A safe driving system based on facial recognition

Abstract

The embodiment of the present invention discloses a safe driving system based on facial recognition, which relates to the field of image recognition technology. The system includes: an image acquisition module, which is used to acquire images in a target vehicle in real time; an abnormal emotion recognition module, which is used to recognize the facial expression of the current driver in the image in the target vehicle, and judge whether the current driver has abnormal emotions according to the recognition result; a double flash control module, which is used to control the double flash lights of the target vehicle to turn on when the abnormal emotion recognition module recognizes that the current driver has abnormal emotions. The present invention can detect the driver's expression through facial recognition during vehicle driving, and give timely reminders when abnormal emotions such as pain and anger appear, effectively avoiding the occurrence of traffic accidents.

Description

Technical Field

[0001] The present invention belongs to the technical field of image recognition, and in particular relates to a safe driving system based on facial recognition. Background Art

[0002] With the rapid development of social economy, the number of vehicles is increasing day by day. Although the traffic is developing rapidly, the developed traffic roads cannot keep up with the demand of the development of the number of vehicles. In addition, the road traffic construction is changing with each passing day, which puts higher requirements on the driving ability of vehicle drivers. The number of novice drivers is gradually increasing, and there are many people who treat road traffic rules as air, which can easily lead to drivers driving with emotions, such as fighting, gambling, road rage, etc., which brings huge safety hazards to road driving. In addition, sudden illness of drivers will also bring greater safety hazards to vehicles.

[0003] The current vehicle driving monitoring and management solutions mainly use road monitoring to check vehicle violations, such as not wearing seat belts correctly, driving while talking on the phone, etc., or arrange traffic police to check drivers for drunk driving and other behaviors. Although this can reduce traffic accidents to a certain extent, it cannot effectively monitor and manage emotional situations such as sudden illness or road rage of drivers, and thus cannot effectively reduce traffic accidents caused by such reasons. Summary of the invention

[0004] In view of this, the embodiment of the present invention provides a safe driving system based on facial recognition, which is used to solve the problem that the existing vehicle driving monitoring and management solutions cannot effectively monitor and manage emotional situations such as sudden illness or road rage of the driver. The present invention can detect the driver's expression through facial recognition during vehicle driving, and promptly remind the driver when abnormal emotions such as pain and anger appear, effectively avoiding traffic accidents.

[0005] An embodiment of the present invention provides a safe driving system based on facial recognition, comprising:

[0006] An image acquisition module, used for acquiring images inside a target vehicle in real time;

[0007] an abnormal emotion recognition module, used to recognize the facial expression of the current driver in the image in the target vehicle, and determine whether the current driver has abnormal emotions according to the recognition result;

[0008] The double flash control module is used to control the double flash lights of the target vehicle to turn on when the abnormal emotion recognition module recognizes that the current driver has abnormal emotions.

[0009] In an optional embodiment, the abnormal emotion recognition module is specifically used to identify faces in the image within the target vehicle based on face recognition technology, extract the facial image of the current driver in the driving seat, and identify the facial expression type of the current driver in the facial image of the current driver based on a preset facial expression feature library, and determine whether the current driver has abnormal emotions based on the preset correspondence between abnormal emotions and facial expression types.

[0010] In an optional embodiment, the facial recognition-based safe driving system further includes:

[0011] The alarm device is used to give a voice alarm to the occupants of the target vehicle when the target vehicle is in an automatic double flash state; wherein the automatic double flash state is a state in which the double flash lights are controlled by the double flash control module to turn on and flash.

[0012] In an optional embodiment, the double flash control module is further used to record the first moment of controlling the double flash lights of the target vehicle to be turned on;

[0013] The alarm device comprises:

[0014] The first judgment module is used to judge whether the double flash lights of the target vehicle are turned off within a preset time after the target vehicle enters the automatic double flash state;

[0015] The voice alarm module is used to play a preset voice to warn the people in the car when the judgment result of the first judgment module is yes.

[0016] In an optional embodiment, the first determination module includes:

[0017] A double flash state monitoring unit is used to monitor the flashing state of the double flash lights of the target vehicle in real time starting from the time when the target vehicle enters the automatic double flash state; wherein the flashing state of the double flash lights includes: non-double flash state, automatic double flash state, and manual double flash state after being manually turned on by the vehicle occupant;

[0018] A trigger control value calculation unit, used to calculate the trigger control value of the in-vehicle alarm device at the current moment according to the first formula;

[0019] A judging unit is used to judge whether the trigger control value of the in-vehicle alarm device at the current moment is 1; if so, it is judged that the double flash lights of the target vehicle have not been turned off within a preset time after the target vehicle enters the automatic double flash state; otherwise, it is judged that the double flash lights of the target vehicle have been turned off within a preset time after the target vehicle enters the automatic double flash state;

[0020] The voice alarm module is specifically used to play a preset voice to warn the occupants of the vehicle when the judgment result of the judgment unit is yes, and determine the control volume value of the voice alarm according to the second formula and control the real-time volume of the preset voice accordingly;

[0021] Among them, the first formula is:

[0022] N(t)=G(t)×F(tt 0 -T)

[0023] In the first formula, N(t) represents the trigger control value of the in-vehicle alarm device at the current moment; t represents the current moment; G(t) represents the flashing state value of the double flash lights of the target vehicle at the current moment. If the target vehicle is in the automatic double flash state at the current moment, G(t) = 1; if the target vehicle is in the manual double flash state at the current moment, G(t) = -1; if the target vehicle is in the non-double flash state at the current moment, G(t) = 0; t 0 Indicates the initial moment when the target vehicle enters the automatic double flash state. If the target vehicle is in the automatic double flash state at the current moment, then t 0 is the first moment, if the target vehicle is not in the automatic double flash state at the current moment, then t 0 =0; T represents the preset duration; F() represents a positive function. If the value in the brackets is a positive number, the function value is 1; if the value in the brackets is a negative number or 0, the function value is 0;

[0024] The second formula is:

[0025]

[0026] In the second formula, D(t) represents the control volume value of the voice alarm at the current moment; D m Indicates the maximum volume value of the preset voice alarm; D 0 Indicates the preset minimum volume value of the voice alarm; N indicates the number of people in the current target vehicle; N m Indicates the maximum number of people that can be accommodated in the target vehicle; t D It indicates the second moment when the voice alarm module initially plays the preset voice to warn the people in the car.

[0027] In an optional embodiment, the abnormal emotion recognition module is further used to determine the number of people in the current target vehicle based on faces in the image of the target vehicle identified by face recognition technology.

[0028] In an optional embodiment, the voice alarm module is specifically used to periodically play a preset voice at a preset interval when the judgment result of the first judgment module is yes, until the double flash status monitoring unit detects that the double flash lights of the target vehicle have changed to a non-double flash state.

[0029] In an optional embodiment, the preset voice is a voice prompting the occupants to turn off the double flash button before repeating the voice message 5 times;

[0030] The alarm device further includes: an enabling control value calculation module and a GPRS module;

[0031] The enabling control value calculation module is used to calculate the GPRS enabling control value at the current moment according to the third formula when the judgment result of the judging unit is yes, and when the calculated GPRS enabling control value is 1, control the enabling of the GPRS module to be turned on, so as to make a telephone / text message alarm to the public security system through the GPRS module;

[0032] Wherein, the third formula is:

[0033] E(t)=F[(tt D )-(4×T e +5×T 0 )]

[0034] In the third formula, E(t) represents the GPRS enabling control value at the current moment; T e Indicates the interval between two consecutive preset voices played by the voice alarm module; T 0 Indicates the duration of playing a single preset voice.

[0035] The present invention provides a safe driving system based on facial recognition. First, an image acquisition module is used to collect images in a target vehicle in real time. Then, an abnormal emotion recognition module is used to identify and judge whether the current driver has abnormal emotions. Finally, when the current driver has abnormal emotions, a double flash control module is used to control the double flash lights of the target vehicle to turn on. The present invention can detect the driver's expression through facial recognition during vehicle driving, and can promptly remind the driver when he or she has abnormal emotions such as pain or anger, thereby effectively avoiding traffic accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A schematic diagram of the structure of a safe driving system based on facial recognition provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0039] It should be clear that the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] Figure 1 A schematic diagram of a safe driving system based on facial recognition provided by an embodiment of the present invention. Figure 1 , the system comprises:

[0041] Image acquisition module 1, used for real-time acquisition of images inside the target vehicle;

[0042] Abnormal emotion recognition module 2, used to recognize the facial expression of the current driver in the image in the target vehicle, and determine whether the current driver has abnormal emotions according to the recognition result;

[0043] The double flash control module 3 is used to control the double flash lights of the target vehicle to turn on when the abnormal emotion recognition module 2 recognizes that the current driver has abnormal emotions.

[0044] The beneficial effects of the above technical solution are as follows: the embodiment of the present invention provides a safe driving system based on facial recognition, firstly, the image acquisition module 1 acquires the image in the target vehicle in real time, then the abnormal emotion recognition module 2 recognizes and determines whether the current driver has abnormal emotions (such as sudden illness or road rage), and finally, when the current driver has abnormal emotions, the double flash control module 3 controls to turn on the double flash lights of the target vehicle. The present invention can detect the driver's expression through facial recognition during vehicle driving, and give timely reminders when abnormal emotions such as pain and anger appear, effectively avoiding traffic accidents.

[0045] As an optional embodiment, the abnormal emotion recognition module 2 is specifically used to identify faces in the image in the target vehicle based on face recognition technology, extract the face image of the current driver in the driving seat, and identify the facial expression type of the current driver in the face image of the current driver based on a preset facial expression feature library, and determine whether the current driver has abnormal emotions based on the preset correspondence between abnormal emotions and facial expression types.

[0046] The beneficial effect of the above technical solution is that a large number of facial images with abnormal emotions can be collected, and through big data statistical analysis and graphic recognition technology, an abnormal emotion facial expression feature library can be obtained, and then this feature library is used to identify the facial expression type of the current driver, with high accuracy in abnormal emotion recognition.

[0047] As an optional embodiment, the facial recognition-based safe driving system further includes:

[0048] The alarm device is used to give a voice alarm to the occupants of the target vehicle when the target vehicle is in an automatic double flash state; wherein the automatic double flash state is a state in which the double flash lights are controlled by the double flash control module to turn on and flash.

[0049] The beneficial effect of the above technical solution is: when it is identified that the current driver has abnormal emotions, on the one hand, the double flash lights can be used to remind the surrounding vehicles and people in the car, and on the other hand, a voice alarm can be used to notify the people in the car, so as to facilitate timely response measures, thereby effectively reducing the impact of abnormal emotions on the safe driving of the vehicle and effectively improving driving safety.

[0050] As an optional embodiment, the double flash control module is further used to record the first moment of controlling the double flash lights of the target vehicle to be turned on;

[0051] The alarm device comprises:

[0052] The first judgment module is used to judge whether the double flash lights of the target vehicle are turned off within a preset time after the target vehicle enters the automatic double flash state;

[0053] The voice alarm module is used to play a preset voice to warn the people in the car when the judgment result of the first judgment module is yes.

[0054] The beneficial effect of the above technical solution is: when it is identified that the current driver has abnormal emotions, the automatic double flash lights are used to remind all people in the car that the current driver has abnormal emotions. After the preset time, if the abnormal emotions are not dealt with in time, that is, no one turns off the double flash lights, a preset voice is played to alarm the people in the car, which effectively improves the intelligence level of the system.

[0055] As an optional embodiment, the first determination module includes:

[0056] The double flash state monitoring unit is used to monitor the flashing state of the double flash lights of the target vehicle in real time starting from the time when the target vehicle enters the automatic double flash state; wherein the flashing state of the double flash lights includes: non-double flash state, automatic double flash state, and manual double flash state after being manually turned on by the person in the vehicle; wherein, considering that after the double flash control module controls the double flash lights of the target vehicle to be turned on so that the target vehicle enters the automatic double flash state, at a certain moment the user in the vehicle manually clicks the double flash lights, then from this moment on, the double flash state monitoring unit considers that the flashing state of the double flash lights of the target vehicle detected at the current moment is the manual double flash state, until the double flash lights are turned off;

[0057] A trigger control value calculation unit, used to calculate the trigger control value of the in-vehicle alarm device at the current moment according to the first formula;

[0058] A judging unit is used to judge whether the trigger control value of the in-vehicle alarm device at the current moment is 1; if so, it is judged that the double flash lights of the target vehicle have not been turned off within a preset time after the target vehicle enters the automatic double flash state; otherwise, it is judged that the double flash lights of the target vehicle have been turned off within a preset time after the target vehicle enters the automatic double flash state;

[0059] The voice alarm module is specifically used to play a preset voice to warn the occupants of the vehicle when the judgment result of the judgment unit is yes, and determine the control volume value of the voice alarm according to the second formula and control the real-time volume of the preset voice accordingly;

[0060] Among them, the first formula is:

[0061] N(t)=G(t)×F(tt 0 -T) (1)

[0062] In the first formula, N(t) represents the trigger control value of the in-vehicle alarm device at the current moment, N(t)=1, it is determined that the double flash lights of the target vehicle have not been turned off within the preset time after the target vehicle enters the automatic double flash state, and N(t)=0, it is determined that the double flash lights of the target vehicle have been turned off within the preset time after the target vehicle enters the automatic double flash state; t represents the current moment; G(t) represents the flashing state value of the double flash lights of the target vehicle at the current moment, if the target vehicle is in the automatic double flash state at the current moment, G(t)=1, if the target vehicle is in the manual double flash state at the current moment, G(t)=-1, if the target vehicle is in the non-double flash state at the current moment, G(t)=0; t 0 Indicates the initial moment when the target vehicle enters the automatic double flash state. If the target vehicle is in the automatic double flash state at the current moment, then t 0 is the first moment, if the target vehicle is not in the automatic double flash state at the current moment, then t 0=0; T represents the preset duration; F() represents a positive function. If the value in the brackets is a positive number, the function value is 1; if the value in the brackets is a negative number or 0, the function value is 0;

[0063] The second formula is:

[0064]

[0065] In the second formula, D(t) represents the control volume value of the voice alarm at the current moment; D m Indicates the maximum volume value of the preset voice alarm; D 0 Indicates the preset minimum volume value of the voice alarm; N indicates the number of people in the current target vehicle; N m Indicates the maximum number of people that can be accommodated in the target vehicle; t D It indicates the second moment when the voice alarm module initially plays the preset voice to warn the people in the car.

[0066] Preferably, the abnormal emotion recognition module 2 is further used to determine the number of people in the current target vehicle based on faces in the image of the target vehicle identified by face recognition technology.

[0067] The beneficial effects of the above technical solution are as follows: the first formula (1) is used to control the triggering status of the alarm device in the car according to the current double flash state of the car and the current moment, thereby performing intelligent analysis according to the automatic and manual status of the double flash lights, reflecting the intelligent characteristics of the system; and then the second formula (2) is used to control the volume of the voice alarm according to the number of people in the car, thereby effectively reminding all people in the car of abnormal conditions while saving energy.

[0068] As an optional embodiment, the voice alarm module is specifically used to periodically play a preset voice at a preset interval when the judgment result of the first judgment module is yes, until the double flash status monitoring unit detects that the double flash lights of the target vehicle have changed to a non-double flash state.

[0069] The beneficial effects of the above technical solution are: the preset voice can be played periodically at a preset interval to remind the occupants of the vehicle that the current driver is in an abnormal mood, so as to facilitate timely response and treatment. After the treatment is completed, the voice reminder can be turned off by turning off the double flash lights. If no response is taken, the voice reminder and the double flash lights can be made to flash for continuous reminders. On the one hand, it can effectively remind the passengers in the vehicle to take timely emergency measures, and on the other hand, it can also turn off the reminder in time to save energy, effectively improving the intelligence level of the system.

[0070] As an optional embodiment, the preset voice is a voice prompting the occupants to turn off the double flash button before repeating the voice message 5 times;

[0071] The alarm device further includes: an enabling control value calculation module and a GPRS module;

[0072] The enabling control value calculation module is used to calculate the GPRS enabling control value at the current moment according to the third formula when the judgment result of the judging unit is yes, and when the calculated GPRS enabling control value is 1, control the enabling of the GPRS module to be turned on, so as to make a telephone / text message alarm to the public security system through the GPRS module;

[0073] Wherein, the third formula is:

[0074] E(t)=F[(tt D )-(4×T e +5×T 0 )] (3)

[0075] In the third formula, E(t) represents the GPRS enabling control value at the current moment; T e Indicates the interval between two consecutive preset voices played by the voice alarm module; T 0 Indicates the duration of playing a single preset voice.

[0076] In this embodiment, when the judgment result of the judgment unit is yes, the enabling control value calculation module can, according to the third formula, make a telephone / text message alarm to the public security system when the GPRS enabling control value is calculated to be equal to 1 for the first time; or calculate the GPRS enabling control value once at every preset period, and make a telephone / text message alarm to the public security system every time the GPRS enabling control value is calculated to be equal to 1, thereby effectively improving the safety of the vehicle.

[0077] The beneficial effect of the above technical solution is: using the third formula (3) to control the enabling of the GPRS module in the alarm device according to the duration of a single voice alarm reminder, the interval between two adjacent voice alarm reminders, the current time and the time when the in-vehicle alarm device is controlled to be triggered, and then when no feedback is received from the occupants for a long time, a telephone and text message alarm is issued to ensure the reliability of rescue.

[0078] It can be seen from the contents of the above embodiments that during driving, the driver's expression is detected by facial recognition, and timely reminders or even alarms are given when abnormal emotions such as pain and anger appear; specifically: if the driver's expression is detected, and abnormal emotions such as pain and anger appear, the double flash button of the car will be automatically lit first to make the car enter the automatic double flash state, so that the car is currently in the double flash state and starts timing. If the double flash button in the cab is turned off within a preset time when the car is in the automatic double flash state, the alarm device will not be triggered. If the double flash button in the cab is not turned off within a preset time when the car is in the automatic double flash state, the alarm device is triggered. The alarm of the alarm device is divided into two states, one state is to start the speaker in the car for voice reminder, and control the volume of the voice alarm according to the number of people in the car. The voice will remind the user in the car that the driver is currently in an abnormal state and whether an alarm rescue is needed. If not, please turn off the double flash button before repeating the voice message 5 times. If the voice reminder is repeated 5 times and the car is still in the automatic double flash state, the GPRS module in the alarm device is controlled to make a telephone or text message alarm, so as to more effectively avoid traffic accidents.

[0079] 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 An apparatus for the method specified in one or more blocks.

[0080] 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 The method specified in one or more boxes.

[0081] 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 in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of a method specified in one or more boxes.

[0082] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these changes and variations. The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A safe driving system based on facial recognition, characterized in that: include: An image acquisition module, used for acquiring images inside a target vehicle in real time; an abnormal emotion recognition module, used to recognize the facial expression of the current driver in the image in the target vehicle, and determine whether the current driver has abnormal emotions according to the recognition result; A double flash control module, used to control turning on the double flash lights of the target vehicle when the abnormal emotion recognition module identifies that the current driver has abnormal emotions; Wherein, the system further comprises: An alarm device is used to give a voice alarm to the occupants of the target vehicle when the target vehicle is in an automatic double flash state; wherein the automatic double flash state is a state in which the double flash lights are controlled by the double flash control module to turn on and flash; The double flash control module is further used to record the first moment of turning on the double flash lights of the target vehicle; The alarm device comprises: The first judgment module is used to judge whether the double flash lights of the target vehicle are turned off within a preset time after the target vehicle enters the automatic double flash state; A voice alarm module, used to play a preset voice to warn the occupants of the vehicle when the judgment result of the first judgment module is yes; Wherein, the first judgment module includes: A double flash state monitoring unit is used to monitor the flashing state of the double flash lights of the target vehicle in real time starting from the time when the target vehicle enters the automatic double flash state; wherein the flashing state of the double flash lights includes: non-double flash state, automatic double flash state, and manual double flash state after being manually turned on by the vehicle occupant; A trigger control value calculation unit, used to calculate the trigger control value of the in-vehicle alarm device at the current moment according to the first formula; A judging unit is used to judge whether the trigger control value of the in-vehicle alarm device at the current moment is 1; if so, it is judged that the double flash lights of the target vehicle have not been turned off within a preset time after the target vehicle enters the automatic double flash state; otherwise, it is judged that the double flash lights of the target vehicle have been turned off within a preset time after the target vehicle enters the automatic double flash state; The voice alarm module is specifically used to play a preset voice to warn the occupants of the vehicle when the judgment result of the judgment unit is yes, and determine the control volume value of the voice alarm according to the second formula and control the real-time volume of the preset voice accordingly; Among them, the first formula is: In the first formula, Indicates the trigger control value of the alarm device in the car at the current moment; Indicates the current moment; Indicates the flashing status value of the target vehicle's double flash lights at the current moment. If the target vehicle is in the automatic double flash state at the current moment, If the target vehicle is in manual double flash state at the current moment, If the target vehicle is not in the double flash state at the current moment, ; Indicates the initial moment when the target vehicle enters the automatic double flash state. If the target vehicle is in the automatic double flash state at the current moment, is the first moment, if the target vehicle is not in the automatic double flash state at the current moment ; Indicates the preset duration; Represents a positive function. If the value in the brackets is a positive number, the function value is 1. If the value in the brackets is a negative number or 0, the function value is 0. The second formula is: In the second formula, Indicates the control volume value of the voice alarm at the current moment; Indicates the maximum volume value of the preset voice alarm; Indicates the preset minimum volume value of the voice alarm; Indicates the number of people in the current target vehicle; Indicates the maximum number of people that can be accommodated in the target vehicle; It indicates the second moment when the voice alarm module initially plays the preset voice to warn the people in the car.

2. The facial recognition-based safe driving system according to claim 1, characterized in that: The abnormal emotion recognition module is specifically used to identify the face in the image in the target vehicle based on face recognition technology, extract the face image of the current driver in the driving seat, and identify the facial expression type of the current driver in the face image of the current driver based on a preset facial expression feature library, and determine whether the current driver has abnormal emotions based on the preset correspondence between abnormal emotions and facial expression types.

3. The facial recognition-based safe driving system according to claim 1, characterized in that: The abnormal emotion recognition module is also used to determine the number of people in the current target vehicle based on the faces in the image of the target vehicle identified by face recognition technology.

4. The facial recognition-based safe driving system according to claim 1, characterized in that: The voice alarm module is specifically used to periodically play a preset voice according to a preset interval when the judgment result of the first judgment module is yes, until the double flash state monitoring unit detects that the double flash lights of the target vehicle have changed to a non-double flash state.

5. The facial recognition-based safe driving system according to claim 4, characterized in that: The preset voice is a voice that prompts the occupants to turn off the double flash button before repeating the voice message 5 times; The alarm device further includes: an enabling control value calculation module and a GPRS module; The enabling control value calculation module is used to calculate the GPRS enabling control value at the current moment according to the third formula when the judgment result of the judging unit is yes, and when the calculated GPRS enabling control value is 1, control the enabling of the GPRS module to be turned on, so as to make a telephone / text message alarm to the public security system through the GPRS module; Wherein, the third formula is: In the third formula, Indicates the GPRS enabling control value at the current moment; Indicates the interval between two consecutive preset voices played by the voice alarm module; Indicates the duration of playing a single preset voice.

Images