CN110278367A - Eye detection method, system, equipment and its medium based on filming apparatus - Google Patents
Eye detection method, system, equipment and its medium based on filming apparatus Download PDFInfo
- Publication number
- CN110278367A CN110278367A CN201810210493.XA CN201810210493A CN110278367A CN 110278367 A CN110278367 A CN 110278367A CN 201810210493 A CN201810210493 A CN 201810210493A CN 110278367 A CN110278367 A CN 110278367A
- Authority
- CN
- China
- Prior art keywords
- detected person
- filming apparatus
- eyes
- image
- human eye
- 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
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/73—Circuitry for compensating brightness variation in the scene by influencing the exposure time
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Eye Examination Apparatus (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to monitoring field, a kind of eye detection method based on filming apparatus, system, equipment and its medium are disclosed.Eye detection method in the present invention is the following steps are included: obtain the multiframe consecutive image of the detected person shot by filming apparatus, wherein, image is when shooting, line between the eyes of detected person and the row or column in the pixel array of imaging sensor form an angle, and angle is greater than zero;According to the human eye part in the film speed of filming apparatus and multiframe consecutive image, the eyes open and-shut mode of detected person is determined.The present invention can effectively improve the detection frequency to human eye, to effectively improve the accuracy in detection to human eye closed state.
Description
Technical field
The present invention relates to monitoring field, in particular to a kind of eye detection method based on filming apparatus, system, equipment and
Its medium.
Background technique
Traffic accident related with fatigue driving takes place frequently always, and therefore, the driver status detection for fatigue driving has
Important meaning.
During detecting to driver status, the contacts means detection such as detection heartbeat, pulse can use
The state of driver also can use filming apparatus by carrying out image detection to the macroscopic motion of driver's face and local motion
To analyze and speculate the state of driver.Driver status detection based on filming apparatus, due to it is non-contact, to driver without dry
The advantages that disturbing has been widely used in driver status detection.The shape of driver is analyzed and speculated by image detection
State includes the detection to driver's eyes open and-shut mode.
The mode for the electronic shutter that imaging sensor generallys use in filming apparatus at present has global shutter (Global
Shutter) and two kinds of belt-type shutter (rolling shutter), global shutter are to be exposed by picture in its entirety in the same time
What light was realized.The all pixels point of sensor is collected simultaneously light, exposes simultaneously.Belt-type shutter is different from global shutter, it
It is to be realized by way of controlling chip and exposing line by line.Belt-type shutter passes through also without the shutter on practical significance
Control system of switching on or off electricity sensor keeps its different piece different to the susceptibility of light under different time.It is exposed line by line, until institute
There is pixel to be all exposed.Wherein, belt-type shutter is conveniently widely used since cheap, follow-up data is handled.
But using the filming apparatus of belt-type shutter when being detected to driver's eyes open and-shut mode, exist as
Lower problem:
Filming apparatus can not detect the human eye opening and closing activity occurred between two field pictures are taken.Because generally adopting
When with filming apparatus, line between human eye it is parallel with the row or column in the pixel array of its imaging sensor (generally with row
In parallel), in exposure, two eyes are exposed in the same time.For example, Fig. 1 (a) shows the eye closing behavior hair of detected person
Life is in t1-t2Period, Fig. 1 (b) show the bat that common (people's eyes are parallel with the row of pixel array) uses belt-type shutter
Take the photograph the state of the human eye of device shooting.As can be seen that eye closing behavior shown in Fig. 1 (a) occurs exactly at filming apparatus exposure
Between the time twice of human eye part, therefore it can not detect this eye closing behavior.
Summary of the invention
The purpose of the present invention is to provide a kind of eye detection method based on filming apparatus, system, equipment and its medium,
The detection frequency to human eye can be effectively improved, to effectively improve the accuracy in detection to human eye closed state.
In order to solve the above technical problems, embodiments of the present invention disclose a kind of human eye detection side based on filming apparatus
Method, wherein filming apparatus includes the imaging sensor with belt-type shutter;This method comprises:
Obtain the multiframe consecutive image of detected person shot by filming apparatus, wherein image when shooting, detected person
Eyes between line and imaging sensor pixel array in row or column form an angle, and angle be greater than zero;
According to the human eye part in the film speed of filming apparatus and multiframe consecutive image, determine that the eyes of detected person are opened
Closed state.
In one example, the eyes open and-shut mode for determining detected person includes:
According to the distance between detected person's eyes in the row time for exposure of filming apparatus, angle and image, every frame is calculated
The time for exposure of detected person's eyes is poor in image;
According to the human eye part in the time for exposure difference and image of every frame image in corresponding multiframe consecutive image, quilt is determined
Detect the eyes open and-shut mode of people.
In another example, above-mentioned detected person is vehicle driver, and filming apparatus is installed in the driving vehicle of driver
In.
Embodiments of the present invention also disclose a kind of human eye detection system based on filming apparatus, wherein filming apparatus
Including the imaging sensor with belt-type shutter;The system includes
Acquiring unit, for obtaining the multiframe consecutive image of the detected person by filming apparatus shooting, wherein image is being clapped
When taking the photograph, the line between the eyes of detected person and the row or column in the pixel array of imaging sensor form an angle, and
And angle is greater than zero;
Determination unit determines quilt for the human eye part in the film speed and multiframe consecutive image according to filming apparatus
Detect the eyes open and-shut mode of people.
In one example, detected person is driver, and filming apparatus is installed in the driving vehicle of driver;And really
Order member includes:
Computation subunit, for according in the row time for exposure of filming apparatus, angle and image between detected person's eyes
Distance, the time for exposure for calculating detected person's eyes in every frame image is poor;
Subelement is determined, in the time for exposure difference and image according to every frame image in corresponding multiframe consecutive image
Human eye part determines the eyes open and-shut mode of detected person.
Embodiments of the present invention also disclose a kind of equipment, which includes being stored with depositing for computer executable instructions
Reservoir and processor, processor are configured as executing instruction to implement the eye detection method based on filming apparatus, wherein shooting
Device includes the imaging sensor with belt-type shutter;
Eye detection method based on filming apparatus includes:
Obtain the multiframe consecutive image of detected person shot by filming apparatus, wherein image when shooting, detected person
Eyes between line and imaging sensor pixel array in row or column form an angle, and angle be greater than zero;
According to the human eye part in the film speed of filming apparatus and multiframe consecutive image, determine that the eyes of detected person are opened
Closed state.
In one example, the eyes open and-shut mode for determining detected person includes:
According to the distance between detected person's eyes in the row time for exposure of filming apparatus, angle and image, every frame is calculated
The time for exposure of detected person's eyes is poor in image;
According to the human eye part in the time for exposure difference and image of every frame image in corresponding multiframe consecutive image, quilt is determined
Detect the eyes open and-shut mode of people.
In another example, above-mentioned detected person is vehicle driver, and filming apparatus is installed in the driving vehicle of driver
In.
Embodiments of the present invention also disclose a kind of non-volatile computer storage Jie using computer program code
Matter, computer program include instruction, when instruction is executed by more than one computer, are instructed so that more than one computer
Operation is executed, operation includes:
Obtain the multiframe consecutive image of detected person shot by filming apparatus, wherein image when shooting, detected person
Eyes between line and imaging sensor pixel array in row or column form an angle, and angle be greater than zero;
According to the human eye part in the film speed of filming apparatus and multiframe consecutive image, determine that the eyes of detected person are opened
Closed state.
In another example, instructing further operable is to execute operation, and operation includes:
According to the distance between detected person's eyes in the row time for exposure of filming apparatus, angle and image, every frame is calculated
The time for exposure of detected person's eyes is poor in image;
According to the human eye part in the time for exposure difference and image of every frame image in corresponding multiframe consecutive image, quilt is determined
Detect the eyes open and-shut mode of people.
