Vehicle automatic driving takeover method and system

Abstract

The invention provides a vehicle automatic driving takeover method and system. The method comprises the following steps that the fatigue degree of a driver is recognized according to a driver face image collected in real time; and outputting a corresponding prompt according to the fatigue degree of the driver, and selecting to maintain the vehicle running through automatic driving or control the vehicle to pull over and stop through automatic driving. According to the method, the automobile automatic driving function under different degrees can be automatically started while safety reminding is given, and automobile safety accidents caused by sudden health conditions of a driver can be effectively reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of automobile safe driving, and specifically relates to a vehicle automatic driving takeover method and system. Background Art

[0002] A large part of automobile accidents is caused by physical reasons such as driver fatigue and fainting. As people's lives become more and more abundant, social activities become more and more frequent, which greatly increases the occurrence of collision accidents caused by the driver's physical condition. Active safety, as an important part of automobile safety, has always been the focus of automobile manufacturers. At present, the methods to improve the active safety of automobiles are also changing with each passing day. Major automobile manufacturers are also constantly optimizing solutions in this regard, striving to improve active safety while greatly reducing the frequency of automobile accidents to address the problem of drivers' physical inability to perform normal driving.

[0003] The current strategy is to use the driver health monitoring system to measure the driver's blood pressure, heart rate and other physical parameters, analyze the driver's physical condition through the parameters, and remind the driver that he is in poor health and cannot drive normally. Although this method will remind the driver of his physical condition, it only applies to the situation where the driver is still awake and capable of driving the vehicle to a safe area, which can avoid accidents to a certain extent. Once the driver loses consciousness due to fatigue or sudden fainting while driving, even if there is a reminder of the physical condition, once the driver is not awakened, the car safety accident situation cannot be avoided. Summary of the invention

[0004] The purpose of the present invention is to address the deficiencies of the above-mentioned background technology and to provide a vehicle automatic driving takeover method and system, which can give safety reminders and automatically start the vehicle automatic driving function at different degrees, thereby effectively reducing vehicle safety accidents caused by the driver's sudden health condition.

[0005] The technical solution adopted by the present invention is: a method for taking over automatic driving of a vehicle, comprising the following steps:

[0006] Identify the driver's fatigue level based on the driver's facial image collected in real time;

[0007] Output corresponding reminders based on the driver's fatigue level, and choose to maintain the vehicle's driving through automatic driving or control the vehicle to pull over through automatic driving.

[0008] In the above technical solution, the process of identifying the driver's fatigue level based on the real-time collected driver's facial image includes: real-time positioning of the lips in the driver's facial image, and determining the driver's fatigue level based on the frequency of the lip change amplitude being greater than a set value.

[0009] In the above technical solution, the process of identifying the driver's fatigue level based on the real-time collected driver's facial image includes: real-time positioning of the eyes in the driver's facial image, and determining the driver's fatigue level based on the frequency of the eye change amplitude within a set range.

[0010] In the above technical solution, the lip change amplitude is: the change value of the distance between the upper and lower edges of the mouth at two adjacent sampling moments; the set value is: 1.5 times the distance between the upper and lower edges of the mouth at the previous sampling moment in two adjacent sampling moments; if the frequency of the lip change amplitude being greater than the set value is greater than the corresponding set standard, the driver's physical condition is marked as low, and the corresponding prompt sound is output.

[0011] In the above technical solution, the eye change amplitude is: the change value of the distance between the upper and lower edges of the eye at two adjacent sampling moments; the setting range includes a first setting range and a second setting range:

[0012] The minimum value of the first setting range is: 0.25 times the distance between the upper and lower edges of the mouth at the previous sampling moment in two adjacent sampling moments; the maximum value of the first setting range is: 0.75 times the distance between the upper and lower edges of the mouth at the previous sampling moment in two adjacent sampling moments; if the frequency of the eye change amplitude in the first setting range is greater than the corresponding setting standard, the driver's physical condition is marked as low, the corresponding prompt sound is output, and the automatic driving is started to maintain the vehicle driving;

[0013] The minimum value of the second setting range is: 0; the maximum value of the first setting range is: 0.25 times the distance between the upper and lower edges of the mouth at the previous sampling moment in two adjacent sampling moments; if the frequency of the eye change amplitude in the second setting range is greater than the corresponding setting standard, the driver's physical condition is marked as very low, the corresponding prompt sound is output, and the automatic driving is started to control the vehicle to pull over.

[0014] In the above technical solution, if the driver's physical condition is marked as low, and the frequency of the lip change amplitude greater than the set value within the set time period is greater than the corresponding set standard, the driver's physical condition is marked as low, the corresponding prompt sound is output, and automatic driving is started to maintain vehicle driving.

[0015] In the above technical solution, if the driver's physical condition is marked as low, and the frequency of the eye change amplitude being within the first set range within the set time period is greater than the corresponding set standard, the driver's physical condition is marked as very low, the corresponding prompt sound is output, and the automatic driving is started to control the vehicle to pull over.

[0016] In the above technical solution, by locating the key points in the driver's facial image, several key points located at the upper and lower edges of the mouth are determined respectively; the distance between the symmetrical key points corresponding to the upper and lower edges of the mouth is calculated; the distance calculation values ​​between all the symmetrical key points are averaged to obtain the average distance between the upper and lower edges of the mouth.

[0017] In the above technical solution, by locating the key points in the driver's facial image, several key points located at the upper and lower edges of the eyes are determined respectively; the distance between the symmetrical key points corresponding to the upper and lower edges of the glasses is calculated; the calculated distance values ​​between all the symmetrical key points are averaged to obtain the average distance between the upper and lower edges of the eyes.

[0018] The present invention provides a vehicle automatic driving takeover system, which is used to implement the vehicle automatic driving takeover method described in the above technical solution, including: a fatigue level recognition module, an automatic driving takeover module;

[0019] The fatigue level recognition module is used to recognize the driver's fatigue level based on the driver's face image collected in real time;

[0020] The automatic driving takeover module is used to output corresponding reminders according to the driver's fatigue level, and choose to maintain the vehicle's driving through automatic driving or control the vehicle to pull over through automatic driving.

[0021] The present invention provides a vehicle, comprising:

[0022] one or more processors;

[0023] A memory for storing one or more programs;

[0024] When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle automatic driving takeover method described in the above technical solution.

[0025] The present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the vehicle automatic driving takeover method described in the above technical solution is implemented.

[0026] The beneficial effects of the present invention are as follows: the present invention classifies the physical condition of the driver and takes corresponding countermeasures based on different levels. With the assistance of the active safety scheme, on the one hand, it can effectively avoid the risk of driving caused by the immediate start of automatic driving in response to the driver's physical condition when the driver can complete normal driving but has physical conditions; at this time, the automatic driving function may interfere with and affect the driver's normal driving, causing the driver to misjudge the vehicle condition and cause some unnecessary automobile safety accidents; on the other hand, it can also take into account that when the driver's condition is very poor and can no longer complete normal driving, resulting in major safety hazards, the priority of the automatic driving function is higher than that of the driver, and the driving rights of the car are taken over in time, avoiding the risk of automobile safety accidents caused by the driver's wrong operation of the vehicle due to coma, syncope, confusion and other behaviors. The method can dynamically monitor the driver's physical state by real-time acquisition of the driver's facial image and identification of his fatigue level, so as to take corresponding measures in real time. This can not only improve the safety of the driver, but also effectively avoid traffic accidents caused by fatigue driving, and improve the intelligence and reliability of the automatic driving system.

[0027] Furthermore, the present invention identifies the degree of fatigue by the frequency of the lip change amplitude being greater than a set value. This method, combined with the slight changes in the driver's lips, can accurately determine the driver's fatigue status, especially under the subtle changes in the driver's face, thereby improving the accuracy of fatigue recognition.

[0028] Furthermore, the present invention identifies fatigue by monitoring the amplitude of changes in the driver's eyes, which further increases the dimension of identification. Changes in the eyes are directly related to the driver's attention and sobriety, so combined with changes in the lips, it can provide a more comprehensive fatigue assessment and reduce misjudgment.

[0029] Furthermore, the present invention can accurately reflect the driver's fatigue level by calculating the change amplitude of the lips and setting a reasonable change value threshold. The set threshold can be adjusted according to multiple factors (such as the distance between the upper and lower edges of the mouth at the sampling time) to ensure the sensitivity and accuracy of the system. This helps to issue a warning in time before fatigue driving occurs, ensuring driving safety.

[0030] Furthermore, the present invention provides a more detailed identification of fatigue driving by comparing the amplitude of eye changes with a set range. By setting multiple threshold ranges, the system can judge the degree of fatigue in different levels and trigger different response measures, such as maintaining vehicle movement or pulling over, so as to more flexibly respond to different driver conditions.

[0031] Furthermore, when the driver's physical condition is marked as low, the present invention can timely detect the driver's physical condition further deteriorating by monitoring the frequency of the lip change amplitude. This dynamic adjustment method can take more stringent safety measures when the driver continues to be fatigued, reducing safety risks.

[0032] Furthermore, if the driver's physical condition deteriorates further, the present invention can further confirm the driver's fatigue level and take emergency measures by monitoring the amplitude of eye changes, such as automatically controlling the vehicle to pull over. This method can ensure the safety of the driver while avoiding accidents and improving road safety.

[0033] Furthermore, the present invention can obtain the specific information of mouth changes very accurately by accurately locating the key points in the driver's facial image and calculating the distance between the symmetrical key points of the upper and lower edges of the mouth. This precise measurement can improve the recognition accuracy of fatigue level, reduce misjudgment, and provide a more accurate judgment basis for the automatic driving system.

[0034] Further, similar to the measurement of lip changes, the present invention provides accurate detection of eye fatigue by locating key points of the eyes and calculating the average distance between the upper and lower edges of the eyes. The eyes are an important indicator of whether the driver is concentrating or not. By monitoring the changes in the eyes, the driver's fatigue level can be effectively identified, enhancing the safety and reliability of the entire system. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0036] Figure 2 is a flowchart of face image data processing in a specific embodiment;

[0037] Figure 3 Schematic diagram of key points of a facial image according to a specific embodiment. DETAILED DESCRIPTION

[0038] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments to facilitate a clear understanding of the present invention, but they do not constitute a limitation on the present invention.

[0039] Example 1

[0040] like Figure 1 As shown, the present invention provides a method for taking over automatic driving of a vehicle, comprising the following steps:

[0041] Identify the driver's fatigue level based on the driver's facial image collected in real time;

[0042] Output corresponding reminders based on the driver's fatigue level, and choose to maintain the vehicle's driving through automatic driving or control the vehicle to pull over through automatic driving.

[0043] Specifically, the process of identifying the driver's fatigue level based on the driver's facial image collected in real time includes: locating the lips in the driver's facial image in real time, and determining the driver's fatigue level based on the frequency of the lip change amplitude being greater than a set value.

[0044] Specifically, the process of identifying the driver's fatigue level based on the driver's facial image collected in real time includes: locating the eyes in the driver's facial image in real time, and determining the driver's fatigue level based on the frequency of the eye change amplitude within a set range.

[0045] Specifically, the lip change amplitude is: the change value of the distance between the upper and lower edges of the mouth at two adjacent sampling moments; the set value is: 1.5 times the distance between the upper and lower edges of the mouth at the previous sampling moment in two adjacent sampling moments; if the frequency of the lip change amplitude being greater than the set value is greater than the corresponding set standard, the driver's physical condition is marked as low, and the corresponding prompt sound is output.

[0046] Specifically, the eye change amplitude is: the change value of the distance between the upper and lower edges of the eye at two adjacent sampling moments; the setting range includes a first setting range and a second setting range:

[0047] The minimum value of the first setting range is: 0.25 times the distance between the upper and lower edges of the mouth at the previous sampling moment in two adjacent sampling moments; the maximum value of the first setting range is: 0.75 times the distance between the upper and lower edges of the mouth at the previous sampling moment in two adjacent sampling moments; if the frequency of the eye change amplitude in the first setting range is greater than the corresponding setting standard, the driver's physical condition is marked as low, the corresponding prompt sound is output, and the automatic driving is started to maintain the vehicle driving;

[0048] The minimum value of the second setting range is: 0; the maximum value of the first setting range is: 0.25 times the distance between the upper and lower edges of the mouth at the previous sampling moment in two adjacent sampling moments; if the frequency of the eye change amplitude in the second setting range is greater than the corresponding setting standard, the driver's physical condition is marked as very low, the corresponding prompt sound is output, and the automatic driving is started to control the vehicle to pull over.

[0049] Specifically, if the driver's physical condition is marked as low, and the frequency of the lip changes exceeding the set value within the set time period is greater than the corresponding set standard, the driver's physical condition is marked as low, the corresponding prompt sound is output, and automatic driving is started to maintain vehicle driving.

[0050] Specifically, if after the driver's physical condition is marked as low, if the frequency of the eye change amplitude being within the first set range within the set time period is greater than the corresponding set standard, the driver's physical condition is marked as very low, a corresponding prompt sound is output, and automatic driving is started to control the vehicle to pull over.

[0051] Specifically, by locating the key points in the driver's facial image, several key points located at the upper and lower edges of the mouth are determined respectively; the distance between the symmetrical key points corresponding to the upper and lower edges of the mouth is calculated; the distance calculation values ​​between all the symmetrical key points are averaged to obtain the average distance between the upper and lower edges of the mouth.

[0052] Specifically, by locating the key points in the driver's facial image, several key points located at the upper and lower edges of the eyes are determined respectively; the distance between the symmetrical key points corresponding to the upper and lower edges of the glasses is calculated; the distance calculation values ​​between all the symmetrical key points are averaged to obtain the average distance between the upper and lower edges of the eyes.

[0053] Example 2

[0054] The present invention provides a method for taking over an automatic driving vehicle. The driver's fatigue status is comprehensively assessed through the recorded data to determine whether the driver is capable of normal driving, and in conjunction with the automatic driving function, automobile safety accidents caused by driver fatigue during driving can be effectively avoided. In order to address the safety issue that the driver cannot drive normally due to sudden physical conditions during driving, a comprehensive driver fatigue monitoring device can be used to effectively identify the driver's physical condition based on the driver's driving status, determine whether the driver can complete the driving process normally, and automatically start the automatic driving function of the car at different levels while giving safety reminders based on the different physical conditions of the driver. This can effectively reduce automobile safety accidents caused by sudden health conditions of the driver. Specifically, the following steps are included, such as Figure 2 As shown:

[0055] The first step is to use the front image acquisition device in the car to collect the driver's face image in real time, and identify and locate 68 key points in the face image. How to locate the key points is a conventional method in the prior art. The above key points usually include the positions of facial features such as eyes, nose, and mouth. By detecting these key points, functions such as driver face recognition and expression recognition can be achieved. Figure 3 The acquisition frequency is 5 times / s.

[0056] The second step is to calculate the distances between the symmetrical key points on the upper and lower edges of the eyes and the symmetrical key points on the upper and lower edges of the lips at two adjacent sampling moments, that is, d1(n) and d2(n) in two time steps, and the corresponding change values ​​△d1(n) and △d2(n), where:

[0057]

[0058]

[0059] Δd1(n)=|d1(n+1)-d1(n)|

[0060] Δd2(n)=|d2(n+1)-d2(n)|

[0061] Wherein, D38~D42 represent the y coordinate values ​​of the key points of the right eye (with the eye closed direction as the y direction), D44-D48 represent the y coordinate values ​​of the key points of the left eye, D51-D53 represent the y coordinate values ​​of the key points on the upper edge of the lip, D57-D59 represent the y coordinate values ​​of the key points on the lower edge of the lip, d1(n) represents the distance between the upper and lower edges of the driver's lips at the nth time step, d2(n) represents the distance between the upper and lower edges of the driver's eyes at the nth time step, △d1(n) represents the change in the distance between the upper and lower edges of the driver's lips in two adjacent time steps, and △d2(n) represents the change in the distance between the upper and lower edges of the driver's eyes in two adjacent time steps. If the calculated data is not abnormal,

[0062] The third step is to judge the driver's fatigue level based on the following criteria:

[0063] If the lip change amplitude △d1(n) is greater than 1.5*d1, it is determined whether the driver is yawning and the frequency is recorded.

[0064] If the yawning frequency is greater than 3 times / 5 minutes, which is significantly higher than the normal yawning frequency, the system will determine that the driver is beginning to enter a state of fatigue and will record the driver's physical condition as being in poor condition.

[0065] The risk of the driver falling asleep is judged based on the eye change amplitude Δd2(n). If the eye change amplitude Δd2(n) is always in the range of 0.25d2-0.75d2 within 10s, the driver's eyes are in a semi-closed to closed state for a long time, which is very similar to the state of the eyes when a person is tired. At this time, it is determined that the driver has entered a tired state and is at high risk of falling asleep, and the driver's physical condition is recorded as low.

[0066] If the eye change amplitude Δd2(n) is always in the range of 0-0.25d2 within 10s, the driver's eyes are completely closed for a long time, which is very similar to a person being asleep. The driver is judged to have fallen asleep or fainted, and the driver's physical condition is recorded as very low.

[0067] According to the three levels of driver status: low, low and very low, different autonomous driving response plans are given to assist the driver in driving and pulling over to avoid potential dangers during driving. The process is as follows Figure 1 The specific response plans are as follows:

[0068] When the driver's physical condition is judged to be poor, that is, the driver can barely complete a short period of driving, the vehicle will promptly remind the driver of the poor physical condition, give various physical unqualified indicators, inform the driver of the potential risks, and suggest the driver to stop driving as soon as possible. The driver's physical condition will be continuously followed up. Once the driver's physical condition does not improve, that is, the yawning frequency is still greater than 3 times / 5 minutes, it will be upgraded to the next level in time.

[0069] When the driver's physical condition is judged to be poor, that is, the driver has reached the edge of being unable to drive normally and there is a risk of driving safety hazards, the vehicle will repeatedly remind the driver of poor physical condition and give various unqualified indicators to inform the driver of the many risks involved. The vehicle will automatically turn on the double flash, and the automatic driving will start in time to assist driving and slow down the car. At the same time, the monitoring frequency is increased, that is, to determine whether the eye change amplitude Δd2(n) is always in the range of 0-0.25d2 within 8s; once it is judged to be yes, it is determined that the driver's physical condition has not improved and it is upgraded to the next level in time.

[0070] When the driver's physical condition is judged to be very poor, that is, the driver is unable to complete the driving of the entire vehicle, and the vehicle safety may be at risk at any time; the vehicle will repeatedly remind the driver of his poor physical condition, and try to wake up the drowsy or fainted driver by increasing the reminder volume. The automatic driving will be started immediately, and the auxiliary vehicle will park on the side of the road. The vehicle will automatically turn on the double flash (with a higher priority than the driver), and notify the usual contacts by phone to inform them that the driver's physical condition is very poor and that medical rescue is required if necessary.

[0071] This embodiment uses the above-mentioned different response plans designed based on the different physical conditions of the driver to grade the driver's physical condition and take corresponding response measures based on different levels. With the assistance of this active safety improvement plan, on the one hand, it can effectively avoid the situation where the driver can complete normal driving but has physical conditions, and the risk of driving caused by the immediate start of automatic driving to deal with the driver's physical condition problems; at this time, the automatic driving function may interfere with and affect the driver's normal driving, causing the driver to misjudge the vehicle condition and cause some unnecessary automobile safety accidents; on the other hand, it can also take into account that when the driver's condition is very poor and can no longer complete normal driving, resulting in major safety hazards, the automatic driving function has a higher priority than the driver, and the driving rights of the car are taken over in time, avoiding the risk of automobile safety accidents caused by the driver's wrong operation of the vehicle due to coma, syncope, confusion and other behaviors. Based on the above considerations, a more comprehensive improvement of the active safety plan for automobiles can effectively avoid automobile safety accidents caused by problems with the driver's physical condition, improve the active safety performance of the vehicle, and greatly optimize the driver's driving experience.

[0072] Example 3

[0073] The present invention provides a vehicle automatic driving takeover system, which is used to implement the vehicle automatic driving takeover method described in the above technical solution, including: a fatigue level recognition module, an automatic driving takeover module;

[0074] The fatigue level recognition module is used to recognize the driver's fatigue level based on the driver's face image collected in real time;

[0075] The automatic driving takeover module is used to output corresponding reminders according to the driver's fatigue level, and choose to maintain the vehicle's driving through automatic driving or control the vehicle to pull over through automatic driving.

[0076] Example 4

[0077] The present invention provides a vehicle, comprising:

[0078] one or more processors;

[0079] A memory for storing one or more programs;

[0080] When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle automatic driving takeover method described in the above technical solution.

[0081] Example 5

[0082] The present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the vehicle automatic driving takeover method described in the above technical solution is implemented.

[0083] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0084] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0085] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0086] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0087] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

[0088] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.

Claims

1. A method for taking over automatic driving of a vehicle, characterized in that: The following steps are involved: Identify the driver's fatigue level based on the driver's facial image collected in real time; Output corresponding reminders based on the driver's fatigue level, and choose to maintain the vehicle's driving through automatic driving or control the vehicle to pull over through automatic driving.

2. A method according to claim 1, characterized in that: The process of identifying the driver's fatigue level based on the real-time collected driver's face image includes: real-time positioning of the lips in the driver's face image, and determining the driver's fatigue level based on the frequency of the lip change amplitude being greater than a set value.

3. A method according to claim 2, characterized in that: The process of identifying the driver's fatigue level based on the real-time collected driver's face image includes: real-time positioning of the eyes in the driver's face image, and determining the driver's fatigue level based on the frequency of the eye change amplitude within a set range.

4. A method according to claim 2, characterized in that: The lip change amplitude is: the change value of the distance between the upper and lower edges of the mouth at two adjacent sampling moments; the set value is: 1.5 times the distance between the upper and lower edges of the mouth at the previous sampling moment in two adjacent sampling moments; if the frequency of the lip change amplitude being greater than the set value is greater than the corresponding set standard, the driver's physical condition is marked as low and a corresponding prompt sound is output.

5. A method according to claim 4, characterized in that: The eye change amplitude is: the change value of the distance between the upper and lower edges of the eye at two adjacent sampling moments; the setting range includes a first setting range and a second setting range: The minimum value of the first setting range is: 0.25 times the distance between the upper and lower edges of the mouth at the previous sampling moment in two adjacent sampling moments; the maximum value of the first setting range is: 0.75 times the distance between the upper and lower edges of the mouth at the previous sampling moment in two adjacent sampling moments; if the frequency of the eye change amplitude in the first setting range is greater than the corresponding setting standard, the driver's physical condition is marked as low, the corresponding prompt sound is output, and the automatic driving is started to maintain the vehicle driving; The minimum value of the second setting range is: 0; the maximum value of the first setting range is: 0.25 times the distance between the upper and lower edges of the mouth at the previous sampling moment in two adjacent sampling moments; if the frequency of the eye change amplitude in the second setting range is greater than the corresponding setting standard, the driver's physical condition is marked as very low, the corresponding prompt sound is output, and the automatic driving is started to control the vehicle to pull over.

6. A method according to claim 5, characterized in that: If the driver's physical condition is marked as low, and the frequency of the lip changes exceeding the set value within the set time period is greater than the corresponding set standard, the driver's physical condition will be marked as low, the corresponding prompt sound will be output, and automatic driving will be started to maintain vehicle driving.

7. A method according to claim 5, characterized in that: If after the driver's physical condition is marked as low, if the frequency of the eye change amplitude being within the first set range within the set time period is greater than the corresponding set standard, the driver's physical condition will be marked as very low, a corresponding prompt sound will be output, and automatic driving will be started to control the vehicle to pull over.

8. A method according to claim 5, characterized in that: By locating the key points in the driver's facial image, several key points located at the upper edge and the lower edge of the mouth are determined respectively; the distance between the symmetrical key points corresponding to the upper edge and the lower edge of the mouth is calculated; the distance calculation values ​​between all the symmetrical key points are averaged to obtain the average distance between the upper and lower edges of the mouth.

9. A method according to claim 5, characterized in that: By locating key points in the driver's facial image, a number of key points located at the upper edge and the lower edge of the eyes are determined respectively; Calculate the distance between the symmetrical key points corresponding to the upper and lower edges of the glasses; average the calculated distance values ​​between all symmetrical key points to obtain the average distance between the upper and lower edges of the eyes.

10. A vehicle automatic driving takeover system, characterized in that: A method for implementing the vehicle automatic driving takeover method according to any one of claims 1 to 9, comprising: a fatigue level recognition module and an automatic driving takeover module; The fatigue level recognition module is used to recognize the driver's fatigue level based on the driver's face image collected in real time; The automatic driving takeover module is used to output corresponding reminders according to the driver's fatigue level, and choose to maintain the vehicle's driving through automatic driving or control the vehicle to pull over through automatic driving.

11. A vehicle, characterized in that: The vehicle comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle automatic driving takeover method as described in any one of claims 1-9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, it implements the vehicle automatic driving takeover method as described in any one of claims 1-9.

Images