CN212484555U - Fatigue driving multi-source information detection system - Google Patents
Fatigue driving multi-source information detection system Download PDFInfo
- Publication number
- CN212484555U CN212484555U CN202021461891.8U CN202021461891U CN212484555U CN 212484555 U CN212484555 U CN 212484555U CN 202021461891 U CN202021461891 U CN 202021461891U CN 212484555 U CN212484555 U CN 212484555U
- Authority
- CN
- China
- Prior art keywords
- acquisition module
- information
- fatigue
- detection system
- fatigue driving
- 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
Abstract
The utility model discloses a driver fatigue multisource information detecting system, including facial feature acquisition module, physiology feature acquisition module, vehicle signal acquisition module, controller and early warning execution module. The facial feature acquisition module acquires driving time, eyelid closing degree, blinking frequency and mouth opening degree information of a driver; the physiological characteristic acquisition module acquires heart rate and blood pressure information of a driver; the vehicle signal acquisition module acquires the running time of a vehicle, the steering wheel corner, a steering lamp and transverse displacement information; the controller receives and processes the information of each module, and comprehensively judges the fatigue degree. The utility model discloses having fused multisource information and having carried out driver fatigue degree and judge, having and detecting more comprehensive, judge more accurate advantage.
Description
Technical Field
The utility model relates to a driver fatigue multisource information detection system belongs to car safety and driver fatigue control technical field.
Background
Fatigue refers to a phenomenon of human body characterization in which the functional response is weakened due to excessive consumption of brain, muscles, or other organs, and driving a vehicle in a fatigue state is called fatigue driving. After fatigue, the physiological state of the driver changes and influences the driving behavior, and road traffic accidents are easy to happen.
At present, effective detection of fatigue driving through multiple technologies already has corresponding theoretical research foundation and technical feasibility, but in actual complex and changeable driving environments, the method has certain limitations, low accuracy and serious misinformation and misreport by only depending on various single technologies and methods. The fatigue driving monitoring based on the facial features of the driver is based on the continuous closing time of the eyes and the PERCLOS principle, and is technically mature. Fatigue driving monitoring based on physiological characteristics of a driver needs contact measurement, normal driving is affected, and monitoring conditions are harsh. The fatigue driving monitoring based on the operation characteristics of the driver and the driving state of the vehicle does not need to add excessive hardware equipment, does not cause interference to normal driving of the driver, has higher accuracy under partial working conditions, is influenced by personal habits and skill differences, vehicle characteristics and road environment, and cannot realize full-working-condition and high-accuracy detection.
The mutual fusion of multiple technologies is an effective means for realizing the fatigue driving detection under all working conditions at high accuracy, the complementarity and the redundancy among different information are fully utilized, the reliability and the fault-tolerant capability of the system are improved, and the defects among different technologies can be overcome.
Disclosure of Invention
Therefore, the utility model provides a fatigue driving multisource information detecting system fuses the index of a plurality of dimensions such as driver's characteristic and vehicle travel state to reliability based on the index fuses the judgement, makes the judgement result more accurate, comprehensive.
The utility model discloses the technical scheme who takes as follows: a fatigue driving multi-source information detection system comprises a facial feature acquisition module, a physiological feature acquisition module, a vehicle signal acquisition module, a controller and an early warning execution module;
the facial feature acquisition module is used for acquiring the driving time length, the eyelid closing degree, the blinking frequency and the opening degree information of a driver;
the physiological characteristic acquisition module is used for acquiring heart rate and blood pressure information of a driver;
the vehicle signal acquisition module acquires the running time of a vehicle, the steering wheel corner, a steering lamp and transverse displacement information in real time;
the controller transmits signals with the facial feature acquisition module, the physiological feature acquisition module and the vehicle signal acquisition module in a wired or wireless mode, receives and processes the information of the modules in real time, and comprehensively judges the fatigue degree.
Further, the facial feature acquisition module selects an infrared vision sensor and is installed at the A column of the cab.
Further, the physiological characteristic acquisition module is integrated on wearing the bracelet.
Furthermore, the lateral displacement information is collected and transmitted to the vehicle signal collection module by a road side unit, or is directly obtained by a vehicle-mounted positioning sensor in the vehicle signal collection module.
Further, an information processing module and a fusion judging module are preset in the controller.
Further, the controller calculates the continuous eye closing time through the eyelid closing degree information, wherein the continuous eye closing time is a time period for driving the eyes to have eyelid closing continuously exceeding 90%.
Further, the controller performs PERCLOS value calculation according to the eyelid closing degree information, and the PERCLOS value is calculated according to P80.
Further, the blink frequency is an action of more than 90% of eyelid closure and more than 500ms, but not more than 2s within a certain time window.
Further, the controller calculates the frequency of yawning within a certain time window according to the eyelid closing degree information and the oral opening degree information, wherein the yawning is an action that the eyelid closing exceeds 90% and the oral opening exceeds 90%.
Further, the controller calculates a lateral displacement index within a certain time window according to the lateral displacement information, the lateral displacement index is used for averaging N pieces of lateral displacement data, then calculating a standard deviation, and then calculating a ratio of the standard deviation to the vehicle width.
The utility model has the advantages that: the utility model provides a driver detection system tired has fused long, facial feature, physiological feature and vehicle signal multidimension degree index when driving in succession to based on the reliability of index, judge fatigue degree, have and detect more comprehensively, judge more accurate advantage, for prior art, very big reduction leak report rate, wrong report rate.
Drawings
Fig. 1 is a schematic diagram of the system of the present invention.
Detailed Description
The present invention is described in detail with reference to the accompanying drawings and examples, which are used for explaining the present invention, but it should be understood by those skilled in the art that the following examples are not the only limitations of the present invention, and all equivalent changes and modifications made in the spirit of the present invention should be considered as belonging to the protection scope of the present invention.
The utility model provides a driver fatigue multisource information detecting system, including several following functional modules: the system comprises a facial feature acquisition module 1, a physiological feature acquisition module 2, a vehicle signal acquisition module 3, a controller 4 and an early warning execution module 5.
The facial feature acquisition module 1 selects an infrared vision sensor, is installed at the column A of the cab, acquires facial images of a driver in real time in a vision perception mode, acquires information such as eyelid closing degree, blink frequency and mouth opening degree, and identifies the identity of the driver based on machine vision.
Physiological characteristic collection module 2, the integration is on wearing the bracelet, information such as the rhythm of the heart of the real-time collection driver, blood pressure.
And the vehicle signal acquisition module 3 is used for acquiring the running time of the vehicle, the steering wheel corner, the steering lamp and the transverse displacement information in real time. The lateral displacement information can be collected and transmitted to the vehicle signal acquisition module by a road side unit based on a vehicle-road cooperation technology, or directly acquired by a vehicle-mounted positioning sensor in the vehicle signal acquisition module.
The controller 4 is in signal transmission with the facial feature acquisition module 1, the physiological feature acquisition module 2 and the vehicle signal acquisition module 3 in a wired or wireless mode, receives information acquired by the modules in real time, is preset with an information processing module and a fusion judgment module in the controller 4, processes the information and makes decision judgment.
The early warning execution module 5 can be composed of an alarm lamp and an alarm horn, and the controller 4 sends out early warning after making a judgment result by the early warning execution module 5. The controller 4 and the early warning execution module 5 are connected in a wired or wireless manner.
The controller 4 has data processing capabilities including:
the driver continuous driving time length is calculated by receiving the driver identity information, the calculation is started when the driver gets on the vehicle and the image acquisition is started by the surface characteristic acquisition module 1, and the time length of the acquired image is recorded as the driving time length of the driver until the vehicle stops getting off the vehicle.
And calculating the total daily accumulated driving time length of the driver by receiving the identity information of the driver, and recording the total daily accumulated time length for collecting the same driver image as the total daily accumulated driving time length of the driver.
And calculating the continuous eye closing time by receiving the eyelid closing degree information, wherein the continuous eye closing time is a time period for driving the eyelids of the eyes to be closed continuously for more than 90%.
By receiving eyelid closure degree information, a calculation of blink frequency within a certain time window is performed, blink being defined as an action of more than 90% eyelid closure and lasting more than 500ms, but not more than 2 s. The blink frequency may be calculated as a 1min time window.
And (3) carrying out PERCLOS value calculation by receiving eyelid closing degree information, wherein the PERCLOS value is calculated according to P80, and P80 refers to the time accounting for more than 80% of eyelid closing in a certain time.
By receiving the eyelid closing degree information and the oral opening degree information, the frequency of yawning is calculated within a certain time window, the yawning is the action that the eyelid is closed by more than 90 percent, meanwhile, the oral opening is opened by more than 90 percent, and the frequency of yawning can be calculated according to the time window of 5 min.
The time for which the steering wheel is not operated continuously is calculated by receiving the steering wheel angle information, and the steering wheel is considered to be not operated when the steering wheel angle information is not received.
And calculating the absolute value of the steering wheel angular velocity by receiving the steering wheel angle information and the steering lamp information.
By receiving the transverse displacement information, calculating the transverse displacement index in a certain time window, wherein the calculation method comprises the following steps:
step 1: defining the transverse displacement refers to the relative offset between the central line of the vehicle and the central line of the lane, and collecting N transverse displacement data L in a certain time windowi，i＝1,2…N；
step 2: calculating the average value L of N pieces of transverse displacement datam：
step 3: calculating the standard deviation L of N pieces of transverse displacement datastd：
step 4: calculating a transverse displacement index D:
the controller 4 makes fusion judgment based on the collected multisource information of the continuous driving time of the driver, the physiological reaction of the driver, the facial representation of the driver, the operation performance of the driver and the driving state of the vehicle, and comprises the following steps:
(1) based on the multi-source information, a fatigue index system is established, see table 1, and the established fatigue indexes include but are not limited to the following 10 items, wherein the threshold value in the 10 items of fatigue indexes can be customized and is generally determined according to long-term accumulated empirical data.
TABLE 1 fatigue index
(2) The fatigue indexes are classified according to the confidence level and the risk degree, and the weight coefficient Pi of each index is set, which is shown in a table 2.
TABLE 2 fatigue index types and weighting coefficients
The confidence coefficient and the risk degree are determined according to long-term experience, the weight coefficient of each fatigue index is taken according to the corresponding value of the confidence coefficient and the risk degree, the higher the confidence coefficient and the risk degree is, the larger the weight coefficient is, and the smaller the weight coefficient is otherwise. For example, for the indicators such as the continuous closed-eye time, the number of blinks, and the lateral displacement, if any one of the indicators is greater than the threshold, a security accident may occur, and the confidence is very high, and therefore, such an indicator weight coefficient is very large for the high-confidence and high-risk indicators; for the indexes such as continuous driving time, total day accumulated driving time and yawning times, although the confidence coefficient is high, even if the driving time is very long or the yawning times are many, the individual difference is not very large in possible risk, so that the indexes are set as high-confidence and low-risk indexes, and the index weight coefficient belongs to a middle level; for the indexes P80, the time when the steering wheel is not operated continuously, the absolute value of the angular velocity of the steering wheel when the turn lamp is turned off, and the heart rate, for example, the confidence is low even if the steering wheel is not operated for a long time or the heart rate is low and is not necessarily fatigue, and the index is a low confidence index and a low risk index because there is no risk even if the steering wheel is not operated continuously or the heart rate is low, the weight coefficient is small.
(3) And calculating the fatigue degree index Fi based on the fatigue indexes exceeding the threshold value and the corresponding weight coefficients Pi.
And N is the number of terms of the overproof fatigue index.
(4) And determining the fatigue degree according to the calculated fatigue degree index Fi based on a fatigue degree grading table embedded in the system, and referring to a table 3.
TABLE 3 fatigue level-defining table
| Serial number | Degree of fatigue | Fatigue index Fi range |
| 1 | Sobering up | 0＜Fi＜S1 |
| 2 | Slight fatigue | S1≤Fi＜S2 |
| 3 | Moderate fatigue | S2≤Fi＜S3 |
| 4 | Severe fatigue | Fi≥S3 |
As can be seen from table 3, the fatigue index Fi falls within which limit interval, and belongs to which fatigue level. The fatigue degree grade can be divided by self-definition, for example, the grade can be divided into four grades in a table 3, can also be simply divided into three grades, and can also be divided into five grades in a complex way.
The fatigue degree limit value Si in table 3 is set by self-definition, and is only a relative weighing value, and has no specific value limitation, and has no specific numerical value meaning, and is only to distinguish the correlation between the fatigue degree grades, for example, the order of magnitude can be taken as 1 or less, the order of magnitude can be taken as 10 or less, the order of magnitude can be taken as 100 or less, and it is only required to ensure that S1 is greater than S2 is greater than S3 …, and the value is taken from small to large according to the fatigue degree.
Because the fatigue degree grade is determined according to the fatigue degree limit value interval to which the fatigue degree index Fi belongs, and the fatigue degree index Fi is the sum of the weight coefficients Pi, the value range of the weight coefficient Pi is actually determined according to the fatigue degree limit value, the value range of any weight coefficient Pi is more than 0 and less than or equal to Smax, and Smax refers to the maximum limit value in the fatigue degree grade table. Similarly, the weight coefficient is only a relative measure value, and is not related to the magnitude of the value itself.
The following is a specific operational example:
the following threshold values of various fatigue indexes are set: the continuous eye closing time is 2s, the blink frequency in the 1min time window is 10 times, the transverse displacement index in the 1min time window is 0.1, the continuous driving time in the daytime is 4h or the continuous driving time at night (22 hours-6 days) is 2h, the cumulative driving time in the whole day is 8h, the yawning frequency in the 5min time window is 3 times, the P80 value of PERCLOS is 0.2, the time of continuously not operating the steering wheel is 4s, the absolute value of the angular velocity of the steering wheel when the steering lamp is turned off is 8 degrees/s, and the heart rate is 80% of the standard value. When the indexes exceed respective thresholds, it is considered that fatigue signs appear.
And further determining the confidence coefficient and the risk degree of each index for each fatigue index, and then assigning a value to the weight coefficient Pi of each index according to the fatigue degree limit value in the fatigue degree grading table. The higher the confidence and the higher the risk degree, the larger the weight coefficient Pi. The upper limit value of each fatigue degree in the fatigue degree grading table is set as follows: when the wakefulness is 1 and the fatigue is generally 6, the minimum value of the weighting factor Pi is 0 < Pi.ltoreq.6. For each item weight coefficient Pi in table 2, the values are given as: p1-6, P2-6, P3-6, P4-1, P5-1, P6-1, P7-0.5, P8-0.5, P9-0.5, and P10-0.5.
According to the weighting coefficients Pi, assuming that indexes D4, D5, D8 and D9 exceed standards, the fatigue degree index Fi is calculated as:
the fatigue degree is determined based on the fatigue degree index Fi and the fatigue degree ranking table, and Fi is 3, which is above the wakefulness upper limit value and below the general fatigue upper limit value, and therefore is general fatigue.
For the judgment of general fatigue, an alarm sound or an indicator light can be sent out by the early warning execution module 5. If the fatigue is determined to be serious, a strong warning alarm sound or an indicator light is emitted.
Claims (10)
1. The utility model provides a fatigue driving multisource information detecting system which characterized in that: the system comprises a facial feature acquisition module, a physiological feature acquisition module, a vehicle signal acquisition module, a controller and an early warning execution module;
the facial feature acquisition module is used for acquiring the driving time length, the eyelid closing degree, the blinking frequency and the opening degree information of a driver;
the physiological characteristic acquisition module is used for acquiring heart rate and blood pressure information of a driver;
the vehicle signal acquisition module is used for acquiring the running time of a vehicle, the steering wheel corner, a steering lamp and transverse displacement information;
the controller transmits signals with the facial feature acquisition module, the physiological feature acquisition module and the vehicle signal acquisition module in a wired or wireless mode, receives and processes the information of the modules in real time, and comprehensively judges the fatigue degree.
2. The fatigue driving multi-source information detection system according to claim 1, wherein: the facial feature acquisition module selects an infrared vision sensor and is installed at the column A of the cab.
3. The fatigue driving multi-source information detection system according to claim 1, wherein: the physiological characteristic acquisition module is integrated on the wearable bracelet.
4. The fatigue driving multi-source information detection system according to claim 1, wherein: the lateral displacement information is collected and transmitted to the vehicle signal collection module by a road side unit, or is directly obtained by a vehicle-mounted positioning sensor in the vehicle signal collection module.
5. The fatigue driving multi-source information detection system according to claim 1, wherein: an information processing module and a fusion judging module are preset in the controller.
6. The fatigue driving multi-source information detection system according to claim 1, wherein: and the controller calculates the continuous eye closing time through the eyelid closing degree information, wherein the continuous eye closing time is a time period in which the eyelid of a driver is continuously closed for more than 90%.
7. The fatigue driving multi-source information detection system according to claim 1, wherein: and the controller performs PERCLOS value calculation according to the eyelid closing degree information, and the PERCLOS value is calculated by P80.
8. The fatigue driving multi-source information detection system according to claim 1, wherein: the blink frequency is an action of more than 90% of eyelid closure and more than 500ms, but not more than 2s within a certain time window.
9. The fatigue driving multi-source information detection system according to claim 1, wherein: the controller carries out calculation of the yawning times within a certain time window through the eyelid closing degree information and the oral opening degree information, and the yawning is the action that the eyelid is closed by more than 90% and the oral opening is opened by more than 90%.
10. The fatigue driving multi-source information detection system according to claim 1, wherein: and the controller calculates a transverse displacement index in a certain time window according to the transverse displacement information, the transverse displacement index is used for averaging N transverse displacement data, then calculating a standard deviation and then calculating a ratio of the standard deviation to the vehicle width.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202021461891.8U CN212484555U (en) | 2020-07-22 | 2020-07-22 | Fatigue driving multi-source information detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202021461891.8U CN212484555U (en) | 2020-07-22 | 2020-07-22 | Fatigue driving multi-source information detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN212484555U true CN212484555U (en) | 2021-02-05 |
Family
ID=74452515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202021461891.8U Active CN212484555U (en) | 2020-07-22 | 2020-07-22 | Fatigue driving multi-source information detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN212484555U (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113183968A (en) * | 2021-04-25 | 2021-07-30 | 前海七剑科技(深圳)有限公司 | Anti-fatigue driving method, device, equipment and storage medium |
| CN113643512A (en) * | 2021-07-28 | 2021-11-12 | 北京中交兴路信息科技有限公司 | Fatigue driving detection method and device, electronic equipment and storage medium |
| CN116636808A (en) * | 2023-06-28 | 2023-08-25 | 交通运输部公路科学研究所 | Intelligent cockpit driver visual health analysis method and device |
-
2020
- 2020-07-22 CN CN202021461891.8U patent/CN212484555U/en active Active
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113183968A (en) * | 2021-04-25 | 2021-07-30 | 前海七剑科技(深圳)有限公司 | Anti-fatigue driving method, device, equipment and storage medium |
| CN113643512A (en) * | 2021-07-28 | 2021-11-12 | 北京中交兴路信息科技有限公司 | Fatigue driving detection method and device, electronic equipment and storage medium |
| CN113643512B (en) * | 2021-07-28 | 2023-07-18 | 北京中交兴路信息科技有限公司 | Fatigue driving detection method and device, electronic equipment and storage medium |
| CN116636808A (en) * | 2023-06-28 | 2023-08-25 | 交通运输部公路科学研究所 | Intelligent cockpit driver visual health analysis method and device |
| CN116636808B (en) * | 2023-06-28 | 2023-10-31 | 交通运输部公路科学研究所 | Intelligent cockpit driver visual health analysis method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN212484555U (en) | Fatigue driving multi-source information detection system | |
| CN104146722B (en) | Driving fatigue detecting and grading early warning method based on head signals | |
| CN111166357A (en) | Fatigue monitoring device system with multi-sensor fusion and monitoring method thereof | |
| Picot et al. | Drowsiness detection based on visual signs: blinking analysis based on high frame rate video | |
| CN107697069A (en) | Fatigue of automobile driver driving intelligent control method | |
| CN105869356A (en) | Railway driver work state evaluation intervening system and method | |
| Friedrichs et al. | Camera-based drowsiness reference for driver state classification under real driving conditions | |
| JP6134112B2 (en) | Driving concentration determination method and system for vehicle operation state information base | |
| CN101224113B (en) | Method for monitoring vehicle drivers status and system thereof | |
| CN106571015A (en) | Driving behavior data collection method based on Internet | |
| CN108446600A (en) | A kind of vehicle driver's fatigue monitoring early warning system and method | |
| CN108230619A (en) | Method for detecting fatigue driving based on multi-feature fusion | |
| CN108099601A (en) | A kind of detecting system for improving drive safety | |
| CN109147279B (en) | Driver fatigue driving monitoring and early warning method and system based on Internet of vehicles | |
| CN207266712U (en) | For monitoring the vehicle-mounted monitor and alarm system of automobile driver physical condition | |
| CN106355838A (en) | Fatigue driving detection method and system | |
| CN105185038A (en) | Safety driving system based on Android smart phone | |
| CN105931430A (en) | Alarm sensitivity detection method and apparatus for driver state early warning system | |
| CN104794856A (en) | Driver's attention comprehensive evaluation system | |
| CN107669283A (en) | Spectacle driving fatigue monitoring warning device based on multi-feature fusion and method | |
| CN104068868A (en) | Method and device for monitoring driver fatigue on basis of machine vision | |
| CN108335457B (en) | Driving safety monitoring method based on driving hand ring | |
| CN108021875A (en) | A kind of vehicle driver's personalization fatigue monitoring and method for early warning | |
| CN107563346A (en) | One kind realizes that driver fatigue sentences method for distinguishing based on eye image processing | |
| CN108926352A (en) | A kind of driving fatigue detection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |