CN113313913A - Automobile safety early warning system and weighting early warning method - Google Patents
Automobile safety early warning system and weighting early warning method Download PDFInfo
- Publication number
- CN113313913A CN113313913A CN202110557470.8A CN202110557470A CN113313913A CN 113313913 A CN113313913 A CN 113313913A CN 202110557470 A CN202110557470 A CN 202110557470A CN 113313913 A CN113313913 A CN 113313913A
- Authority
- CN
- China
- Prior art keywords
- early warning
- fatigue
- vehicle
- cloud platform
- classifier
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims abstract description 37
- 238000004891 communication Methods 0.000 claims abstract description 16
- 206010016256 fatigue Diseases 0.000 claims description 90
- 230000009471 action Effects 0.000 claims description 36
- 210000003128 head Anatomy 0.000 claims description 30
- 230000001815 facial effect Effects 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 15
- 230000004397 blinking Effects 0.000 claims description 11
- 241001282135 Poromitra oscitans Species 0.000 claims description 10
- 206010048232 Yawning Diseases 0.000 claims description 10
- 230000004424 eye movement Effects 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 8
- 230000001133 acceleration Effects 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 230000004886 head movement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/06—Alarms for ensuring the safety of persons indicating a condition of sleep, e.g. anti-dozing alarms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the field of vehicle driving early warning, in particular to an automobile safety early warning system and a weighting early warning method. The utility model provides an automobile safety early warning system, includes cloud platform and a plurality of vehicle mounted terminal, unmanned aerial vehicle, the monitor terminal who carries out communication connection with the cloud platform, the cloud platform acquires vehicle mounted terminal and unmanned aerial vehicle's data and handles and categorised the back, sends monitor terminal. The invention has the beneficial effects that: data parameters acquired by the vehicle-mounted terminal and the unmanned aerial vehicle and a pre-stored multi-parameter classifier are classified and calculated in a one-to-one correspondence mode through the cloud platform, fatigue states and fatigue grades of drivers are obtained, fatigue early warning is generated and sent to the monitoring terminal, a comprehensive management platform which collects multiple vehicles and multiple drivers to carry out fatigue monitoring and early warning simultaneously is formed, real-time monitoring is facilitated, working efficiency is improved, and preparation is also made for follow-up emergency scheduling.
Description
Technical Field
The invention relates to the field of vehicle driving early warning, in particular to an automobile safety early warning system and a weighting early warning method.
Background
The driver is easy to fatigue after keeping the driving state for a long time, serious accidents are easy to happen to fatigue driving, whether the driver is in the fatigue state or not is effectively monitored, and the driver is reminded when the driver is in the fatigue state, so that the accidents can be effectively prevented.
Various technologies for detecting fatigue driving of a driver exist currently, such as fatigue driving detection technology based on facial expression recognition, fatigue driving detection technology based on continuous driving time monitoring, fatigue driving detection technology based on vehicle data, and the like. The fatigue driving detection method is suitable for fatigue detection of a single driver, is not suitable for monitoring fatigue driving of a plurality of vehicles, and currently lacks a comprehensive management platform for simultaneous fatigue monitoring and early warning of a plurality of vehicles and a plurality of drivers.
Disclosure of Invention
Aiming at the defects in the technology, the invention provides an automobile safety early warning system and a weighting early warning method, and the specific scheme is as follows:
the utility model provides an automobile safety early warning system, includes cloud platform and a plurality of vehicle mounted terminal, unmanned aerial vehicle, the monitor terminal who carries out communication connection with the cloud platform, the cloud platform acquires vehicle mounted terminal and unmanned aerial vehicle's data and handles and categorised the back, sends monitor terminal.
Specifically, the data acquired by the cloud platform include head motion parameters, eye motion parameters, facial feature parameters, driving parameters, continuous steering wheel non-operation time and lane line deviation parameters.
Specifically, the vehicle-mounted terminal comprises a terminal main board, and a communication device, a camera, an angle sensor and a navigation positioning device which are respectively connected with corresponding pins of the terminal main board.
Specifically, the cloud platform comprises a cloud platform controller, and a multi-parameter classifier, a computing unit, an early warning unit, a timing unit and a communication unit which are respectively connected with corresponding pins of the cloud platform controller.
Specifically, the multi-parameter classifier includes:
the head action classifier is used for processing and classifying the head and outputting the action of nodding;
the eye motion classifier is used for processing and classifying the eye motion and outputting the motion of eyes which are closed or blinked or opened;
the facial action classifier is used for processing and classifying facial actions and outputting actions of mouth opening or yawning;
and the lane departure classifier is used for processing and classifying the vehicle navigation route and the vehicle real-time route and outputting whether the lane departs.
Specifically, the monitoring terminal comprises a monitoring terminal controller, and an operation monitoring unit, a command scheduling unit and an information interaction unit which are respectively connected with corresponding pins of the monitoring terminal controller.
The weighted early warning method for the automobile early warning system comprises the following steps:
s1, the cloud platform judges the results of the multiple classifiers,
head motion fatigue state Q1: when the head action classifier outputs the nodding action, Q1 is equal to 1, and when the head action classifier does not output the nodding action, Q1 is equal to 0;
eye movement fatigue state Q2: the eye movement classifier outputs Q2 being 1 when closing the eyes, Q2 being 0.5 when blinking, and Q2 being 0 when opening the eyes;
facial movement fatigue state Q3: the facial motion classifier outputs Q3 being 1 when the action is yawning, Q3 being 0.5 when the action is mouth opening, and Q3 being 0 when the action is not output;
lane departure fatigue state Q4: the output of the lane departure classifier is that Q4 is equal to 1 when the lane departs, and the output is that Q4 is equal to 0 when the lane does not depart;
s2, performing weighted budgeting on the judged result,
fatigue state value Q-Q1 × n1+ Q2 × n2+ Q3 × n3+ Q4 × n 4;
wherein n1, n2, n3 and n4 are corresponding weight factors, and n1+ n2+ n3+ n4 is 1;
and S3, grading the fatigue state.
Specifically, in step S3, the fatigue states are set in stages as: q is less than 0.25 and is in a normal state;
q is more than or equal to 0.25 and less than or equal to 0.5, which is first-grade fatigue;
q is more than 0.5 and less than or equal to 0.75, which is secondary fatigue;
q is more than 0.75 and less than or equal to 1, and is the third-level fatigue.
Specifically, step S4 follows step S3, and step S4 specifically includes:
s41, acquiring real-time dynamic driving images of the current vehicle and the adjacent vehicle;
s42, calculating the real-time route and the real-time position of the vehicle to obtain a safe distance;
and S43, sending early warning scheduling information to the vehicles with the distance less than the safe distance.
Specifically, the early warning scheduling information includes: fatigue state, fatigue grade, scheduling instructions; the scheduling instructions include: deceleration, acceleration, left lane change and right lane change.
The invention has the beneficial effects that:
(1) head motion parameters acquired by the vehicle-mounted terminal and the unmanned aerial vehicle through the cloud platform, eye motion parameters, facial feature parameters, driving parameters, continuous steering wheel non-operation time, lane line deviation parameters and a pre-stored multi-parameter classifier are classified and calculated in a one-to-one correspondence mode, the fatigue state and the fatigue grade of a driver are obtained, fatigue early warning is generated and sent to the monitoring terminal, a comprehensive management platform which integrates multiple vehicles and multiple drivers to perform fatigue monitoring and early warning simultaneously is formed, real-time monitoring is facilitated, working efficiency is improved, and preparation is also made for follow-up emergency scheduling.
(2) Through the position and the motion state of obtaining adjacent vehicle, set up safe distance and schedule adjacent vehicle, realize many vehicles, many drivers fatigue monitoring simultaneously and early warning dispatch, improve the security of trip.
(3) By collecting the parameters of the head, the eyes, the face, the driving parameters, the time of continuously not operating the steering wheel and the lane line deviation for comparison, whether the driver is in a fatigue state can be accurately obtained, and errors are reduced.
(4) By arranging the unmanned aerial vehicle, the vehicle navigation route inaccuracy of real-time positioning and route planning caused by the damage or fault of the navigation equipment is avoided, the accurate judgment of whether the vehicle drifts is effectively improved, and accurate data support is provided for further fatigue driving judgment.
Drawings
For clarity of illustration. Embodiments of the present invention or technical solutions in the prior art will be briefly described below with reference to the drawings used in the description of the embodiments or the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic diagram of the system of the present invention;
FIG. 2 is a flow chart of the method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention discloses an automobile safety early warning system and a weighted early warning method;
the utility model provides an automobile safety early warning system, includes cloud platform and a plurality of vehicle mounted terminal, unmanned aerial vehicle, the monitor terminal who carries out communication connection with the cloud platform, the cloud platform acquires vehicle mounted terminal and unmanned aerial vehicle's data and handles and categorised the back, sends monitor terminal.
The data obtained by the cloud platform comprises: head motion parameters, eye motion parameters, facial feature parameters, driving parameters, continuous steering wheel non-operation time, lane line deviation parameters.
The head motion parameters include: nodding action amplitude and nodding action time; the eye movement parameters include: eye closing time, eye blinking frequency, eye blinking speed, eye opening amplitude and eye watching direction conversion frequency; the facial feature parameters include: opening the mouth and punching yawning times; the driving characteristic parameters include: continuous driving time and total driving time all day; the lane line deviation parameter includes: lane line deviation times and lane line deviation duration.
The vehicle-mounted terminal comprises a terminal mainboard and a plurality of pins connected with the terminal mainboard: communication equipment, camera, angle sensor, navigation positioning equipment.
The cloud platform comprises a cloud platform controller, and a multi-parameter classifier, a computing unit, an early warning unit, a timing unit and a communication unit which are respectively connected with corresponding pins of the cloud platform controller.
The multi-parameter classifier includes: the head action classifier is used for processing and classifying head actions and outputting head nodding actions; the eye motion classifier is used for processing and classifying the eye motion and outputting the motion of eyes which are closed or blinked or opened; a facial motion classifier; the device is used for processing and classifying facial actions and outputting actions of mouth opening or yawning; and the lane departure classifier is used for processing and classifying the vehicle navigation route and the vehicle real-time route and outputting whether the lane departs.
The monitoring terminal comprises a monitoring terminal controller, and an operation monitoring unit, a command scheduling unit and an information interaction unit which are respectively connected with corresponding pins of the monitoring terminal controller.
The weighted early warning method for the automobile early warning system comprises the following steps:
s1, the cloud platform judges the results of the multiple classifiers,
head motion fatigue state Q1: when the head action classifier outputs the nodding action, Q1 is equal to 1, and when the head action classifier does not output the nodding action, Q1 is equal to 0;
eye movement fatigue state Q2: the eye movement classifier outputs Q2 being 1 when closing the eyes, Q2 being 0.5 when blinking, and Q2 being 0 when opening the eyes;
facial movement fatigue state Q3: the facial motion classifier outputs Q3 being 1 when the action is yawning, Q3 being 0.5 when the action is mouth opening, and Q3 being 0 when the action is not output;
lane departure fatigue state Q4: the output of the lane departure classifier is that Q4 is equal to 1 when the lane departs, and the output is that Q4 is equal to 0 when the lane does not depart;
s2, performing weighted budgeting on the judged result,
fatigue state value Q-Q1 × n1+ Q2 × n2+ Q3 × n3+ Q4 × n 4;
wherein n1, n2, n3 and n4 are corresponding weight factors, and n1+ n2+ n3+ n4 is 1;
s3, carrying out fatigue state grading, wherein Q is less than 0.25 and is a normal state;
q is more than or equal to 0.25 and less than or equal to 0.5, which is first-grade fatigue;
q is more than 0.5 and less than or equal to 0.75, which is secondary fatigue;
q is more than 0.75 and less than or equal to 1, and is the third-level fatigue.
Step S4 follows step S3, and step S4 specifically includes:
s41, acquiring real-time dynamic driving images of the current vehicle and the adjacent vehicle;
s42, calculating the real-time route and the real-time position of the vehicle to obtain a safe distance;
and S43, sending early warning scheduling information to the vehicles with the distance less than the safe distance.
The early warning scheduling information includes: fatigue state, fatigue grade, scheduling instructions; the scheduling instructions include: deceleration, acceleration, left lane change and right lane change.
Example 1
As shown in fig. 1, an embodiment of the present invention provides an automobile safety early warning system, which includes a plurality of vehicle-mounted terminals, a cloud platform, an unmanned aerial vehicle, and a monitoring terminal.
The plurality of vehicle-mounted terminals are respectively and correspondingly arranged on the plurality of vehicles; every vehicle terminal includes the terminal mainboard and corresponds pin with the terminal mainboard and be connected: communication equipment, camera, angle sensor, navigation positioning equipment. The camera is used for collecting real-time images of the face, the angle sensor is used for collecting real-time rotation angles of the steering wheel, and the navigation positioning equipment is used for real-time positioning and navigation.
The cloud platform is connected to the plurality of vehicle-mounted terminals in a communication mode and used for data receiving, sending, processing and early warning.
The unmanned aerial vehicle is in communication connection with the cloud platform and used for respectively acquiring real-time dynamic driving images of a plurality of vehicles. The monitoring terminal is in communication connection with the cloud platform and used for respectively acquiring real-time running states and early warning information of the vehicles.
The cloud platform comprises a cloud platform controller, and a multi-parameter classifier, a computing unit, an early warning unit, a timing unit and a communication unit which are respectively connected with corresponding pins of the cloud platform controller. And the calculating unit is used for carrying out weighted calculation according to the results after one-by-one classification by the multi-parameter classifier to obtain whether the driver is in a fatigue state and the fatigue grade. The early warning unit is used for acquiring the fatigue state and the fatigue grade of the driver, generating a fatigue early warning and sending the fatigue early warning to the monitoring terminal for displaying and early warning. The timing unit is used for timing the nodding action time, the eye closing time, the blinking time, the continuous driving time, the total day accumulated driving time, the continuous steering wheel non-operation time and the lane line deviation time, and provides timing data reference for fatigue state judgment.
The monitoring terminal comprises a monitoring terminal controller, and an operation monitoring unit, a command scheduling unit and an information interaction unit which are respectively connected with corresponding pins of the monitoring terminal controller. The operation monitoring unit is used for acquiring real-time operation states and early warning information of a plurality of vehicles from the cloud platform to display, and provides functions of real-time operation state monitoring and early warning. And the commanding and scheduling unit is used for acquiring real-time running states and early warning information of other adjacent vehicles from the running monitoring unit to carry out influence range analysis and scheduling analysis when the vehicle is determined to be fatigue driving, and sending the scheduling information and the fatigue state and grade of the current vehicle to the adjacent vehicles in the influence range to carry out early warning and avoidance. The monitor terminal is intelligent terminal equipment, includes: PC, panel computer, cell-phone.
The system starts to work, the cloud platform obtains the real-time facial image from the vehicle-mounted terminal and performs image processing to obtain head movement parameters, eye movement parameters, facial feature parameters and driving parameters in unit time. The cloud platform acquires the real-time rotation angle of the steering wheel from the angle sensor and performs data analysis to acquire the time of continuously not operating the steering wheel. The cloud platform compares the vehicle navigation route acquired from the navigation device with the vehicle real-time route acquired from the vehicle real-time dynamic driving image to acquire a lane line deviation parameter in unit time.
The cloud platform performs one-to-one corresponding classification and calculation according to the acquired head motion parameters, eye motion parameters, facial feature parameters, driving parameters, continuous steering wheel non-operation time and lane line deviation parameters in unit time and a pre-stored multi-parameter classifier to obtain whether a driver is in a fatigue state, a fatigue grade and fatigue early warning, and sends the fatigue early warning to the monitoring terminal for displaying and early warning; the parameters of the head, the eyes, the face, the driving parameters, the time for continuously not operating the steering wheel and the lane line deviation are compared, so that whether the driver is in a fatigue state or not can be accurately obtained, and the error is reduced; compared with the real-time positioning and vehicle navigation route of single navigation equipment, the unmanned aerial vehicle is added, the acquired real-time dynamic driving image of the vehicle is subjected to image processing, the acquired real-time route of the vehicle is compared with the real-time positioning and vehicle navigation route acquired by the navigation equipment, the inaccuracy of the vehicle navigation route of real-time positioning and route planning caused by the damage or failure of the navigation equipment is avoided, the accurate judgment of whether the vehicle drifts is effectively improved, and accurate data support is provided for further fatigue driving judgment.
The cloud platform generates early warning information and sends the early warning to the monitor terminal to display, the cloud platform communicates with a plurality of vehicle terminals, the unmanned aerial vehicle and the monitor terminal respectively, a comprehensive management platform which collects a plurality of vehicles and a plurality of drivers to carry out fatigue monitoring and early warning simultaneously is formed, real-time monitoring is facilitated, working efficiency is improved, and preparation is also made for follow-up emergency scheduling.
The head motion parameters comprise nodding motion amplitude and nodding motion time; the eye movement parameters comprise eye closing time, eye blinking frequency, eye blinking speed, eye opening amplitude and eye gazing direction conversion frequency; the facial feature parameters comprise the times of yawning by opening mouth; the driving parameters comprise the continuous driving time length and the total day accumulated driving time length; the lane line deviation parameters include the number of lane line deviations and the lane line deviation duration.
Whether the head has a fatigue state is reflected by setting the head nodding action amplitude and the head nodding action time; setting the eye closing time, the eye blinking frequency, the eye blinking speed, the eye opening amplitude and the eye watching direction conversion frequency to reflect whether the eyes are in a fatigue state or not; setting the times of yawning by opening mouth to reflect whether the face has a fatigue state; setting continuous driving time length and total day accumulated driving time length to reflect whether the driver has fatigue driving history; the setting includes the number of lane line deviations and the lane line deviation duration to reflect whether the lane line is deviated or not to further reflect whether the driver enters a fatigue state or not.
Example 2
On the basis of the system described in embodiment 1, in order to perform accurate calculation better, as shown in fig. 2, the present invention provides a weighted early warning method for the above system.
S1, determining a classification result of the multiple classifiers, wherein if the output result of the head motion classifier is a nodding motion, Q1 is equal to 1, otherwise Q1 is equal to 0; if the output result of the eye motion classifier is eye closing motion, Q2 is 1; if the output result of the eye movement classifier is a blinking movement, Q2 is 0.5; if the output result of the eye motion classifier is an opening motion, Q2 is equal to 0; if the output result of the facial motion classifier is yawning, Q3 is 1; if the output result of the facial movement classifier is mouth opening, Q3 is equal to 0.5; if the facial motion classifier has no output result, Q3 is equal to 0; if the output result of the lane departure classifier is departure, Q4 is equal to 1, otherwise Q4 is equal to 0;
s2, a weighting calculation is performed, and the fatigue state value Q is head motion fatigue state Q1 × n1+ eye motion fatigue state Q2 × n2+ face motion fatigue state Q3 × n3+ lane departure fatigue state Q4 × n 4.
Wherein n1, n2, n3 and n4 are corresponding weight factors, and n1+ n2+ n3+ n4 is 1;
s3, in order to judge the fatigue state better and perform fatigue grade division more accurately, Q < 0.25 is preferably defined as a normal state; q is more than or equal to 0.25 and less than or equal to 0.5, which is first-grade fatigue; q is more than 0.5 and less than or equal to 0.75, which is secondary fatigue; q is more than 0.75 and less than or equal to 1, and is the third-level fatigue.
By the method, the computing unit of the cloud platform is set to perform weighted computation according to the classification result of the multi-parameter classifier, so that the accuracy of fatigue state judgment is further improved, the fatigue grade is quantitatively given, and data reference and support are provided for subsequent fatigue early warning and safety scheduling.
And wireless communication modes are preferably adopted among the cloud platform, the plurality of vehicle-mounted terminals, the unmanned aerial vehicle and the monitoring terminal.
And S41, the monitoring terminal acquires real-time dynamic driving images of the current vehicle and the adjacent vehicles through the cloud platform.
And S42, calculating the real-time route and the real-time position of the vehicle according to the real-time dynamic driving images of the current vehicle and the adjacent vehicles to obtain the safe distance, and marking the adjacent vehicles with the real-time distance smaller than the safe distance.
S43, sending early warning scheduling information to adjacent vehicles with a safety distance, wherein the early warning information comprises the following specific steps: fatigue state, fatigue grade; the scheduling information includes: deceleration, acceleration, left lane change and right lane change.
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. The utility model provides an automobile safety early warning system, its characterized in that, includes cloud platform and a plurality of vehicle mounted terminal, unmanned aerial vehicle, monitor terminal who carries out communication connection with the cloud platform, the cloud platform acquires vehicle mounted terminal and unmanned aerial vehicle's data and handles and categorised back, sends monitor terminal.
2. The automobile safety pre-warning system according to claim 1, wherein the data acquired by the cloud platform comprises head motion parameters, eye motion parameters, facial feature parameters, driving parameters, continuous steering wheel non-operation time and lane line deviation parameters.
3. The automobile safety early warning system according to claim 1, wherein the vehicle-mounted terminal comprises a terminal main board, and a communication device, a camera, an angle sensor and a navigation positioning device which are respectively connected with corresponding pins of the terminal main board.
4. The automobile safety early warning system according to claim 1, wherein the cloud platform comprises a cloud platform controller, and a multi-parameter classifier, a computing unit, an early warning unit, a timing unit and a communication unit which are respectively connected with corresponding pins of the cloud platform controller.
5. The vehicle safety precaution system of claim 4, wherein the multi-parameter classifier comprises:
the head action classifier is used for processing and classifying the head and outputting the action of nodding;
the eye motion classifier is used for processing and classifying the eye motion and outputting the motion of eyes which are closed or blinked or opened;
the facial action classifier is used for processing and classifying facial actions and outputting actions of mouth opening or yawning;
and the lane departure classifier is used for processing and classifying the vehicle navigation route and the vehicle real-time route and outputting whether the lane departs.
6. The automobile safety early warning system according to claim 1, wherein the monitoring terminal comprises a monitoring terminal controller, and an operation monitoring unit, a commanding and scheduling unit and an information interaction unit which are respectively connected with corresponding pins of the monitoring terminal controller.
7. The weighted early warning method for the automobile safety early warning system according to claims 1 to 6, characterized by comprising the steps of:
s1, the cloud platform judges the results of the multiple classifiers,
head motion fatigue state Q1: when the head action classifier outputs the nodding action, Q1 is equal to 1, and when the head action classifier does not output the nodding action, Q1 is equal to 0;
eye movement fatigue state Q2: the eye movement classifier outputs Q2 being 1 when closing the eyes, Q2 being 0.5 when blinking, and Q2 being 0 when opening the eyes;
facial movement fatigue state Q3: the facial motion classifier outputs Q3 being 1 when the action is yawning, Q3 being 0.5 when the action is mouth opening, and Q3 being 0 when the action is not output;
lane departure fatigue state Q4: the output of the lane departure classifier is that Q4 is equal to 1 when the lane departs, and the output is that Q4 is equal to 0 when the lane does not depart;
s2, performing weighted budgeting on the judged result,
fatigue state value Q-Q1 × n1+ Q2 × n2+ Q3 × n3+ Q4 × n 4;
wherein n1, n2, n3 and n4 are corresponding weight factors, and n1+ n2+ n3+ n4 is 1;
and S3, grading the fatigue state.
8. The weighted early warning method of claim 7, wherein the fatigue status of step S3 is graded as: q is less than 0.25 and is in a normal state;
q is more than or equal to 0.25 and less than or equal to 0.5, which is first-grade fatigue;
q is more than 0.5 and less than or equal to 0.75, which is secondary fatigue;
q is more than 0.75 and less than or equal to 1, and is the third-level fatigue.
9. The weighted early warning method according to claim 7, wherein step S4 is further provided after step S3, and step S4 specifically comprises:
s41, acquiring real-time dynamic driving images of the current vehicle and the adjacent vehicle;
s42, calculating the real-time route and the real-time position of the vehicle to obtain a safe distance;
and S43, sending early warning scheduling information to the vehicles with the distance less than the safe distance.
10. The weighted early warning method of claim 9, wherein the early warning scheduling information comprises: fatigue state, fatigue grade, scheduling instructions; the scheduling instructions include: deceleration, acceleration, left lane change and right lane change.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110557470.8A CN113313913A (en) | 2021-05-21 | 2021-05-21 | Automobile safety early warning system and weighting early warning method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110557470.8A CN113313913A (en) | 2021-05-21 | 2021-05-21 | Automobile safety early warning system and weighting early warning method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113313913A true CN113313913A (en) | 2021-08-27 |
Family
ID=77374062
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110557470.8A Withdrawn CN113313913A (en) | 2021-05-21 | 2021-05-21 | Automobile safety early warning system and weighting early warning method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113313913A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117351648A (en) * | 2023-10-08 | 2024-01-05 | 海南大学 | Driver fatigue monitoring and early warning method and system |
-
2021
- 2021-05-21 CN CN202110557470.8A patent/CN113313913A/en not_active Withdrawn
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117351648A (en) * | 2023-10-08 | 2024-01-05 | 海南大学 | Driver fatigue monitoring and early warning method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110770084B (en) | Vehicle monitoring system and vehicle monitoring method | |
CN204515511U (en) | Cultivating one monitoring system built by bridge | |
CN107943046B (en) | Method and system for handing over human-machine control right of automatic driving vehicle | |
CN105354988B (en) | A kind of driver tired driving detecting system and detection method based on machine vision | |
Chen et al. | Driving behavior analysis based on vehicle OBD information and adaboost algorithms | |
CN101950355B (en) | Method for detecting fatigue state of driver based on digital video | |
CN110866427A (en) | Vehicle behavior detection method and device | |
CN109803127A (en) | Urban safety building site monitoring system and method based on big data and technology of Internet of things | |
CN111964922A (en) | Intelligent driving vehicle test system | |
CN112071061A (en) | Vehicle service system based on cloud computing and data analysis | |
CN108609019A (en) | A kind of electric vehicle automatic Pilot method based on artificial intelligence platform | |
CN109031251A (en) | A kind of automobile mounted sensor fault automatic testing method and device | |
CN110097783A (en) | Vehicle early warning method and system | |
CN111845736A (en) | Vehicle collision early warning system triggered by distraction monitoring and control method | |
CN112289031A (en) | Method and device for detecting and alarming abnormal conditions in bus driving process | |
CN110781872A (en) | Driver fatigue grade recognition system with bimodal feature fusion | |
CN113313913A (en) | Automobile safety early warning system and weighting early warning method | |
CN112949457A (en) | Maintenance method, device and system based on augmented reality technology | |
CN115782905A (en) | Automatic driving vehicle driving safety degree quantification system | |
CN111881952A (en) | Driver tendency analysis method based on early warning big data | |
CN115384540A (en) | Vehicle-mounted safe driving detection device | |
CN115762169A (en) | Intelligent control system and method for unmanned driving of sanitation vehicle | |
CN114633774A (en) | Rail transit fault detection system based on artificial intelligence | |
CN112698660B (en) | Driving behavior visual perception device and method based on 9-axis sensor | |
WO2023108364A1 (en) | Method and apparatus for detecting driver state, and storage medium |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210827 |