CN115299948A - Driver fatigue detection method and detection system - Google Patents
Driver fatigue detection method and detection system Download PDFInfo
- Publication number
- CN115299948A CN115299948A CN202210866703.7A CN202210866703A CN115299948A CN 115299948 A CN115299948 A CN 115299948A CN 202210866703 A CN202210866703 A CN 202210866703A CN 115299948 A CN115299948 A CN 115299948A
- Authority
- CN
- China
- Prior art keywords
- driver
- steering
- brake
- characteristic data
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/18—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state for vehicle drivers or machine operators
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
- A61B5/0816—Measuring devices for examining respiratory frequency
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2576/00—Medical imaging apparatus involving image processing or analysis
- A61B2576/02—Medical imaging apparatus involving image processing or analysis specially adapted for a particular organ or body part
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Pulmonology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Physiology (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Psychiatry (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to a driver fatigue detection method and a driver fatigue detection system, wherein the method comprises the steps of obtaining the driving speed of a vehicle, obtaining brake characteristic data, judging whether the driver is tired or not by combining the driving speed, obtaining steering characteristic data by combining the brake characteristic data with the distance between the brake and the brake time, and judging whether the driver is tired or not by combining the driving speed, wherein the steering characteristic data comprises a steering angle and steering time. The method comprises the steps of obtaining the driving speed, the brake characteristic data and the steering characteristic data of a vehicle, combining the driving speed with the brake characteristic data and the steering characteristic data respectively, and judging whether a driver is tired or not from zero angles of braking and steering simultaneously. Compared with the prior art, the fatigue detection method can detect whether the driver is tired from multiple angles, and has higher accuracy.
Description
Technical Field
The invention relates to the technical field of driving assistance, in particular to a driver fatigue detection method and a driver fatigue detection system.
Background
As the automobile industry develops and the industrial structure is upgraded, the profit margin for vehicle transportation is gradually compressed, and many drivers choose to extend their working hours to maintain income, but the number of accidents caused by fatigue driving is also increased. The driver is reminded in time, and the loss caused by fatigue driving is reduced.
At present, although many researches are focused on fatigue detection, the prior art often decides whether a driver is tired from one angle only, for example, the driver only moves to lower the head to judge, which is not accurate and effective enough, and sometimes wrong prompts may cause problems to normal driving of the driver.
Therefore, how to comprehensively and accurately judge the fatigue state of the driver from multiple angles is an urgent problem to be solved.
Disclosure of Invention
In view of the above, it is necessary to provide a method for detecting fatigue of a driver, so as to solve the problem in the prior art that the criterion for determining fatigue driving is too single.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
in a first aspect, the present invention provides a method for detecting driver fatigue, comprising:
acquiring the running speed of a vehicle;
obtaining brake characteristic data, and judging whether a driver is tired or not by combining the driving speed, wherein the brake characteristic data comprises the distance between the brake heel and the brake time;
and acquiring steering characteristic data, and judging whether a driver is tired or not by combining the driving speed, wherein the steering characteristic data comprises a steering angle and steering time.
Further, the obtaining of brake characteristic data and the judgment of whether the driver is tired by combining the driving speed include:
judging the running working condition of the vehicle according to the running speed, and if the vehicle belongs to the normal deceleration working condition, acquiring the brake characteristic data;
and judging whether the distance between the brake and the rear car exceeds a preset distance range, and if so, judging that the driver is tired.
Further, the determining the driving condition of the vehicle according to the driving speed includes:
obtaining the brake opening of a vehicle and obtaining the change rate of the brake opening along with time;
and if the vehicle running speed is greater than a set running threshold value and the change rate of the brake opening along with the time is smaller than a set change rate threshold value, judging that the vehicle belongs to a normal deceleration working condition.
Further, the obtaining of the brake characteristic data and the judgment of whether the driver is tired by combining the driving speed further include:
storing the brake heel car distance as a historical brake heel car distance;
obtaining an average value of the following distance and a standard deviation of the following distance according to the following distances of all historical brakes;
and obtaining the preset following distance range according to the following distance average value and the following distance standard deviation.
Further, the obtaining of brake characteristic data and the judgment of whether the driver is tired by combining the driving speed further includes:
and judging whether the braking time is continuously greater than a preset time threshold for multiple times, and if so, judging that the driver is tired.
Further, the acquiring the steering characteristic data and determining whether the driver is tired by combining the driving speed includes:
acquiring the steering angle and the steering time;
obtaining a steering angle-steering time relation curve under different driving speeds according to all the historical driving speeds, the historical steering angles and the historical steering time;
and judging whether the driver is tired or not based on the steering angle-steering time relation curve according to the driving speed, the steering angle and the steering time.
Further, the method also comprises the following steps:
obtaining a plurality of acceleration values of the vehicle according to the running speed;
and judging whether the standard deviation of the acceleration values is larger than a set threshold value or not, and if so, judging that the driver is tired.
Further, the method also comprises the following steps:
acquiring a face image of a driver;
obtaining the eye parameters of the driver according to the face image of the driver, wherein the eye parameters of the driver comprise the number of closed-eye frames of the driver;
and judging whether the driver is tired or not based on a PERCLOS algorithm according to the eye parameters of the driver.
Further, the method also comprises the following steps:
acquiring the respiratory frequency and the yawning frequency of a driver;
and judging whether the driver is tired or not according to the breathing frequency and the yawning frequency.
In a second aspect, the present invention also provides a driver fatigue detection system, comprising:
the speed acquisition unit is used for acquiring the running speed of the vehicle;
the brake characteristic decision unit is used for acquiring brake characteristic data and judging whether a driver is tired or not by combining the driving speed, wherein the brake characteristic data comprises a brake rear heel distance, brake time and a brake distance;
and the steering characteristic decision unit is used for acquiring steering characteristic data and judging whether a driver is tired or not by combining the driving speed, wherein the steering characteristic data comprises a steering angle and steering time.
According to the driver fatigue detection method and the driver fatigue detection system, the driving speed, the brake characteristic data and the steering characteristic data of the vehicle are obtained, the driving speed is respectively combined with the brake characteristic data and the steering characteristic data, and whether the driver is fatigue or not is judged from zero angles of braking and steering. Compared with the prior art, the fatigue detection method can detect whether the driver is tired from multiple angles, and has higher accuracy.
Drawings
FIG. 1 is a flowchart of a method for detecting driver fatigue according to an embodiment of the present invention;
FIG. 2 is a flowchart of the method of step S102 in one embodiment of the method for detecting driver fatigue of the present invention;
FIG. 3 is a curve of the relationship between steering angle and steering time in an embodiment of the method for detecting fatigue of a driver according to the present invention;
fig. 4 is a schematic structural diagram of a driver fatigue detection system provided by the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
According to the driver fatigue detection method and the driver fatigue detection system, data related to a plurality of angles such as the vehicle speed, the steering angle and the brake angle are obtained and combined to jointly detect whether the driver is tired, and the purpose of being more accurate is achieved.
The invention provides a driver fatigue detection method and a driver fatigue detection system, which are respectively explained below.
Referring to fig. 1, a specific embodiment of the present invention discloses a method for detecting driver fatigue, which includes:
s101, acquiring the running speed of a vehicle;
s102, brake characteristic data are obtained, whether a driver is tired or not is judged according to the running speed, and the brake characteristic data comprise the distance between the brake heel and the brake time;
s103, obtaining steering characteristic data, and judging whether a driver is tired or not by combining the driving speed, wherein the steering characteristic data comprises a steering angle and steering time.
During implementation, the vehicle speed, the brake characteristic data and the steering characteristic data of the vehicle can be acquired through a vehicle machine and a sensing system of the vehicle, the driving speed, the brake characteristic data and the steering characteristic data of the vehicle are acquired, the driving speed is respectively combined with the brake characteristic data and the steering characteristic data, and whether a driver is tired or not is judged from zero angles of braking and steering. Compared with the prior art, the fatigue detection method can detect whether the driver is tired from multiple angles, and has higher accuracy.
It should be noted that, in the present embodiment, the judgment of fatigue through the braking characteristic data and the judgment of fatigue through the steering characteristic data both have the decision right, that is, only one of the two decision means needs to obtain the result of fatigue of the driver, so that the driver can be determined to be in a fatigue state. In practice, according to specific needs, the results obtained by the two means may be combined together to make a decision, for example, a weight may be respectively assigned to the detection result obtained through the braking characteristic data and the detection result obtained through the steering characteristic data, and the weight may be calculated according to a preset determination formula to decide whether the driver is tired.
As shown in fig. 2, as a preferred embodiment, the step S102 in this embodiment of obtaining braking characteristic data, and determining whether the driver is tired by combining the driving speed specifically includes:
s201, judging the running condition of the vehicle according to the running speed, and if the vehicle belongs to a normal deceleration condition, acquiring the brake characteristic data;
s202, judging whether the distance between the brake and the car is beyond the preset car following distance range or not, and judging that the driver is tired if the distance between the brake and the car is beyond the preset car following distance range.
Specifically, step S201 in the above process of determining the driving condition of the vehicle according to the driving speed includes:
obtaining the brake opening of a vehicle and obtaining the change rate of the brake opening along with time;
and if the vehicle running speed is greater than a set running threshold value and the change rate of the brake opening along with time is smaller than a set change rate threshold value, judging that the vehicle belongs to a normal deceleration working condition.
In this embodiment, when the vehicle running speed is greater than the set running threshold, the vehicle may be considered to belong to a normal running condition, that is, not to be in a limp or traffic jam queuing road condition, at this time, an opening degree signal of the vehicle brake may be detected, and when a time-dependent change rate of the vehicle brake opening degree is smaller than the set change rate threshold, the vehicle may be considered to be in a normal deceleration state, and not to be in an emergency braking state. At this time, subsequent steps such as detection and judgment are carried out, so that the influence of external objective factors can be eliminated, and the judgment result is more accurate.
Step S202, judging whether the braking rear-heel distance exceeds a preset vehicle following distance range, if so, judging that the driver is tired, wherein the braking rear-heel distance refers to the remaining distance between the vehicle and the front vehicle after the braking action is finished, and the preset vehicle following distance range can be manually specified and also can be adjusted according to the driving habit of the driver, for example:
referring to fig. 2, as a preferred embodiment, the step S102 in this embodiment of obtaining the braking characteristic data and determining whether the driver is tired by combining the driving speed further includes:
s203, storing the braking rear heel distance as a historical braking rear heel distance;
s204, obtaining an average value of following distances and a standard deviation of the following distances according to all historical braking following distances;
and S205, obtaining the preset following distance range according to the following distance average value and the following distance standard deviation.
In the implementation process, the brake heel car distance obtained by detecting each time is stored as the historical brake heel car distance in the embodiment, and the average value L of the brake heel car distance is obtained through the following formula Flat plate And standard deviation σ of following distance:
wherein N represents the total number of the current collected historical braking heel car distances, L i Indicating the vehicle distance behind the ith historical brake. Under this situation, can realize the directional car following distance data of collecting specific driver, according to driver's driving habit, adjust predetermineeing the range of car following distance to the car following distance when more accurately utilizing the brake detects driver's reaction sensitivity.
It is understood that, in practice, the above steps S203 to S205 can be executed before or after the step S202 according to specific needs, and are not limited to the embodiment.
Further, referring to fig. 2 again, the present invention further provides a preferred embodiment, in which step S102 of the embodiment, the obtaining the braking characteristic data, and determining whether the driver is tired by combining the driving speed, further includes:
and S206, judging whether the braking time is continuously and repeatedly greater than a preset time threshold value, and if so, judging that the driver is tired.
The step can judge the response sensitivity of the driver through the braking time and the braking distance, and when the continuous multiple times of braking time of the driver is longer than a preset time threshold value, the driver can be considered to be tired. Similarly, the brake heel distance can also be judged in the same manner, namely when the brake heel distance is detected to continuously exceed the preset brake heel distance range for multiple times, the fatigue of a driver can be judged.
In a preferred embodiment, the step S103 of acquiring the steering characteristic data and determining whether the driver is tired by combining the driving speed includes:
acquiring the steering angle and the steering time;
obtaining a steering angle-steering time relation curve under different driving speeds according to all historical driving speeds, historical steering angles and historical steering time;
and judging whether the driver is tired or not based on the steering angle-steering time relation curve according to the driving speed, the steering angle and the steering time.
In the above process, the detected steering angle and steering time and the corresponding driving speed are stored as the historical steering angle, the historical steering time and the historical driving speed, and a steering angle-steering time relation curve at different driving speeds is established, as shown in fig. 3, to represent the normal level of the steering reaction of the driver. When the driver is tired and the response is slow, the steering time and the steering angle of the driver can form a difference with the established steering angle-steering time relation curve, whether the driver is tired can be judged according to the difference, and the default steering angle-steering time relation curve can be adopted before enough sample data is not collected.
In a preferred embodiment, the method further comprises:
obtaining a plurality of acceleration values of the vehicle according to the running speed;
and judging whether the standard deviation of the acceleration values is larger than a set threshold value or not, and if so, judging that the driver is tired.
A plurality of acceleration values cooperate with the standard deviation to reflect the stability of the vehicle speed during driving, so that whether the vehicle speed is suddenly and suddenly reduced or not is judged, and the fatigue state of a driver is further judged.
As a preferred embodiment, the driver fatigue detection method in the present embodiment further includes detecting, based on the driver face information:
acquiring a face image of a driver;
obtaining the eye parameters of the driver according to the face image of the driver, wherein the eye parameters of the driver comprise the number of closed-eye frames of the driver;
and judging whether the driver is tired or not based on a PERCLOS algorithm according to the eye parameters of the driver.
The above-mentioned process accessible camera in the car gathers driver's face information, utilizes image recognition technology discernment driver's eye: firstly, graying a color image acquired by a camera in a vehicle, and determining a human head region based on contour features by using a maximum connected domain after a background subtraction algorithm. Then, the hough transformation method is used for positioning the eyes, the change of the eyes of the driver is tracked, whether the driver is in a fatigue state is determined according to the PERCLOS value, and the calculation method of the PERCLOS value is as follows:
PERCLOS value = (closed-eye frame number ÷ total frame number) × 100%
The invention also provides a preferable embodiment, and the method for detecting the fatigue of the driver in the embodiment further comprises the following steps:
acquiring the respiratory frequency and the yawning frequency of a driver;
and judging whether the driver is tired or not according to the respiratory frequency and the yawning frequency.
The sound in the car can be collected in real time through the sound recorder in the car in the process, the collected sound is subjected to characteristic analysis through the pre-training model, the sound of the driver is extracted, and the breathing frequency and the yawning frequency of the driver are obtained. When the breathing frequency of the driver is obviously slowed down, the attention of the driver is reduced, and the driver may be in a relaxed state caused by fatigue, or the yawning frequency of the driver is too high, and the driver may be in a fatigue state, in both cases, the driver can be considered to be tired.
Preferably, the above decision process can be combined with time. For example, when the vehicle is driving nine o ' clock in the evening and six o ' clock in the morning, the driver is more fatigued, the road view is darkened and limited, and the detection threshold of the driver's voice detection system is automatically adjusted.
In order to better implement the driver fatigue detection method in the embodiment of the present invention, on the basis of the driver fatigue detection method, please refer to fig. 4 correspondingly, fig. 4 is a schematic structural diagram of an embodiment of the driver fatigue detection system provided by the present invention, and a driver fatigue detection system 400 provided by the embodiment of the present invention includes:
a speed acquisition unit 410 for acquiring a running speed of the vehicle;
a braking characteristic decision unit 420, configured to obtain braking characteristic data, and determine whether a driver is tired by combining the driving speed, where the braking characteristic data includes a braking rear heel distance, a braking time, and a braking distance;
and a steering characteristic decision unit 430, configured to obtain steering characteristic data, and determine whether the driver is tired by combining the driving speed, where the steering characteristic data includes a steering angle and a steering time.
Specifically, the speed acquisition unit 410 in the present embodiment includes a vehicle speed detector, such as an in-vehicle sensor, which has the capability of continuously detecting and recording a change in vehicle speed, and is connected to a braking characteristic decision unit 420 and a steering characteristic decision unit 430.
The braking characteristic decision unit 420 in this embodiment includes an image processing module, a decision module, and a storage, where the image processing module may be a camera mounted on a vehicle, and the decision module and the storage may be a vehicle-mounted device, a traveling computer, or the like mounted on the vehicle, or a computer mounted separately. The distance measurement of the front vehicle or the front obstacle can be realized by the image processing module, and the storage of historical brake characteristic data, the operation processing of a preset vehicle following distance range and the decision of whether fatigue occurs or not can be realized by the decision module and the storage.
The steering characteristic decision unit 430 includes a steering detector and decision module, and a memory. The steering detector may be a sensor built in the vehicle, and the decision module and the memory in the steering characteristic decision unit 430 may be shared with the decision module and the memory in the braking characteristic decision unit 420. The method is used for storing historical driving speed, historical steering angle and historical steering time, calculating steering angle-steering time relation curves at different driving speeds and deciding whether fatigue occurs.
Further, the driver fatigue detection system 400 in the present embodiment further includes a driver facial feature decision unit 440, configured to obtain a driver facial image, and detect whether the driver is tired based on the driver facial image according to the method in the above embodiment. The driver facial feature decision unit 440 includes an image capture device, such as a camera in the vehicle, which may also share the decision module and memory with other units described above, or may be configured independently.
The driver fatigue detection system 400 in the present embodiment further includes a driver voice feature decision unit 450, configured to obtain the breathing frequency and the yawning frequency of the driver, and detect whether the driver is fatigued based on the face image of the driver according to the method in the above embodiment. The driver voice characteristic decision unit 450 includes a voice collecting device, such as a microphone in the vehicle, and may also use the decision module and the memory together with the other units, or may be configured independently.
Here, it should be noted that: the driver fatigue detection system 400 provided in the above embodiments may implement the technical solutions described in the above method embodiments, and the specific implementation principles of the modules or units may refer to the corresponding contents in the above method embodiments, and are not described herein again.
Further, to more specifically describe the method and system for detecting fatigue of a driver in the present invention, the present invention further provides a preferred embodiment, which is specifically a streaming media rearview mirror imaging system with fatigue detection function, the system includes:
the system comprises an interior rearview mirror in the vehicle, a sensor in the vehicle, an interior camera positioned on the mirror surface of the rearview mirror, a front camera positioned on the back surface of the rearview mirror, a rear camera positioned at the tail of the vehicle, two exterior rearview mirrors respectively positioned on the left and the right of the vehicle, a graphic processing module, an analysis decision module and an execution module. The camera in the car adopts a CCD camera, and the front camera and the rear camera adopt high-definition wide-angle cameras.
The sensors in the vehicle are the vehicle speed detector in the speed acquisition unit 410 and the steering detector in the steering characteristic decision unit 430, and the specific types of the sensors can be flexibly used according to actual requirements, such as wheel rotation speed sensors, infrared displacement sensors, potentiometers, and the like.
The front camera mainly provides a function of a driving recorder, collects and records images in front of the vehicle in real time, and provides a basis for traffic accident arbitration, and specifically is an image processing module of the brake characteristic decision unit 420 in the embodiment, collects images of the front vehicle during normal deceleration of the vehicle, and the image processing module measures the distance of the front vehicle.
The analysis decision module includes the decision module and memory of the driver fatigue detection system 400 described above. On the other hand, in the embodiment, the graphic processing module, in addition to the functions of the driver fatigue detection system 400, may further analyze whether there is a vehicle coming from behind according to the rear camera image, and define a danger warning range in the graphic, if the vehicle is located within the danger warning range of the image, the control system determines that there is a vehicle in the set detection area behind the vehicle, and if there is no vehicle in the danger warning range of the image, the control system determines that there is no vehicle in the set detection area behind the vehicle.
The camera provides the image of backing a car behind the car, has reduced driver's field of vision blind area. Meanwhile, the rear camera detects the danger warning range of the rear image of the vehicle, and the control system judges that the vehicle exists in a set detection area behind the vehicle; if no vehicle exists in the danger warning range of the image, the control system judges that no vehicle exists in a set detection area behind the vehicle. And the decision module decides whether the rearview mirror display adopts a rearview mirror surface mode or an anti-dazzling mode according to the information.
The front and the back of the rearview mirror glass are respectively provided with a photosensitive diode, and in the anti-dazzling mode, when the photosensitive diodes generate voltage difference due to the difference of the light intensity of the front and the back environments of the vehicle, the mirror surface can change the reflectivity according to the voltage difference so as to achieve anti-dazzling.
The left outer camera and the right outer camera can provide extra visual angles, and visual field blind areas of drivers are reduced.
The in-vehicle camera is installed on the display surface of the rearview mirror, and collects the image information of the driver in real time, that is, the driver facial feature decision unit 440 includes an image collecting device. The image processing module can transmit image information to the image processing module for receiving and processing, and the transverse width ratio of the eyes of a driver is analyzed to realize fatigue detection of the driver.
The driver can select the camera image appearing in the display screen from the master through a button on the rearview mirror. The image can be automatically judged by depending on the rearview mirror, and when the automobile is in reverse gear and starts to move, the rearview mirror can automatically cut the image of the camera of the rearview automobile; when the automobile turns to, the rear-view mirror can cut the split screen mode automatically, and half display screen on turning direction one side will show the outer camera image of this direction, and half display screen will show the back car camera image in addition. When the camera image signal selected by the driver conflicts with the camera image signal automatically judged by the rearview mirror, the image selected by the driver is displayed.
In order to ensure real-time effectiveness of image information of each camera, in this embodiment, an FPD-LinkIII standard transmission harness is used to connect each camera and the rearview mirror, and coaxial cable transmission for transmitting LVDS signals is adopted.
The embodiment provides an execution module for fatigue driving reminding, which comprises a buzzer arranged on the back surface of a streaming media rearview mirror, a flash lamp arranged beside the mirror surface of the streaming media rearview mirror, and a text prompt function or a sound prompt function which is sent to a mobile phone of a driver on the premise of logging in a mobile phone app of the driver. The execution module executes the decisions made by the decision modules.
The behavior of the executive module is differentiated according to the clear degree of the fatigue characteristics of the driver. The flash lamp, the buzzer and the mobile phone app determine the flashing color according to the decision of the decision system, when only one of the detection systems is fatigue, the detection system is determined to be suspected fatigue, yellow light flashes, the sound of the buzzer is small, and the mobile phone app only sends a text prompt. When two or more than two of the detection systems are fatigue, the driver is confirmed to be fatigue, red light flickers, the buzzer sounds loud, and the mobile phone app enables a text prompt function and a sound prompt function.
Preferably, the embodiment provides a function of fatigue reminding by adjusting the seat. When confirming that the driver is tired, the streaming media rear-view mirror decision-making system sends the seat and adjusts the signal, because streaming media rear-view mirror and automobile body electronic system electric connection, straightens the seat back with slow speed automatically, prevents that the driver from paralyzing to sit on the seat, takes place to sleep the serious traffic accident that leads to. Meanwhile, the sense of touch of the back of the driver when the seat is pushed up can well remind the driver of fatigue, and interference on normal driving of the driver is not easy to cause.
The embodiment further provides a streaming media rearview mirror which is provided with a video export module, is used for exporting images of all cameras through a transmission interface on the streaming media rearview mirror, can be used for obtaining evidence in the process of traffic accidents or checking the shooting angle of the cameras, and is easy for a driver to manually adjust.
According to the driver fatigue detection method and the driver fatigue detection system, the driving speed, the brake characteristic data and the steering characteristic data of the vehicle are obtained, the driving speed is respectively combined with the brake characteristic data and the steering characteristic data, and whether the driver is fatigue or not is judged from zero angles of braking and steering. Compared with the prior art, the fatigue detection method can detect whether the driver is tired from multiple angles, and has higher accuracy.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention 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 present invention are included in the scope of the present invention.
Claims (10)
1. A driver fatigue detection method, characterized by comprising:
acquiring the running speed of a vehicle;
obtaining brake characteristic data, and judging whether a driver is tired or not by combining the driving speed, wherein the brake characteristic data comprises the brake rear heel distance and the brake time;
and acquiring steering characteristic data, and judging whether a driver is tired or not by combining the driving speed, wherein the steering characteristic data comprises a steering angle and steering time.
2. The method for detecting fatigue of a driver according to claim 1, wherein the obtaining braking characteristic data and determining whether the driver is fatigued in combination with the driving speed comprises:
judging the running working condition of the vehicle according to the running speed, and if the vehicle belongs to the normal deceleration working condition, acquiring the brake characteristic data;
and judging whether the distance between the brake and the rear car exceeds a preset distance range, and if so, judging that the driver is tired.
3. The driver fatigue detection method according to claim 2, wherein the determining the running condition of the vehicle from the running speed includes:
obtaining the brake opening of a vehicle, and obtaining the change rate of the brake opening along with time;
and if the vehicle running speed is greater than a set running threshold value and the change rate of the brake opening along with time is smaller than a set change rate threshold value, judging that the vehicle belongs to a normal deceleration working condition.
4. The method for detecting fatigue of a driver according to claim 2, wherein the obtaining braking characteristic data and determining whether the driver is fatigued in combination with the driving speed further comprises:
storing the brake heel car distance as a historical brake heel car distance;
obtaining an average value of the following distances and a standard deviation of the following distances according to all historical braking following distance;
and obtaining the preset following distance range according to the following distance average value and the following distance standard deviation.
5. The method for detecting fatigue of a driver according to claim 2, wherein the obtaining braking characteristic data and determining whether the driver is fatigued in combination with the driving speed further comprises:
and judging whether the braking time is continuously greater than a preset time threshold for multiple times, and if so, judging that the driver is tired.
6. The driver fatigue detection method according to claim 1, wherein the acquiring steering characteristic data and determining whether the driver is fatigued in conjunction with the travel speed includes:
acquiring the steering angle and the steering time;
obtaining a steering angle-steering time relation curve under different driving speeds according to all historical driving speeds, historical steering angles and historical steering time;
and judging whether the driver is tired or not based on the steering angle-steering time relation curve according to the running speed, the steering angle and the steering time.
7. The driver fatigue detection method according to claim 1, further comprising:
obtaining a plurality of acceleration values of the vehicle according to the running speed;
and judging whether the standard deviation of the acceleration values is larger than a set threshold value or not, and if so, judging that the driver is tired.
8. The driver fatigue detection method according to claim 1, further comprising:
acquiring a face image of a driver;
obtaining the eye parameters of the driver according to the face image of the driver, wherein the eye parameters of the driver comprise the number of closed-eye frames of the driver;
and judging whether the driver is tired or not based on a PERCLOS algorithm according to the eye parameters of the driver.
9. The driver fatigue detection method according to claim 1, further comprising:
acquiring the respiratory frequency and the yawning frequency of a driver;
and judging whether the driver is tired or not according to the respiratory frequency and the yawning frequency.
10. A driver fatigue detection system, comprising:
the speed acquisition unit is used for acquiring the running speed of the vehicle;
the brake characteristic decision unit is used for acquiring brake characteristic data and judging whether a driver is tired or not by combining the driving speed, wherein the brake characteristic data comprises a brake heel distance, brake time and a brake distance;
and the steering characteristic decision unit is used for acquiring steering characteristic data and judging whether a driver is tired or not by combining the driving speed, wherein the steering characteristic data comprises a steering angle and steering time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210866703.7A CN115299948A (en) | 2022-07-22 | 2022-07-22 | Driver fatigue detection method and detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210866703.7A CN115299948A (en) | 2022-07-22 | 2022-07-22 | Driver fatigue detection method and detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115299948A true CN115299948A (en) | 2022-11-08 |
Family
ID=83857040
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210866703.7A Pending CN115299948A (en) | 2022-07-22 | 2022-07-22 | Driver fatigue detection method and detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115299948A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101427881B1 (en) | 2009-10-22 | 2014-08-07 | 퀄컴 인코포레이티드 | Determination of cell reselection parameters by the access point |
-
2022
- 2022-07-22 CN CN202210866703.7A patent/CN115299948A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101427881B1 (en) | 2009-10-22 | 2014-08-07 | 퀄컴 인코포레이티드 | Determination of cell reselection parameters by the access point |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11661075B2 (en) | Inward/outward vehicle monitoring for remote reporting and in-cab warning enhancements | |
| CN112389448B (en) | Abnormal driving behavior identification method based on vehicle state and driver state | |
| EP1182089B1 (en) | Vehicle driver warning procedure | |
| US20180304806A1 (en) | Driver state sensing system, driver state sensing method, and vehicle including the same | |
| CN111016899B (en) | Vehicle lane change monitoring and predicting system based on big data | |
| CN108297879A (en) | A kind of Car warning system | |
| KR101938314B1 (en) | Apparatus and Method for Warning Rear Side of Vehicle with Learning of Driving Pattern | |
| CN109835251B (en) | Vehicle forward collision early warning system | |
| CN108973861A (en) | A kind of intelligence A column driving safety system | |
| CN110667475A (en) | Auxiliary monitoring system and method for blind area of passenger car | |
| CN114872713A (en) | Device and method for monitoring abnormal driving state of driver | |
| KR20180065527A (en) | Vehicle side-rear warning device and method using the same | |
| CN112319366A (en) | Parking monitoring and early warning method and system | |
| CN114360210A (en) | Vehicle fatigue driving early warning system | |
| US11608070B2 (en) | System and method for monitoring driver | |
| KR20170035035A (en) | Apparatus and method for preventing drowsy driving | |
| CN115299948A (en) | Driver fatigue detection method and detection system | |
| CA3165782A1 (en) | System and method for controlling vehicle functions based on evaluated driving team composition | |
| KR102556845B1 (en) | AVM system with real-time control function | |
| CN111717196A (en) | Driving safety auxiliary device based on visual analysis | |
| JP2021060676A (en) | System and program or the like | |
| CN113920734B (en) | Lane change early warning method based on logistic model | |
| CN113060130B (en) | Vehicle-mounted driving assistance control method and storage medium | |
| KR102426735B1 (en) | Automotive security system capable of shooting in all directions with theft notification function applied | |
| KR102239221B1 (en) | 360 degree dash cam system for high quality video transmission |
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 |