In another example, above-mentioned detected person is vehicle driver, and filming apparatus is installed in the driving vehicle of driver
In.
Compared with prior art, the main distinction and its effect are embodiment of the present invention:
By using the filming apparatus of belt-type shutter, and by the pixel array and human eye of imaging sensor in filming apparatus
Line is arranged in an oblique way, and can effectively improve the detection frequency to human eye, to effectively improve the standard of the detection to human eye closed state
Exactness.
Further, by effectively improving the accuracy of human eye closed state detection, to improve to driver tired driving
The accuracy in detection of state.
Detailed description of the invention
Fig. 1 (a) is the schematic diagram of the primary eye closing behavior of detected person;Fig. 1 (b) is fast using rolling door type in the prior art
The schematic diagram for the human eye state that the filming apparatus of door detects;Fig. 1 (c) is in first embodiment of the invention using rolling door type
The schematic diagram for the human eye state that the filming apparatus of shutter detects.
Fig. 2 is between the eyes line of detected person in first embodiment of the invention and the pixel array of imaging sensor
Positional diagram.
Fig. 3 is the flow diagram of the eye detection method based on filming apparatus in first embodiment of the invention;
Fig. 4 is the structural schematic diagram of the human eye detection system in second embodiment of the invention based on filming apparatus.
Specific embodiment
In the following description, in order to make the reader understand this application better, many technical details are proposed.But this
The those of ordinary skill in field is appreciated that even if without these technical details and many variations based on the following respective embodiments
And modification, each claim of the application technical solution claimed can also be realized.
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to implementation of the invention
Mode is described in further detail.
First embodiment of the invention is related to a kind of eye detection method based on filming apparatus.Fig. 3 is the human eye detection
The flow diagram of method.
Specifically, as shown in Figure 1, method includes the following steps:
In step 301, the multiframe consecutive image of the detected person shot by filming apparatus is obtained, wherein image is being clapped
When taking the photograph, the line between the eyes of detected person and the row or column in the pixel array of imaging sensor form an angle, and
And angle is greater than zero.Wherein, filming apparatus includes the imaging sensor with belt-type shutter.For example, Fig. 2 shows be detected
The positional diagram of people's eyes and pixel array, in Fig. 2, arrow E indicates to use the imaging sensor of belt-type shutter
The scanning direction progressively scanned, it is locating in pixel array that straight line A and B respectively indicate two eyes of detected person
Row, straight line D indicate the direction of the row of the pixel array.As can be seen that the line C between eyes and the row in expression pixel array
Straight line A or B or C θ in a certain angle.
Furthermore, it is to be understood that present invention meaning filming apparatus is the device for capableing of continuously shot images, such as video camera is taken the photograph
As head etc..
Then into step 302.According to the human eye part in the film speed of filming apparatus and multiframe consecutive image, determine
The eyes open and-shut mode of detected person.
It is appreciated that eyes open and-shut mode includes that eyes are in state of opening, closed state or in opening and be closed
Between state.For example, can indicate the open and-shut mode of eyes, when human eye is closed completely, eye using the closure degree of eyes
The closure degree of eyeball is 100%, and when human eye is opened completely, closure degree is 0.
Furthermore, it is to be understood that the film speed of filming apparatus includes needed for the one-row pixels in its exposing pixels array
Time for exposure additionally may include the other parameters for indicating the film speed of filming apparatus, herein with no restrictions.
Below with reference to Fig. 1 (c) and Fig. 2, the concrete mode for determining the eyes open and-shut mode of detected person is described in detail:
1) according to the row time for exposure t of filming apparatus0, the distance between detected person's eyes s, meter in angle theta and image
Calculate the time for exposure difference Δ t of detected person's eyes in every frame image.For example, Δ t can be calculated by the following formula:
Δ t=t0×s×sinθ
It is appreciated that the row time for exposure refers to the figure using rolling door type shutter in the embodiments of the present invention
The time for exposure as needed for the one-row pixels in exposure sensor pixel array.
2) it according to the human eye part in the time for exposure difference and image of every frame image in corresponding multiframe consecutive image, determines
The eyes open and-shut mode of detected person.For example, at the t1 moment, the eyes R in image starts to expose for image shown in Fig. 2,
It is 30% that it, which is closed degree,;And the eyes L in the t2 moment, image starts to expose, closure degree is 60%.It can speculate people
Eye has eye closing trend, while by the identical measurement of former frames or rear a few frame images to the frame image, to speculate that eyes are
It is no to be closed, such as the closure degree of eyes R and L are respectively 100% and 0 in the next frame image of the image, then can sentence
It is disconnected go out detected person once close one's eyes behavior.
It is understood that the specific example in of the invention is illustrative, number or specific steps therein
According to the actual situation, can be changed accordingly, but it changes all within the scope of the application advocated protection.
Hereafter terminate this process.
For the above method, can be applied in the driver monitoring field of driver, i.e. detected person drives for vehicle
The person of sailing, filming apparatus are installed in the driving vehicle of driver.In the application scenario, filming apparatus is generally camera,
It is mounted on the steering wheel, for detecting state of the driver in driving procedure.
The accuracy of human eye closed state detection can be improved in this method, thus it is helped to improve to driver tired driving
The accuracy in detection of state.Based on this method, those skilled in the art can using various existing means to driver whether into
Row fatigue driving is analyzed.
The present invention by using belt-type shutter filming apparatus, and by the pixel array of imaging sensor in filming apparatus
It is arranged in an oblique way with human eye line, the detection frequency to human eye can be effectively improved, to effectively improve to human eye closed state
Accuracy in detection.
Second embodiment of the present invention is related to a kind of human eye detection system based on filming apparatus, wherein filming apparatus
Including the imaging sensor with belt-type shutter.Fig. 4 is the structural schematic diagram of the human eye detection system.Specifically, such as Fig. 4 institute
Show, which includes:
Acquiring unit, for obtaining the multiframe consecutive image of the detected person by filming apparatus shooting, wherein image is being clapped
When taking the photograph, the line between the eyes of detected person and the row or column in the pixel array of imaging sensor form an angle, and
And angle is greater than zero.
Determination unit determines quilt for the human eye part in the film speed and multiframe consecutive image according to filming apparatus
Detect the eyes open and-shut mode of people.
In a preferred example, detected person is driver, and filming apparatus is installed in the driving vehicle of driver.
In another preferred example, determination unit includes:
Computation subunit, for according in the row time for exposure of filming apparatus, angle and image between detected person's eyes
Distance, the time for exposure for calculating detected person's eyes in every frame image is poor;
Subelement is determined, in the time for exposure difference and image according to every frame image in corresponding multiframe consecutive image
Human eye part determines the eyes open and-shut mode of detected person.
First embodiment is method implementation corresponding with present embodiment, and present embodiment can be implemented with first
Mode is worked in coordination implementation.The relevant technical details mentioned in first embodiment are still effective in the present embodiment, in order to
It reduces and repeats, which is not described herein again.Correspondingly, the relevant technical details mentioned in present embodiment are also applicable in the first implementation
In mode.
Third embodiment of the present invention is related to a kind of equipment, which includes being stored with depositing for computer executable instructions
Reservoir and processor, processor are configured as executing instruction to implement the eye detection method based on filming apparatus, wherein shooting
Device includes the imaging sensor with belt-type shutter;Eye detection method based on filming apparatus includes:
Obtain the multiframe consecutive image of detected person shot by filming apparatus, wherein image when shooting, detected person
Eyes between line and imaging sensor pixel array in row or column form an angle, and angle be greater than zero;
According to the human eye part in the film speed of filming apparatus and multiframe consecutive image, determine that the eyes of detected person are opened
Closed state.
In a demonstration example, determine that the eyes open and-shut mode of detected person includes:
According to the distance between detected person's eyes in the row time for exposure of filming apparatus, angle and image, every frame is calculated
The time for exposure of detected person's eyes is poor in image;
According to the human eye part in the time for exposure difference and image of every frame image in corresponding multiframe consecutive image, quilt is determined
Detect the eyes open and-shut mode of people.
In another demonstration example, detected person is vehicle driver, and filming apparatus is installed in the driving vehicle of driver
In.
4th embodiment of the invention is related to a kind of non-volatile computer storage Jie using computer program code
Matter, computer program include instruction, when instruction is executed by more than one computer, are instructed so that more than one computer
Operation is executed, operation includes:
Obtain the multiframe consecutive image of detected person shot by filming apparatus, wherein image when shooting, detected person
Eyes between line and imaging sensor pixel array in row or column form an angle, and angle be greater than zero;
According to the human eye part in the film speed of filming apparatus and multiframe consecutive image, determine that the eyes of detected person are opened
Closed state.
In a demonstration example, instructing further operable is to execute operation, and operation includes:
According to the distance between detected person's eyes in the row time for exposure of filming apparatus, angle and image, every frame is calculated
The time for exposure of detected person's eyes is poor in image;
According to the human eye part in the time for exposure difference and image of every frame image in corresponding multiframe consecutive image, quilt is determined
Detect the eyes open and-shut mode of people.
In another demonstration example, detected person is vehicle driver, and filming apparatus is installed in the driving vehicle of driver
In.
Each method embodiment of the invention can be realized in a manner of software, hardware, firmware etc..Regardless of the present invention be with
Software, hardware or firmware mode realize that instruction code may be stored in any kind of computer-accessible memory
In (such as permanent perhaps revisable volatibility is perhaps non-volatile solid or non-solid, it is fixed or
The replaceable medium etc. of person).Equally, memory may, for example, be programmable logic array (Programmable Array
Logic, referred to as " PAL "), random access memory (Random Access Memory, referred to as " RAM "), it may be programmed read-only deposit
Reservoir (Programmable Read Only Memory, referred to as " PROM "), read-only memory (Read-Only Memory, letter
Claim " ROM "), electrically erasable programmable read-only memory (Electrically Erasable Programmable ROM, referred to as
" EEPROM "), disk, CD, digital versatile disc (Digital Versatile Disc, referred to as " DVD ") etc..
It should be noted that each unit/the module mentioned in each equipment embodiment of the present invention is all logic unit/mould
Block, physically, a logic unit can be a physical unit, are also possible to a part of a physical unit, may be used also
With with the combination of multiple physical units realization, the Physical realization of these logic units itself be not it is most important, these
The combination for the function that logic unit is realized is only the key for solving technical problem proposed by the invention.In addition, for protrusion
Innovative part of the invention, the above-mentioned each equipment embodiment of the present invention is not by the technical problem proposed by the invention with solution
The less close unit of relationship introduces, this does not indicate above equipment embodiment and there is no other units.
It should be noted that in the claim and specification of this patent, such as first and second or the like relationship
Term is only used to distinguish one entity or operation from another entity or operation, without necessarily requiring or implying
There are any actual relationship or orders between these entities or operation.Moreover, the terms "include", "comprise" or its
Any other variant is intended to non-exclusive inclusion so that include the process, methods of a series of elements, article or
Equipment not only includes those elements, but also including other elements that are not explicitly listed, or further include for this process,
Method, article or the intrinsic element of equipment.In the absence of more restrictions, being wanted by what sentence " including one " limited
Element, it is not excluded that there is also other identical elements in the process, method, article or apparatus that includes the element.
Although being shown and described to the present invention by referring to some of the preferred embodiment of the invention,
It will be understood by those skilled in the art that can to it, various changes can be made in the form and details, without departing from this hair
Bright spirit and scope.
Claims (11)
1. a kind of eye detection method based on filming apparatus, which is characterized in that the filming apparatus includes having roller shutter type fast
The imaging sensor of door;
The described method includes:
Obtain the multiframe consecutive image of the detected person shot by the filming apparatus, wherein described image when shooting, is detected
The row or column surveyed in the pixel array of the line and described image sensor between the eyes of people forms an angle, and described
Angle is greater than zero;
According to the human eye part in the film speed of the filming apparatus and the multiframe consecutive image, the detected person is determined
Eyes open and-shut mode.
2. eye detection method according to claim 1, which is characterized in that the eyes of the determination detected person are opened
Closed state includes:
According to the distance between detected person's eyes in the row time for exposure of the filming apparatus, the angle and described image,
The time for exposure for calculating detected person's eyes in every frame described image is poor;
According to the human eye part in the time for exposure difference and described image of every frame image in the correspondence multiframe consecutive image, really
The eyes open and-shut mode of the fixed detected person.
3. eye detection method according to claim 1 or 2, which is characterized in that the detected person is vehicle driver,
The filming apparatus is installed in the driving vehicle of the driver.
4. a kind of human eye detection system based on filming apparatus, which is characterized in that the filming apparatus includes having roller shutter type fast
The imaging sensor of door;
The system comprises
Acquiring unit, for obtaining the multiframe consecutive image of the detected person shot by the filming apparatus, wherein described image
When shooting, the row or column in the line between the eyes of the detected person and the pixel array of described image sensor at
Certain angle, and the angle is greater than zero;
Determination unit, for the human eye part in the film speed and the multiframe consecutive image according to the filming apparatus, really
The eyes open and-shut mode of the fixed detected person.
5. human eye detection system according to claim 4, which is characterized in that the detected person is driver, the bat
Device is taken the photograph to be installed in the driving vehicle of the driver;And
The determination unit includes:
Computation subunit, for according to detected person in the row time for exposure of the filming apparatus, the angle and described image
The distance between eyes, the time for exposure for calculating detected person's eyes in every frame described image are poor;
Subelement is determined, for the time for exposure difference and described image according to every frame image in the correspondence multiframe consecutive image
In human eye part, determine the eyes open and-shut mode of the detected person.
6. a kind of equipment, which is characterized in that memory and processor including being stored with computer executable instructions, the processing
Device is configured as executing described instruction to implement the eye detection method based on filming apparatus, wherein the filming apparatus includes
Imaging sensor with belt-type shutter;
The eye detection method based on filming apparatus includes:
Obtain the multiframe consecutive image of the detected person shot by the filming apparatus, wherein described image is when shooting, described
Line between the eyes of detected person and the row or column in the pixel array of described image sensor form an angle, and
The angle is greater than zero;
According to the human eye part in the film speed of the filming apparatus and the multiframe consecutive image, the detected person is determined
Eyes open and-shut mode.
7. equipment according to claim 6, which is characterized in that the eyes open and-shut mode packet of the determination detected person
It includes:
According to the distance between detected person's eyes in the row time for exposure of the filming apparatus, the angle and described image,
The time for exposure for calculating detected person's eyes in every frame described image is poor;
According to the human eye part in the time for exposure difference and described image of every frame image in the correspondence multiframe consecutive image, really
The eyes open and-shut mode of the fixed detected person.
8. equipment according to claim 6 or 7, which is characterized in that the detected person is vehicle driver, the shooting
Device is installed in the driving vehicle of the driver.
9. a kind of nonvolatile computer storage media using computer program code, which is characterized in that the computer journey
Sequence includes instruction, and when described instruction is executed by more than one computer, described instruction makes one above calculating
Machine executes operation, and the operation includes:
Obtain the multiframe consecutive image of the detected person shot by the filming apparatus, wherein described image is when shooting, described
Line between the eyes of detected person and the row or column in the pixel array of described image sensor form an angle, and
The angle is greater than zero;
According to the human eye part in the film speed of the filming apparatus and the multiframe consecutive image, the detected person is determined
Eyes open and-shut mode.
10. computer storage medium according to claim 9, which is characterized in that further operable described instruction is to hold
Row operation, the operation include:
According to the distance between detected person's eyes in the row time for exposure of the filming apparatus, the angle and described image,
The time for exposure for calculating detected person's eyes in every frame described image is poor;
According to the human eye part in the time for exposure difference and described image of every frame image in the correspondence multiframe consecutive image, really
The eyes open and-shut mode of the fixed detected person.
11. computer storage medium according to claim 9 or 10, which is characterized in that the detected person drives for vehicle
The person of sailing, the filming apparatus are installed in the driving vehicle of the driver.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810210493.XA CN110278367B (en) | 2018-03-14 | 2018-03-14 | Human eye detection method, system, device and medium based on shooting device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810210493.XA CN110278367B (en) | 2018-03-14 | 2018-03-14 | Human eye detection method, system, device and medium based on shooting device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110278367A true CN110278367A (en) | 2019-09-24 |
CN110278367B CN110278367B (en) | 2021-11-19 |
Family
ID=67957631
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810210493.XA Active CN110278367B (en) | 2018-03-14 | 2018-03-14 | Human eye detection method, system, device and medium based on shooting device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110278367B (en) |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070086624A1 (en) * | 1995-06-07 | 2007-04-19 | Automotive Technologies International, Inc. | Image Processing for Vehicular Applications |
US20090261979A1 (en) * | 1992-05-05 | 2009-10-22 | Breed David S | Driver Fatigue Monitoring System and Method |
CN101692980A (en) * | 2009-10-30 | 2010-04-14 | 吴泽俊 | Method for detecting fatigue driving |
CN101834997A (en) * | 2009-03-09 | 2010-09-15 | 三星数码影像株式会社 | The method of digital image processing apparatus and this digital image processing apparatus of control |
CN102054163A (en) * | 2009-10-27 | 2011-05-11 | 南京理工大学 | Method for testing driver fatigue based on monocular vision |
CN102193269A (en) * | 2010-03-15 | 2011-09-21 | 索尼公司 | Image pickup apparatus |
CN203838770U (en) * | 2014-04-29 | 2014-09-17 | 深圳前向启创数码技术有限公司 | Automobile data recorder |
CN104718743A (en) * | 2012-10-02 | 2015-06-17 | 株式会社电装 | State monitoring device |
DE102014221039A1 (en) * | 2014-10-16 | 2016-04-21 | Robert Bosch Gmbh | A control device for a motor vehicle having a driver-side camera and a method for picking up the face of a vehicle occupant |
CN106327801A (en) * | 2015-07-07 | 2017-01-11 | 北京易车互联信息技术有限公司 | Method and device for detecting fatigue driving |
US20170330042A1 (en) * | 2010-06-04 | 2017-11-16 | Masoud Vaziri | Method and apparatus for an eye tracking wearable computer |
CN107563346A (en) * | 2017-09-20 | 2018-01-09 | 南京栎树交通互联科技有限公司 | One kind realizes that driver fatigue sentences method for distinguishing based on eye image processing |
CN107595307A (en) * | 2017-10-23 | 2018-01-19 | 湖南科技大学 | Fatigue driving detection device and detection method based on machine vision eye recognition |
-
2018
- 2018-03-14 CN CN201810210493.XA patent/CN110278367B/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090261979A1 (en) * | 1992-05-05 | 2009-10-22 | Breed David S | Driver Fatigue Monitoring System and Method |
US20070086624A1 (en) * | 1995-06-07 | 2007-04-19 | Automotive Technologies International, Inc. | Image Processing for Vehicular Applications |
CN101834997A (en) * | 2009-03-09 | 2010-09-15 | 三星数码影像株式会社 | The method of digital image processing apparatus and this digital image processing apparatus of control |
CN102054163A (en) * | 2009-10-27 | 2011-05-11 | 南京理工大学 | Method for testing driver fatigue based on monocular vision |
CN101692980A (en) * | 2009-10-30 | 2010-04-14 | 吴泽俊 | Method for detecting fatigue driving |
CN102193269A (en) * | 2010-03-15 | 2011-09-21 | 索尼公司 | Image pickup apparatus |
US20170330042A1 (en) * | 2010-06-04 | 2017-11-16 | Masoud Vaziri | Method and apparatus for an eye tracking wearable computer |
CN104718743A (en) * | 2012-10-02 | 2015-06-17 | 株式会社电装 | State monitoring device |
CN203838770U (en) * | 2014-04-29 | 2014-09-17 | 深圳前向启创数码技术有限公司 | Automobile data recorder |
DE102014221039A1 (en) * | 2014-10-16 | 2016-04-21 | Robert Bosch Gmbh | A control device for a motor vehicle having a driver-side camera and a method for picking up the face of a vehicle occupant |
CN106327801A (en) * | 2015-07-07 | 2017-01-11 | 北京易车互联信息技术有限公司 | Method and device for detecting fatigue driving |
CN107563346A (en) * | 2017-09-20 | 2018-01-09 | 南京栎树交通互联科技有限公司 | One kind realizes that driver fatigue sentences method for distinguishing based on eye image processing |
CN107595307A (en) * | 2017-10-23 | 2018-01-19 | 湖南科技大学 | Fatigue driving detection device and detection method based on machine vision eye recognition |
Also Published As
Publication number | Publication date |
---|---|
CN110278367B (en) | 2021-11-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP4962581B2 (en) | Lane marking detector | |
EP3480729B1 (en) | System and method for face position tracking and alerting user | |
US8050459B2 (en) | System and method for detecting pedestrians | |
US20180268687A1 (en) | Method and device for obtaining evidences for illegal parking of a vehicle | |
CN110136224A (en) | Image interfusion method and equipment | |
EP3627821B1 (en) | Focusing method and apparatus for realizing clear human face, and computer device | |
US20160042243A1 (en) | Object monitoring system, object monitoring method, and monitoring target extraction program | |
JP2007011815A (en) | Driving recorder | |
JP2009048347A (en) | Image processing apparatus, method and program | |
CN103475800B (en) | Method and device for detecting foreground in image sequence | |
KR20220025997A (en) | Apparatus for providing vehicle AVM image for collision prevention of approaching objects | |
JP4506779B2 (en) | Imaging apparatus and program | |
JP4635742B2 (en) | Imaging apparatus and imaging program | |
KR20100101375A (en) | Digital moving picture photographing apparatus, method for controlling the same, recording medium storing program to implement the method, and method for determining movement of subject | |
US9781331B2 (en) | Imaging apparatus, and control method thereof | |
CN110278367A (en) | Eye detection method, system, equipment and its medium based on filming apparatus | |
JP2009088709A (en) | Height estimation device, and photographing device | |
KR102378216B1 (en) | Apparatus and method for object speed detection using rolling shutter | |
CN115442521B (en) | Image pickup control method and related device, camera and storage medium | |
JP2009244944A (en) | Image-recovering apparatus and photographing apparatus | |
CN105763766A (en) | Control method, control device and electronic device | |
EP3471017A1 (en) | Method, system and apparatus for selecting frames of a video sequence | |
JP2008252321A5 (en) | ||
JP2011046516A (en) | Monitoring system in elevator car | |
JP2014074957A (en) | Image processing apparatus and image processing method |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |