司 | Method for determining driving state of driver, computer storage medium, and electronic device |
| CN115398508A (en) * | 2020-03-31 | 2022-11-25 | 五十铃自动车株式会社 | Permission/non-permission determination device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140292638A1 (en) * | 2013-03-29 | 2014-10-02 | Wistron Corp. | Computing system and method for automatically detecting fatigue status of user |
| CN102647581B (en) * | 2012-04-27 | 2015-05-20 | 浙江晨鹰科技有限公司 | Video monitoring device and system |
| CN105488462A (en) * | 2015-11-25 | 2016-04-13 | 努比亚技术有限公司 | Eye positioning identification device and method |
| CN106897725A (en) * | 2015-12-18 | 2017-06-27 | 西安中兴新软件有限责任公司 | A kind of method and device for judging user's asthenopia |
-
2017
- 2017-10-14 CN CN201710955526.9A patent/CN107742103A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102647581B (en) * | 2012-04-27 | 2015-05-20 | 浙江晨鹰科技有限公司 | Video monitoring device and system |
| US20140292638A1 (en) * | 2013-03-29 | 2014-10-02 | Wistron Corp. | Computing system and method for automatically detecting fatigue status of user |
| CN105488462A (en) * | 2015-11-25 | 2016-04-13 | 努比亚技术有限公司 | Eye positioning identification device and method |
| CN106897725A (en) * | 2015-12-18 | 2017-06-27 | 西安中兴新软件有限责任公司 | A kind of method and device for judging user's asthenopia |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110148275A (en) * | 2019-04-20 | 2019-08-20 | 上海科信建筑智能化工程有限公司 | A kind of video monitoring method and its system |
| CN115398508A (en) * | 2020-03-31 | 2022-11-25 | 五十铃自动车株式会社 | Permission/non-permission determination device |
| CN115398508B (en) * | 2020-03-31 | 2024-01-05 | 五十铃自动车株式会社 | Permission determination device |
| WO2022110917A1 (en) * | 2020-11-26 | 2022-06-02 | 亿咖通（湖北）科技有限公司 | Method for determining driving state of driver, computer storage medium, and electronic device |
| CN114187631A (en) * | 2021-11-30 | 2022-03-15 | 北京百度网讯科技有限公司 | Object behavior detection method, device, camera and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107742103A (en) | A kind of video frequency monitoring method and system | |
| US10165971B2 (en) | Driver state determination apparatus | |
| CN104732251B (en) | A kind of trainman's driving condition detection method based on video | |
| CN106709420B (en) | Method for monitoring driving behavior of commercial vehicle driver | |
| CN1275185C (en) | Driver's face image identification and alarm device and method | |
| US7620216B2 (en) | Method of tracking a human eye in a video image | |
| Kurylyak et al. | Detection of the eye blinks for human's fatigue monitoring | |
| CN106530623A (en) | Fatigue driving detection device and method | |
| CN104627076A (en) | Automobile and anti-collision pre-warning system for same | |
| Anjali et al. | Real-time nonintrusive monitoring and detection of eye blinking in view of accident prevention due to drowsiness | |
| Ahmed et al. | Robust driver fatigue recognition using image processing | |
| CN102647581B (en) | Video monitoring device and system | |
| Singh et al. | Lie detection using image processing | |
| CN109190600A (en) | A kind of driver's monitoring system of view-based access control model sensor | |
| CN118587689B (en) | Driver fatigue status detection method and system | |
| CN109606376A (en) | A kind of safe driving Activity recognition system based on vehicle intelligent terminal | |
| CN204526997U (en) | A kind of vehicle anti-collision early warning system and automobile | |
| CN112381871B (en) | Implementation method of locomotive vigilance device based on face recognition | |
| CN105701971A (en) | Iris-recognition-based system, apparatus, and method for preventing fatigue driving | |
| Kannan et al. | Driver drowsiness detection and alert system | |
| Mašanović et al. | Driver monitoring using the in-vehicle camera | |
| JP2019083019A (en) | Driver state determination device | |
| CN110148275A (en) | A kind of video monitoring method and its system | |
| Santhiya et al. | Improved authentication and drowsiness detection from facial features using deep learning framework in real time environments | |
| Devi et al. | Fuzzy based driver fatigue detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180227 |
|
| RJ01 | Rejection of invention patent application after publication |