CN113536967B - Driver state identification method and device based on head movement posture and eye opening and closing degree of driver, and electronic equipment - Google Patents
Driver state identification method and device based on head movement posture and eye opening and closing degree of driver, and electronic equipment Download PDFInfo
- Publication number
- CN113536967B CN113536967B CN202110712742.7A CN202110712742A CN113536967B CN 113536967 B CN113536967 B CN 113536967B CN 202110712742 A CN202110712742 A CN 202110712742A CN 113536967 B CN113536967 B CN 113536967B
- Authority
- CN
- China
- Prior art keywords
- driver
- head
- eye
- alarm
- time
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Abstract
The invention provides a driver state identification method, a device and electronic equipment based on the head movement gesture and the eye opening and closing degree of a driver, wherein the method comprises the following steps: acquiring driving active infrared images in real time, and performing face detection to determine the position of a facial organ and the attitude and pitch angle of the head; judging the opening and closing states of eyes according to the characteristic points of the parts of the eyes; acquiring a head pitch angle calibration value in a normal driving state, if the current pitch angle is smaller than the calibration value, starting to accumulate low head alarm time, and giving out low head alarm when the low head alarm accumulation time reaches a set alarm time threshold T1; when the acquired accumulated time of the head-down actions and the accumulated time of the whole head-down process do not exceed the set threshold T2 and the eye state is closed, the accumulated eye closing alarm time is started, and when the accumulated time of the eye closing alarm reaches the set threshold T3, fatigue alarm is given. The invention can accurately distinguish the driver's true fatigue eye-closing and downward looking actions, thereby giving out accurate alarm reminding.
Description
Technical Field
The disclosure relates to the technical field of driving safety protection, in particular to a driver state identification method, device and electronic equipment based on the head movement posture and the eye opening and closing degree of a driver.
Background
Fatigue driving is one of the important reasons for traffic accidents, and can effectively avoid the fatigue driving of a driver by efficiently and accurately detecting the driving state of the driver and accurately giving out proper alarm reminding, thereby avoiding the occurrence of traffic accidents. The danger level of real fatigue eye closure is higher than the danger level of looking down and distraction in the driving process, and the alarm levels correspondingly given are different, so that the two states need to be accurately distinguished. If the two states cannot be distinguished, the driver detection system can give out false alarm reminding, so that the driver is caused to feel opposite, and the alarm reminding function cannot be exerted.
The method for detecting fatigue driving at present mainly comprises the following steps: and estimating the pitch angle of the head of the human body according to the detected face area, and judging whether the head-down motion exists according to the change of the pitch angle.
According to the method based on the head posture pitch angle, the pitch angle change of the low head of the driver is different due to different pitching orientations of the cameras, different heights of the driver and different sitting habits during driving, and the low head action is difficult to accurately judge. In addition, due to the planar view angle, when the driver looks down and actually tired to close eyes, the eye states in the image picture are very similar, and even the naked eyes of a person can not accurately judge whether to close eyes in many scenes. Therefore, the eye state is similar to the eye closing state when the head is lowered, the error judgment of the eye closing is easily caused by adopting a head pitch angle calibration method, and accurate alarm reminding cannot be given in real time.
Disclosure of Invention
In view of this, the embodiment of the disclosure provides a driver state identification method, device and electronic equipment based on the head movement gesture and the eye opening and closing degree of the driver, which aims to accurately distinguish the true fatigue eye closing and downward looking actions of the driver, and further give an accurate alarm prompt.
In order to achieve the above object, the present invention provides the following technical solutions:
a driver state identification method based on the head movement gesture and the eye opening and closing degree of a driver, comprising:
acquiring a vehicle-mounted driving active infrared image in real time, detecting the face of a driver on the infrared image, and determining the position of a facial organ and the attitude and pitch angle of the head;
obtaining an eye area according to the characteristic points of the eye parts of the driver, judging the opening and closing states of the eyes, and classifying and storing the eye judging states and corresponding head posture pitch angle values;
acquiring a head pitch angle calibration value of a normal driving state of a driver, comparing the current pitch angle with the calibration value in real time, if the current pitch angle is smaller than the calibration value, starting to accumulate low head alarm time, and giving low head alarm when the accumulated low head alarm time reaches a set alarm time threshold T1;
and acquiring the accumulated time of the head-falling actions of the driver and the accumulated time of the head-falling whole process, when the accumulated time of the head-falling whole process and the accumulated time of the head-falling actions do not exceed a set threshold T2, and when the eye state is closed, starting to accumulate the eye-closing alarm time, and when the accumulated time of the eye-closing alarm reaches a set threshold T3, giving out fatigue alarm.
Further, the accumulation condition of the low head action accumulation time is: both the current frame angle and the last frame angle are lower than 0 °.
Further, the accumulation condition of the low head whole process accumulation time is: the current frame Angle is below the pitch Angle calibration and the current frame Angle differs from the minimum Angle by no more than a set Angle threshold Angle1.
Further, the method further comprises, before the step of performing driver face detection on the obtained infrared image, preprocessing the infrared image, wherein the preprocessing comprises the following steps: the image is scaled and filtered to balance the image contrast and remove noise.
Further, when the face detection of the driver is performed, the faces are detected by using the MTCNN, the faces are ordered according to the confidence level, and the largest face is output, namely the face of the driver.
Further, the facial organ positions of the human face including the eye, nose, mouth positions are detected by a PFLD detection algorithm.
Further, obtaining the eye area according to the characteristic points of the eye part of the driver further comprises filtering the eye state with too small area, and judging the opening and closing states of the eyes by using a deep learning classifier.
Further, the pitch angle calibration value obtaining process includes: performing initial calibration for the first time when the driver is in a normal driving state, and continuously updating the calibration value when the stable state is met; wherein, the normal driving state is that the driver opens eyes and the pitch angle is larger than O degrees; the steady state is a normal driving state for a set period of time.
The invention also provides a driver state identification device based on the head movement gesture and the eye opening and closing degree of the driver, which comprises:
the data acquisition module is used for acquiring monitoring data for identifying fatigue driving of a driver, wherein the monitoring data comprise at least three types of data of vehicle driving state data, driver facial image data and head posture pitch angle data;
the data processing and fatigue degree identification module is used for realizing the driver state identification method based on the head movement gesture and the eye opening and closing degree of the driver when executing the stored computer program and identifying the real fatigue eye closing and head lowering downward looking actions of the driver according to the monitoring data;
and the alarm module is used for outputting an alarm prompt according to the identification result of the real fatigue eye closing and the low head looking-down action of the driver.
The invention also provides electronic equipment, which comprises a memory and a processor; the processor executes a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to realize the driver state identification method based on the head movement gesture and the eye opening and closing degree of the driver.
The driver state identification method, the device and the electronic equipment based on the driver head movement gesture and the human eye opening and closing degree have the beneficial effects that: compared with the traditional method based on the head posture pitch angle, the method has good adaptability, can accurately distinguish the real fatigue eye closing and downward looking actions of the driver, can adapt to more scenes, has high alarm judgment accuracy, can better play a reminding role, and reduces the occurrence rate of fatigue accidents.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings may be obtained according to these drawings without inventive effort to a person of ordinary skill in the art.
FIG. 1 is a schematic diagram illustrating an overall flow chart of an embodiment of a driver status recognition method according to the present invention;
FIG. 2 is a flowchart illustrating steps of determining a true fatigue eye closure and head down looking in an embodiment of a driver status recognition method according to the present invention.
Detailed Description
Embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
Other advantages and effects of the present disclosure will become readily apparent to those skilled in the art from the following disclosure, which describes embodiments of the present disclosure by way of specific examples. It will be apparent that the described embodiments are merely some, but not all embodiments of the present disclosure. The disclosure may be embodied or practiced in other different specific embodiments, and details within the subject specification may be modified or changed from various points of view and applications without departing from the spirit of the disclosure. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict. All other embodiments, which can be made by one of ordinary skill in the art without inventive effort, based on the embodiments in this disclosure are intended to be within the scope of this disclosure.
It is noted that various aspects of the embodiments are described below within the scope of the following claims. It should be apparent that the aspects described herein may be embodied in a wide variety of forms and that any specific structure and/or function described herein is merely illustrative. Based on the present disclosure, one skilled in the art will appreciate that one aspect described herein may be implemented independently of any other aspect, and that two or more of these aspects may be combined in various ways. For example, an apparatus may be implemented and/or a method practiced using any number of the aspects set forth herein. In addition, such apparatus may be implemented and/or such methods practiced using other structure and/or functionality in addition to one or more of the aspects set forth herein.
It should also be noted that the illustrations provided in the following embodiments merely illustrate the basic concepts of the disclosure by way of illustration, and only the components related to the disclosure are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.
In addition, in the following description, specific details are provided in order to provide a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects may be practiced without these specific details.
The embodiment of the disclosure provides a driver state identification method based on the head movement gesture and the eye opening and closing degree of a driver, comprising the following steps:
acquiring a vehicle-mounted driving active infrared image in real time, detecting the face of a driver on the infrared image, and determining the position of a facial organ and the attitude and pitch angle of the head;
obtaining an eye area according to the characteristic points of the eye parts of the driver, judging the opening and closing states of the eyes, and classifying and storing the eye judging states and corresponding head posture pitch angle values;
acquiring a head pitch angle calibration value of a normal driving state of a driver, comparing the current pitch angle with the calibration value in real time, if the current pitch angle is smaller than the calibration value, starting to accumulate low head alarm time, and giving low head alarm when the accumulated low head alarm time reaches a set alarm time threshold T1;
and acquiring the accumulated time of the head-falling actions of the driver and the accumulated time of the head-falling whole process, when the accumulated time of the head-falling whole process and the accumulated time of the head-falling actions do not exceed a set threshold T2, and when the eye state is closed, starting to accumulate the eye-closing alarm time, and when the accumulated time of the eye-closing alarm reaches a set threshold T3, giving out fatigue alarm.
The technical scheme of the invention is that based on a vehicle-mounted active infrared image, a traditional image mode recognition method is utilized to detect the face of a driver, position key points (eyes, nose and mouth) of the face and estimate the pitch angle of the head gesture of the person, then a deep learning method is utilized to judge the eye state (open eyes and close eyes), the judging result and the head pitch angle are saved, and corresponding alarm reminding is given according to the logic of judging true fatigue eye closing and low head looking down, and a flow chart is shown in figure 1.
The method comprises the following specific steps:
s1, inputting an infrared image
Acquiring a vehicle-mounted driving active infrared image;
s2, pretreatment
In order to balance the contrast of the image, remove noise and reduce the calculated amount, the image is respectively scaled and filtered by utilizing an image bilinear difference value, a histogram equalization and a median filter, and the processed image is output;
s3, face detection
Detecting a face, i.e., a face position, using MTCNN (Multi-task Cascaded Convolutional Networks); sequencing the faces according to the confidence level, and outputting the largest face, namely the face of the driver;
the MTCNN algorithm is a face detection and face alignment method based on deep learning, can simultaneously finish the tasks of face detection and face alignment, and has better performance and faster detection speed compared with the traditional algorithm.
S4, positioning key points
Detecting key points of the human face by using a PFLD (PFLD: A Practical Facial Landmark Detector) detection algorithm, and outputting the positions of the key points (eyes, nose and mouth) and head posture pitch angles of the human face;
s5, eye state detection and filtration
Obtaining an eye area according to the characteristic points of the eye part, filtering the eye state with too small area, and judging the opening and closing states of the eyes by using a deep learning classifier;
s6, storing the classification result and the pitch angle value
The eye state and pitch angle values obtained by classification are stored;
s7, judging that the eyes are closed and the head is lowered due to real fatigue
The method comprises the steps of obtaining a calibration value p_most of a pitch angle through calibrating a normal driving state of a driver, comparing the current pitch angle with the calibration value in real time, starting accumulating low head alarm time t_go if the pitch angle is smaller than the calibration value, and giving low head alarm when the low head alarm time reaches a set alarm time threshold T1; when the accumulated time of low head alarm does not exceed the set threshold T2 and the eye state is closed, the accumulated eye closing alarm time is started, and when the accumulated time of eye closing alarm reaches the set threshold T3, fatigue alarm is given. The specific flow is shown in fig. 2.
1. Initializing: these parameters are respectively given initial values: pitch angle calibration angle p_most, eye closing time t_closed, head-down overall process time t_go, head-down action time t_stop;
2. calibrating a pitch angle: the normal driving state (eyes open and pitch angle is larger than 0 degree) is initially calibrated for the first time, and the calibration value is continuously updated when the steady state (the normal state lasts for a period of time) is met; and taking the statistical value of a certain confidence interval according to normal distribution within the stable state duration of the calibration value:
in the above formula, T is a stable time range, α is a confidence interval, and std () is root mean square.
3. Low head action time accumulation condition: the current frame angle and the previous frame angle are both lower than 0 degrees;
4. low head total process time accumulation condition: the current frame Angle is lower than the calibration Angle p_most, and the difference between the current frame Angle and the minimum Angle is not more than a set Angle threshold value Angle1;
5. eye closure time accumulation condition: the accumulated time of the low head actions and the whole process time of the low head are taken as maximum values, the maximum values do not exceed a set time threshold T2, and the eyes are in a closed-eye state.
S8, alarming and reminding
When the accumulated time of the low head alarm reaches the alarm time threshold T1, giving out the low head alarm, otherwise judging whether the accumulated time of the eye closing alarm reaches the eye closing alarm time threshold T3, and giving out the fatigue alarm if the accumulated time of the eye closing alarm reaches the eye closing alarm time threshold T3.
Example 1
Initializing: pitch angle calibration angle p_most, eye closing time t_closed, head-down overall process time t_go, head-down action time t_stop pitch angle calibration: normal driving conditions (open eye and pitch angle greater than 0 degrees) are initially calibrated for the first time: p_most=10 degrees. The steady state (normal state is satisfied and the pitch angle does not change by more than 8 degrees for 6 seconds) is followed, p_most is used as a calibration value, otherwise statistics and updating are carried out later.
For example: p_most=10 degrees. And in the following system 6s, the difference between the pitch angle two frames is <8 degrees, which is considered as a stable state, and p_most is output.
Updating the low head action time accumulation condition: the current frame angle and the last frame angle are both lower than 0 degrees, the head-down overall process time accumulation condition: the current frame angle is lower than the nominal angle p_most and the current frame angle differs from the minimum angle by no more than 10 degrees from the eye-closing time accumulation condition: the low head action accumulation time and the low head overall process time take a maximum value, and the maximum value does not exceed t2=450 ms. If the low head motion is <450ms and the eyes are closed, the accumulated eye closing time is started, and when the eye closing time exceeds t1=2.5 s, a fatigue alarm is triggered. If T2>450ms, then the eye-closing logic clears, does not trigger an eye-closing alarm, and if the low head time is continuing to accumulate, and the accumulation time > t3=2.5 s, then a low head alarm is triggered.
The foregoing is merely specific embodiments of the disclosure, but the protection scope of the disclosure is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the disclosure are intended to be covered by the protection scope of the disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
Claims (8)
1. A driver state recognition method based on a driver head movement posture and a human eye opening and closing degree, characterized by comprising:
acquiring a vehicle-mounted driving active infrared image in real time, detecting the face of a driver on the infrared image, and determining the position of a facial organ and the attitude and pitch angle of the head;
obtaining an eye area according to the characteristic points of the eye parts of the driver, judging the opening and closing states of the eyes, and classifying and storing the eye judging states and corresponding head posture pitch angle values;
acquiring a head pitch angle calibration value of a normal driving state of a driver, comparing the current pitch angle with the calibration value in real time, if the current pitch angle is smaller than the calibration value, starting to accumulate low head alarm time, and giving low head alarm when the accumulated low head alarm time reaches a set alarm time threshold T1;
acquiring the accumulated time of the head-falling actions of a driver and the accumulated time of the whole head-falling process, when the accumulated time of the head-falling process and the accumulated time of the head-falling actions do not exceed a set threshold T2, and when the eye state is closed, starting to accumulate the eye-closing alarm time, and when the eye-closing alarm accumulated time reaches a set threshold T3, giving out fatigue alarm;
the accumulation condition of the head-down action accumulation time is: the current frame angle and the previous frame angle are both lower than 0 °;
the accumulation conditions of the accumulation time of the whole process of the low head are as follows: the current frame Angle is below the pitch Angle calibration and the current frame Angle differs from the minimum Angle by no more than a set Angle threshold Angle1.
2. The method for recognizing a driver's state based on the movement posture of the head and the opening and closing degree of the human eye according to claim 1, wherein the method further comprises, before the step of performing the face detection of the driver on the obtained infrared image, preprocessing the infrared image, the preprocessing comprising: the image is scaled and filtered to balance the image contrast and remove noise.
3. The method for recognizing the driver state based on the head movement gesture and the eye opening and closing degree of the driver according to claim 1, wherein when the driver face is detected, the MTCNN is used for detecting the faces, the faces are ranked according to the confidence degree, and the largest face is output, namely the driver face.
4. The driver state identification method based on the driver head movement posture and the human eye opening and closing degree according to claim 1, characterized in that the human face facial organ positions including the eye, nose, mouth positions are detected by a PFLD detection algorithm.
5. The method for recognizing the driver's state based on the head movement posture and the eye opening and closing degree of the driver according to claim 4, wherein the step of obtaining the eye area according to the characteristic points of the driver's eye portion further comprises filtering the eye state with too small area, and then judging the opening and closing state of the eyes by using a deep learning classifier.
6. The method for identifying the driver state based on the head movement posture and the eye opening and closing degree of the driver according to claim 1, wherein the process for obtaining the pitch angle calibration value comprises the following steps: performing initial calibration for the first time when the driver is in a normal driving state, and continuously updating the calibration value when the stable state is met; wherein, the normal driving state is that the driver opens eyes and the pitch angle is larger than 0 degree; the steady state is a normal driving state for a set period of time.
7. A driver state recognition device based on a driver head movement posture and a human eye opening and closing degree, characterized by comprising:
the data acquisition module is used for acquiring monitoring data for identifying fatigue driving of a driver, wherein the monitoring data comprise at least three types of data of vehicle driving state data, driver facial image data and head posture pitch angle data;
a data processing and fatigue degree recognition module that, when executing the stored computer program, implements the driver state recognition method based on the driver head movement posture and the human eye opening and closing degree of any one of claims 1 to 6, for recognizing, based on the monitoring data, a real fatigue eye closing and head lowering looking-down action of the driver;
and the alarm module is used for outputting an alarm prompt according to the identification result of the real fatigue eye closing and the low head looking-down action of the driver.
8. An electronic device, comprising a memory and a processor; wherein the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, for implementing the driver state recognition method based on the driver head movement posture and the human eye opening and closing degree according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110712742.7A CN113536967B (en) | 2021-06-25 | 2021-06-25 | Driver state identification method and device based on head movement posture and eye opening and closing degree of driver, and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110712742.7A CN113536967B (en) | 2021-06-25 | 2021-06-25 | Driver state identification method and device based on head movement posture and eye opening and closing degree of driver, and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113536967A CN113536967A (en) | 2021-10-22 |
| CN113536967B true CN113536967B (en) | 2023-05-30 |
Family
ID=78125899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110712742.7A Active CN113536967B (en) | 2021-06-25 | 2021-06-25 | Driver state identification method and device based on head movement posture and eye opening and closing degree of driver, and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113536967B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023108364A1 (en) * | 2021-12-13 | 2023-06-22 | 华为技术有限公司 | Method and apparatus for detecting driver state, and storage medium |
| CN116012822B (en) * | 2022-12-26 | 2024-01-30 | 无锡车联天下信息技术有限公司 | Fatigue driving identification method and device and electronic equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107229922A (en) * | 2017-06-12 | 2017-10-03 | 西南科技大学 | A kind of fatigue driving monitoring method and device |
| CN108875642A (en) * | 2018-06-21 | 2018-11-23 | 长安大学 | A kind of method of the driver fatigue detection of multi-index amalgamation |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7253739B2 (en) * | 2005-03-10 | 2007-08-07 | Delphi Technologies, Inc. | System and method for determining eye closure state |
| CN108961678A (en) * | 2018-04-26 | 2018-12-07 | 华慧视科技（天津）有限公司 | One kind being based on Face datection Study in Driver Fatigue State Surveillance System and its detection method |
| CN108791299B (en) * | 2018-05-16 | 2020-06-19 | 浙江零跑科技有限公司 | Driving fatigue detection and early warning system and method based on vision |
| CN111079476B (en) * | 2018-10-19 | 2024-03-26 | 上海商汤智能科技有限公司 | Driving state analysis method and device, driver monitoring system and vehicle |
| CN109919049A (en) * | 2019-02-21 | 2019-06-21 | 北京以萨技术股份有限公司 | Fatigue detection method based on deep learning human face modeling |
| CN110991324B (en) * | 2019-11-29 | 2023-06-02 | 中通服咨询设计研究院有限公司 | Fatigue driving detection method based on various dynamic characteristics and Internet of things technology |
| CN110946595B (en) * | 2019-12-16 | 2022-05-17 | 武汉极目智能技术有限公司 | Driver fatigue degree detection method based on DMS system |
-
2021
- 2021-06-25 CN CN202110712742.7A patent/CN113536967B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107229922A (en) * | 2017-06-12 | 2017-10-03 | 西南科技大学 | A kind of fatigue driving monitoring method and device |
| CN108875642A (en) * | 2018-06-21 | 2018-11-23 | 长安大学 | A kind of method of the driver fatigue detection of multi-index amalgamation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113536967A (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107346422B (en) | Living body face recognition method based on blink detection | |
| CN104616438B (en) | A kind of motion detection method of yawning for fatigue driving detection | |
| CN113536967B (en) | Driver state identification method and device based on head movement posture and eye opening and closing degree of driver, and electronic equipment | |
| US20200334477A1 (en) | State estimation apparatus, state estimation method, and state estimation program | |
| JP4389956B2 (en) | Face recognition device, face recognition method, and computer program | |
| CN104200192B (en) | Driver's gaze detection system | |
| CN109919049A (en) | Fatigue detection method based on deep learning human face modeling | |
| US20160272217A1 (en) | Two-step sleepy driving prevention apparatus through recognizing operation, front face, eye, and mouth shape | |
| CN105286802B (en) | Driver Fatigue Detection based on video information | |
| US9105172B2 (en) | Drowsiness-estimating device and drowsiness-estimating method | |
| CN111616718B (en) | Method and system for detecting fatigue state of driver based on attitude characteristics | |
| CN107405121B (en) | Method and device for detecting a fatigue state and/or a sleep state of a driver of a vehicle | |
| JP6399311B2 (en) | Dozing detection device | |
| CN109101943A (en) | It is a kind of for detecting the machine vision method of Falls Among Old People | |
| Nakamura et al. | Detection of driver's drowsy facial expression | |
| JP5292671B2 (en) | Awakening degree estimation apparatus, system and method | |
| CN115937830A (en) | Special vehicle-oriented driver fatigue detection method | |
| Ranjan et al. | Driver Drowsiness Detection System Using Computer Vision | |
| Mašanović et al. | Driver monitoring using the in-vehicle camera | |
| CN115690892B (en) | Mitigation method and device, electronic equipment and storage medium | |
| CN113420656A (en) | Fatigue driving detection method and device, electronic equipment and storage medium | |
| JP2010009093A (en) | Person state determination device | |
| Ma et al. | A real-time fatigue driving detection system design and implementation | |
| Srivastava | Driver's drowsiness identification using eye aspect ratio with adaptive thresholding | |
| CN111696312B (en) | Passenger observation device |
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 |