A vehicle control method, apparatus, device, and medium

Abstract

The application discloses a vehicle control method, device, equipment and medium, comprising: detecting whether a user has a driving intention for a target vehicle; when it is detected that the user has the driving intention for the target vehicle, generating a facial action prompt signal, the facial action prompt signal comprising a target facial action that needs to be performed by the user; collecting a facial image set of the user; determining an actual matching degree between an actual facial action of the user and the target facial action according to the facial image set; and determining whether the target vehicle responds to the driving operation of the user according to the actual matching degree and a preset matching degree. The application can determine whether the user has the possibility of drunk driving based on the response image of the user to the facial action prompt signal, and then determine whether the target vehicle responds to the driving operation of the user according to the possibility of drunk driving, thereby restraining the behavior of drunk driving of the driver, reducing the occurrence probability of the behavior of drunk driving, and improving the driving safety.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle driving, and in particular to a vehicle control method, device, equipment and medium. BACKGROUND

[0002] The popularity of automobiles greatly facilitates people's life, but traffic accidents caused by automobile driving seriously affect the safety of drivers and pedestrians, and drunk driving is the main cause of traffic accidents.

[0003] In related technologies, the relevant departments mainly set up checkpoints on the road to randomly check whether the driver has drunk driving behavior, but this way of constraint has limited effect, and some drivers have the psychology of taking chances and still insist on drunk driving, thus there is a driving safety hazard. Therefore, how to reduce the probability of drunk driving is a problem to be solved at present. SUMMARY

[0004] The embodiments of the present application provide a vehicle control method, device, equipment and medium, which solve the technical problem that the prior art cannot effectively reduce the probability of drunk driving, and achieve the technical effect of reducing the probability of drunk driving.

[0005] In a first aspect, the present application provides a vehicle control method, which comprises:

[0006] detecting whether a user has a driving intention for a target vehicle;

[0007] when it is detected that the user has a driving intention for the target vehicle, generating a facial action prompt signal, the facial action prompt signal comprising a target facial action that needs to be performed by the user;

[0008] collecting a facial image set of the user;

[0009] determining an actual matching degree of the actual facial action of the user and the target facial action according to the facial image set;

[0010] determining whether the target vehicle responds to the driving operation of the user according to the actual matching degree and a preset matching degree.

[0011] Further, determining the actual matching degree of the actual facial action of the user and the target facial action according to the facial image set comprises:

[0012] determining an actual reaction time length of the user responding to the facial action prompt signal according to the facial image set;

[0013] when the actual reaction time length is less than a preset reaction time length, determining the actual matching degree of the actual facial action of the user and the target facial action according to the facial image set.

[0014] Further, after collecting the facial image set of the user, the method further comprises:

[0015] determining an actual shaking frequency of the face of the user according to the facial image set;

[0016] determining whether the target vehicle responds to the driving operation of the user according to the actual matching degree and the preset matching degree, comprising:

[0017] determining whether the target vehicle responds to the driving operation of the user according to the actual matching degree, the preset matching degree, and the actual shaking frequency and the preset shaking frequency.

[0018] Further, when it is determined that the target vehicle prohibits responding to the driving operation of the user, the method further comprises:

[0019] updating the target facial action included in the facial action prompt signal, and re-collecting the facial image set of the user;

[0020] determining whether the target vehicle responds to the driving operation of the user according to the re-collected facial image set of the user.

[0021] Further, after determining that the target vehicle responds to the driving operation of the user, the method further comprises:

[0022] monitoring whether the user has a diet action;

[0023] after determining that the user has a diet action, generating a retest prompt signal, the retest prompt signal including a retest facial action to be performed by the user;

[0024] collecting a retest image set of the user;

[0025] determining whether the target vehicle continues to respond to the driving operation of the user according to the retest image set.

[0026] Further, detecting whether the user has a driving intention for the target vehicle, comprising:

[0027] obtaining a seat signal and a safety belt signal of a driving seat of the target vehicle and an ignition signal of the target vehicle;

[0028] determining whether the user has a driving intention for the target vehicle according to the seat signal, the safety belt signal and the ignition signal.

[0029] Further, the target facial action includes at least one of an eye action, a mouth action and an expression action.

[0030] In a second aspect, the present application provides a vehicle control device, the device comprising:

[0031] a driving intention detection module for detecting whether the user has a driving intention for the target vehicle;

[0032] The signal generation module is configured to generate a facial action prompt signal when it is detected that the user has a driving intention for the target vehicle, the facial action prompt signal including a target facial action that needs to be performed by the user.

[0033] The image acquisition module is configured to acquire a facial image set of the user.

[0034] The matching degree determination module is configured to determine an actual matching degree between the actual facial action of the user and the target facial action according to the facial image set.

[0035] The driving judgment module is configured to determine whether the target vehicle responds to the driving operation of the user according to the actual matching degree and the preset matching degree.

[0036] Further, the matching degree determination module comprises:

[0037] The reaction time determination submodule is configured to determine an actual reaction time of the user in response to the facial action prompt signal according to the facial image set.

[0038] The matching degree determination submodule is configured to determine an actual matching degree between the actual facial action of the user and the target facial action according to the facial image set when the actual reaction time is less than the preset reaction time.

[0039] Further, the device further comprises:

[0040] The shaking frequency determination module is configured to determine an actual shaking frequency of the face of the user according to the facial image set after the facial image set of the user is acquired.

[0041] The driving judgment module is configured to determine whether the target vehicle responds to the driving operation of the user according to the actual matching degree, the preset matching degree, and the actual shaking frequency and the preset shaking frequency.

[0042] Further, the device further comprises:

[0043] The action updating module is configured to update the target facial action included in the facial action prompt signal and reacquire the facial image set of the user when it is determined that the target vehicle prohibits the driving operation of the user.

[0044] The driving judgment module is configured to determine whether the target vehicle responds to the driving operation of the user according to the reacquired facial image set of the user.

[0045] Further, the device further comprises:

[0046] The action monitoring module is configured to monitor whether the user has a drinking action after it is determined that the target vehicle responds to the driving operation of the user.

[0047] The signal generation module is configured to generate a retest prompt signal after determining that the user performs the eating action, the retest prompt signal including a retest facial action that needs to be performed by the user.

[0048] The image acquisition module is configured to acquire a retest image set of the user.

[0049] The driving judgment module is configured to determine whether the target vehicle continues to respond to the driving operation of the user according to the retest image set.

[0050] Further, the driving intention detection module is configured to:

[0051] acquire a seat signal and a safety belt signal of a driving seat of the target vehicle and an ignition signal of the target vehicle;

[0052] determine whether the user has the driving intention for the target vehicle according to the seat signal, the safety belt signal and the ignition signal.

[0053] Further, the target facial action includes at least one of an eye action, a mouth action and an expression action.

[0054] In a third aspect, the present application provides an electronic device, including:

[0055] a processor;

[0056] a memory for storing processor-executable instructions;

[0057] The processor is configured to execute to implement the vehicle control method provided in the first aspect.

[0058] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium, when instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the vehicle control method provided in the first aspect.

[0059] The one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0060] When it is detected that the user has the driving intention for the target vehicle, the facial action prompt signal is generated to remind the user to perform the corresponding target facial action, the image of the face of the user is acquired and recognized, the matching degree between the actual facial action of the user and the target facial action is determined, and then it is determined whether the target vehicle responds to the driving operation of the user. It can be seen that the embodiment can determine whether the user has the possibility of drunk driving based on the response image of the user to the facial action prompt signal, and then determine whether the target vehicle responds to the driving operation of the user according to the possibility of drunk driving, thereby restraining the behavior of drunk driving of the driver, reducing the probability of occurrence of drunk driving behavior, and improving the driving safety. BRIEF DESCRIPTION OF DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0062] Figure 1 A flowchart of a vehicle control method provided by the present application;

[0063] Figure 2 A structural diagram of a vehicle control device provided by the present application;

[0064] Figure 3 A structural diagram of an electronic device provided by the present application. DETAILED DESCRIPTION

[0065] The embodiments of the present application provide a vehicle control method, which solves the technical problem that the occurrence probability of drunk driving cannot be effectively reduced in the prior art.

[0066] The technical solutions of the embodiments of the present application are as follows to solve the above technical problem:

[0067] A vehicle control method, the method comprising: detecting whether a user has a driving intention for a target vehicle; when it is detected that the user has the driving intention for the target vehicle, generating a facial action prompt signal, the facial action prompt signal comprising a target facial action required to be performed by the user; collecting a facial image set of the user; determining an actual matching degree between an actual facial action of the user and the target facial action according to the facial image set; and determining whether the target vehicle responds to a driving operation of the user according to the actual matching degree and a preset matching degree.

[0068] When it is detected that the user has the driving intention for the target vehicle, the embodiments generate the facial action prompt signal to remind the user to perform the corresponding target facial action, collect and identify the image of the user's face, determine the matching degree between the actual facial action of the user and the target facial action, and then determine whether the target vehicle responds to the driving operation of the user. It can be seen that the embodiments can determine whether the user has the possibility of drunk driving based on the response image of the user to the facial action prompt signal, and then determine whether the target vehicle responds to the driving operation of the user according to the possibility of drunk driving, thereby restraining the behavior of drunk driving of the driver, reducing the occurrence probability of the behavior of drunk driving, and improving the driving safety.

[0069] In order to better understand the above technical solutions, the above technical solutions will be described in detail in combination with the drawings of the specification and specific embodiments.

[0070] Firstly, the term "and / or" appearing in the present document only describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in the present document generally represents an "or" relationship between the front and rear associated objects.

[0071] The embodiment provides a vehicle control method as shown in the figure. Figure 1 The method comprises steps S11-S15.

[0072] Step S11, detecting whether the user has a driving intention for the target vehicle;

[0073] Step S12, when it is detected that the user has a driving intention for the target vehicle, a facial action prompt signal is generated, and the facial action prompt signal includes a target facial action required to be performed by the user;

[0074] Step S13, collecting a facial image set of the user;

[0075] Step S14, determining an actual matching degree between the actual facial action of the user and the target facial action according to the facial image set;

[0076] Step S15, determining whether the target vehicle responds to the driving operation of the user according to the actual matching degree and a preset matching degree.

[0077] The vehicle control method provided by the embodiment can be executed by the vehicle-mounted controller of the target vehicle, or by the cloud server. When executed by the cloud server, a communication connection needs to be established between the cloud server and the target vehicle. The embodiment only takes the vehicle control method executed by the vehicle-mounted controller of the target vehicle as an example for subsequent description.

[0078] The target vehicle related in the embodiment needs to be configured with a camera, which can be an infrared camera. The camera can collect images of the area where the driving position of the target vehicle is located. The embodiment can be applied to most types of vehicles. For vehicles without a camera inside, a camera can also be added to achieve the same effect. It can be seen that the embodiment is simple to use, low in cost, and easy to install.

[0079] Regarding step S11, whether the user has a driving intention for the target vehicle is detected.

[0080] Whether the user has a driving intention for the target vehicle can be detected through steps S111-S112.

[0081] Step S111, acquiring a seat signal and a safety belt signal of the driving position of the target vehicle and an ignition signal of the target vehicle.

[0082] Step S112, according to the ride signal, the seat belt signal and the ignition signal, determine whether the user has driving intention to the target vehicle.

[0083] The ride signal of the driver's seat can be the signal generated by the weight sensor or pressure sensor of the driver's seat. The signal detected by the weight sensor or pressure sensor determines whether there is a user on the driver's seat. In addition, the camera inside the target vehicle can also be used for image acquisition, and image recognition can be used to determine whether there is a user on the driver's seat.

[0084] The seat belt signal can be the seat belt buckle signal of the driver's seat. For details, please refer to the related art, which will not be described here.

[0085] The ignition signal can be generated by the user turning the key of the target vehicle, or by the user touching the one-key start button, or by the user through voice control. The specific ignition mode can be determined according to the target vehicle, and this embodiment does not limit it.

[0086] When the ride signal shows that the driver's seat of the target vehicle has a user, the seat belt of the driver's seat has been buckled, and the user's ignition signal has been received, it can be determined that the user has driving intention to the target vehicle. At this time, it is necessary to judge the possibility of drunk driving of the user, that is, steps S12-S15 are continued.

[0087] Regarding step S12, when it is detected that the user has driving intention to the target vehicle, a facial action prompt signal is generated, which includes the target facial action that needs to be performed by the user.

[0088] When it is determined that the user has the demand to drive the target vehicle, a facial action prompt signal is generated, and the facial action prompt signal is displayed to the user through at least one of the display screen, the mobile terminal and the voice prompt. For example, the target vehicle display screen or the user's mobile terminal can be used to display the facial action prompt signal to the user, and the display content can be a picture, a video or a combination of a picture and a video; the target vehicle's car-mounted loudspeaker can be used to convey the facial action prompt signal to the user.

[0089] The target facial action includes at least one of the eye action, the mouth action and the expression action. The eye action can be blinking, closing eyes, looking left, looking right, looking up, looking down, etc. The mouth action can be opening mouth, closing mouth, sticking out tongue, etc. The expression action refers to the combination of the whole facial action, such as smile, cry, surprise, etc. The target facial action can be selected from a pre-set database, and the number of target facial actions in the pre-stored database can be multiple, such as 6. Each facial action prompt signal includes at least one target facial action.

[0090] In addition, the facial action prompt signal can also be a piece of text, and the user will use the lips when reading the text, and the text can correspond to the mouth action, which can be used as the target facial action. In actual operation, the text can be selected from a preset database, and the text can be a text with a large difference in lip action, such as “ah oh fish”, so as to improve the accuracy of subsequent recognition of the mouth action.

[0091] The facial action prompt signal can also be a question, and the user will use the lips when answering the question, and the answer will also correspond to the mouth action, which can be used as the target facial action. In actual operation, the question can be selected from a preset database, and the answer corresponding to the question can be a text with a large difference in lip action, such as “China” and “ocean”, so as to improve the accuracy of subsequent recognition of the mouth action.

[0092] Further, the audio data of the user reading the text or answering the question can also be collected through the microphone of the target vehicle, and then the audio data is identified to determine whether the user reads the text or answers the question accurately, and then the accuracy of the mouth action of the user can be reflected from the side, and the recognition accuracy of the mouth action is improved.

[0093] Regarding step S13, the facial image set of the user is collected.

[0094] The facial image set can be a picture set collected at a preset frequency, or a video, which is not limited in the embodiment.

[0095] After the facial image of the user is collected, the face recognition of the user can be performed to determine the identity information of the current user, and then it can be determined whether the current user is a legal user of the target vehicle, which can prevent illegal personnel from stealing the target vehicle to a certain extent. If the current user is a legal user, the historical record of the current user using the target vehicle can be queried to determine whether the current user has a history of drunk driving, which can provide a judgment tendency for subsequent determination of whether the user has a possibility of drunk driving this time, and the judgment difficulty of drunk driving can also be adjusted according to whether there is a history of drunk driving, for example, a more accurate judgment method is used for judgment if there is a history of drunk driving, or the difficulty of the target facial action is increased to improve the constraint of the user's self-consciousness to avoid drunk driving behavior. In addition, the image of the face of the driver's seat is collected by the camera, which can also avoid the replacement of the user on the driver's seat by other people on the non-driver's seat to perform the judgment of drunk driving, and effectively reduce the probability of cheating behavior.

[0096] As to step S14, the actual matching degree between the actual facial action of the user and the target facial action is determined according to the facial image set.

[0097] The facial image set records the actual facial action of the user, and the similarity between the facial image corresponding to the actual facial action and the standard image with the target facial action is determined by image comparison, and the similarity is taken as the actual matching degree. For example, the facial image recording the actual facial action is denoted as A, and the standard image with the target facial action is denoted as B. The facial actions shown in images A and B are compared to determine the similarity. Among them, image B can be an image taken when the user makes the target facial action in the target vehicle in a non-drunk state.

[0098] In addition, in addition to the above-mentioned image and image comparison method, a pre-trained neural network model can also be used to determine the matching degree between the actual facial action and the target facial action. For example, for each target facial action, the user takes a plurality of standard facial images corresponding to each target facial action in a non-drunk state, and extracts features of these standard facial images through a neural network model, so that the neural network model can recognize each target facial action. Then input the facial image set obtained in step S13 into the neural network model, and make the neural network model output the actual matching degree between the features of the actual facial action and the features of the target facial action.

[0099] As to step S15, whether the target vehicle responds to the driving operation of the user is determined according to the actual matching degree and the preset matching degree.

[0100] When the actual matching degree is less than the preset matching degree, it means that the user's facial control is difficult, and the possibility of drunk driving is higher. At this time, the target vehicle can be prohibited from responding to the driving operation of the user, and then the user is forced to be restrained, thereby reducing the probability of drunk driving.

[0101] In actual operation, the actual matching degree may be less than the preset matching degree due to occasional errors in the facial expression of the user. In order to reduce the probability of misjudging drunk driving behavior caused by occasional errors, when it is determined that the target vehicle prohibits responding to the driving operation of the user, the method further includes steps S151-S152.

[0102] Step S151, updating the target facial action included in the facial action prompt signal, and reacquiring the facial image set of the user;

[0103] Step S152, determining whether the target vehicle responds to the driving operation of the user according to the reacquired facial image set of the user.

[0104] After determining that the target vehicle is prohibited from responding to the user's driving operation, the target facial action can be updated, and the facial image set of the user is re-acquired after updating the facial action prompt signal, and then it is re-determined whether the user has the possibility of drunk driving. The principle of step S152 is similar to that of steps S14-S15, and specific reference can be made to the related content of steps S14-S15, which will not be repeated here.

[0105] It can be seen that by updating the target facial action and re-acquiring the facial image of the user, the probability of misjudgment of drunk driving caused by occasional mistakes of the user can be reduced to a certain extent, and the degree of influence on the user's normal driving of the target vehicle is reduced.

[0106] When the actual matching degree is greater than the preset matching degree, it means that the user's facial control is relatively easy, and the possibility of drunk driving is small. At this time, the target vehicle is allowed to respond to the user's driving operation, so that the user can normally drive the target vehicle.

[0107] After determining that the target vehicle responds to the user's driving operation, the user can normally drive the target vehicle, but the user may drink during driving to evade the drunk driving start monitoring of the target vehicle. In order to reduce the probability of drunk driving of the user during driving, the embodiment also provides steps S153-S156 to monitor the user's behavior during driving.

[0108] Step S153, monitoring whether the user has a food and drink action;

[0109] Step S154, after determining that the user has a food and drink action, generating a retest prompt signal, the retest prompt signal including a retest facial action to be performed by the user;

[0110] Step S155, acquiring a retest image set of the user;

[0111] Step S156, determining whether the target vehicle continues to respond to the user's driving operation according to the retest image set.

[0112] Monitoring whether the user has a food and drink action can be achieved by image acquisition of the user by the camera, analyzing and determining the image of the user during driving to determine whether the user has a food and drink action.

[0113] When the eating action of the user is monitored, a retest prompt signal is generated, and the retest prompt signal is displayed to the user through at least one of a display screen, a mobile terminal, and voice prompting. The retest prompt signal is used to remind the user to perform the corresponding retest facial action. In actual operation, performing the retest facial action by the user during driving increases the driving risk and has a safety hazard. In order to reduce the safety hazard, the retest prompt signal can also include a prompt for the user to park on the roadside in time and complete the retest facial action.

[0114] After the retest prompt signal is displayed to the user, a retest image set of the user can be collected, the matching degree between the actual retest action of the user and the retest facial action is determined according to the retest image set, and then it is determined whether the target vehicle continues to respond to the driving operation of the user. If the matching degree is lower than a preset matching degree, the target vehicle is prohibited to continue to respond to the driving operation of the user, and if the matching degree exceeds the preset matching degree, the target vehicle is allowed to continue to respond to the driving operation of the user. The principle of step S156 is similar to that of steps S14 and S15, and specific reference can be made to the related description of steps S14 and S15, which will not be described here again.

[0115] It can be seen that, by image collection during driving of the user, the retest of drunk driving behavior of the user is performed after the eating action of the user is monitored, so as to constrain the drinking behavior of the user during driving, and then the occurrence probability of drunk driving is reduced and the driving safety is improved.

[0116] In summary, when the driving intention of the user to the target vehicle is detected, the facial action prompt signal is generated to remind the user to perform the corresponding target facial action, the image of the face of the user is collected and image recognition is performed, the matching degree between the actual facial action of the user and the target facial action is determined, and then it is determined whether the target vehicle responds to the driving operation of the user. It can be seen that, the possibility of drunk driving of the user can be determined based on the response image of the user to the facial action prompt signal, and then it is determined whether the target vehicle responds to the driving operation of the user according to the possibility of drunk driving, so as to constrain the drunk driving behavior of the driver, reduce the occurrence probability of drunk driving behavior, and improve the driving safety.

[0117] Further, on the basis of the foregoing scheme, the embodiment further provides a vehicle control method, including steps S21-S26.

[0118] Step S21, detecting whether the user has a driving intention to the target vehicle;

[0119] Step S22, when it is detected that the user has a driving intention to the target vehicle, a facial action prompt signal is generated, and the facial action prompt signal includes a target facial action to be performed by the user;

[0120] Step S23, collect the facial image set of the user;

[0121] Step S24, determine the actual reaction time of the user responding to the facial action prompt signal according to the facial image set;

[0122] Step S25, when the actual reaction time is less than the preset reaction time, determine the actual matching degree between the actual facial action of the user and the target facial action according to the facial image set;

[0123] Step S26, determine whether the target vehicle responds to the driving operation of the user according to the actual matching degree and the preset matching degree.

[0124] Steps S21-S23 are similar to steps S11-S13, and details can be referred to the related content of steps S11-S13, which will not be repeated here.

[0125] Regarding step S24, the actual reaction time of the user responding to the facial action prompt signal can be determined according to the facial image set, that is, the reaction time from when the user hears or sees the facial action prompt signal to when the user's face starts to change. The longer the reaction time, the more scattered the user's attention, and the higher the possibility of drunk driving. The shorter the reaction time, the more concentrated the user's attention, and the lower the possibility of drunk driving.

[0126] The reaction time of different drivers under the condition of non-drinking driving can be statistically analyzed to determine the corresponding preset reaction time. The actual reaction time is compared with the preset reaction time (for example, 5 seconds) to measure whether the current user of the target vehicle has a situation of attention dispersion.

[0127] When the actual reaction time is greater than the preset reaction time, it means that the user's attention is relatively scattered, and it is possible to be drunk driving. In order to ensure driving safety, the target vehicle can be prohibited from responding to the driving operation of the user. When the actual reaction time is less than the preset reaction time, it means that the user's attention is relatively concentrated, but it does not mean that the user has not drunk driving. At this time, step S25 can be executed to further judge whether the user has the possibility of drunk driving. Steps S25 and S26 are similar to steps S14-S15, and details can be referred to the related content of steps S14-S15, which will not be repeated here.

[0128] It can be seen that the embodiment combines the reaction speed of the user to the facial motion prompt signal and the matching degree of the actual facial motion and the target facial motion to determine the possibility of drunk driving of the user, which can further improve the judgment accuracy of whether the user drives drunk, can strengthen the constraint on the drunk driving behavior of the user, further reduce the probability of drunk driving behavior, and improve the driving safety. It should be noted that when the user has a dining action during the driving of the target vehicle and generates a retest prompt signal, the actual reaction time of the user is not counted, because the user cannot complete the retest facial motion during driving and needs to park on the side to complete it. If the time of parking on the side is also included in the actual reaction time, it will lead to misjudgment of the retest result. In order to avoid misjudgment of drunk driving in the retest process, steps S24 and S25 are not executed.

[0129] In addition, based on steps S11-S15, the embodiment further provides a vehicle control method, including steps S31-S36.

[0130] Step S31, detecting whether the user has a driving intention for the target vehicle;

[0131] Step S32, when it is detected that the user has a driving intention for the target vehicle, generating a facial motion prompt signal, the facial motion prompt signal including a target facial motion required to be executed by the user;

[0132] Step S33, collecting a facial image set of the user;

[0133] Step S34, determining an actual shaking frequency of the face of the user according to the facial image set;

[0134] Step S35, determining an actual matching degree of the actual facial motion of the user and the target facial motion according to the facial image set;

[0135] Step S36, determining whether the target vehicle responds to the driving operation of the user according to the actual matching degree, a preset matching degree, and the actual shaking frequency and a preset shaking frequency.

[0136] Steps S31-S33 are similar to steps S11-S13, and specific reference can be made to the related contents of steps S11-S13, which will not be repeated here.

[0137] Regarding step S34, the face muscles of a person are more likely to shake and convulse after drinking, so the stability of the user's face can be analyzed through the facial image set to determine whether the user has the possibility of drunk driving. Specifically, the actual shaking frequency of the target point on the face can be determined according to the facial image set, and the actual shaking frequency of the target point on the face is taken as the actual shaking frequency of the face.

[0138] The target point can be any point on the face of the user. In general, in order to facilitate point recognition, a relatively special point on the face of the user can be selected, for example, a mole on the face of the user can be selected as a target point for monitoring, or a corner of the mouth or an eye corner on the face of the user can be monitored. The target point on the face of the user in the adjacent multiple images is determined according to the face image set, the displacement of the target point is determined based on the adjacent multiple images, and the actual jitter frequency of the target point can be determined in combination with the displacement and the shooting time of the adjacent multiple images.

[0139] A preset jitter frequency is set. The preset jitter frequency can be determined according to the jitter frequency of different drivers in a non-drunk state. When the actual jitter frequency is greater than the preset jitter frequency, it means that the face jitter frequency of the user is high, the face stability is poor, and the possibility of drunk driving is high. In order to ensure driving safety, the target vehicle can be prohibited from responding to the driving operation of the user. When the actual jitter frequency is less than the preset jitter frequency, it means that the face jitter frequency of the user is normal, the face stability is good, and the possibility of drunk driving is low.

[0140] Steps S34 and S35 can be executed simultaneously or in any order, and the embodiment does not limit the order. Step S35 is similar to step S14, and details can be referred to the related content of step S14, which will not be repeated here.

[0141] Regarding step S36, the target vehicle can be determined whether to respond to the driving operation of the user according to the comparison result of the actual matching degree and the preset matching degree and the comparison result of the actual jitter frequency and the preset jitter frequency. When the actual matching degree is greater than the preset matching degree or the actual jitter frequency is greater than the preset jitter frequency, it means that the possibility of drunk driving of the user is high, and the target vehicle can be prohibited from responding to the driving operation of the user, thereby reducing the probability of drunk driving of the user and improving the driving safety. When the actual matching degree is less than the preset matching degree and the actual jitter frequency is less than the preset jitter frequency, it means that the possibility of drunk driving of the user is low, and the target vehicle can respond to the driving operation of the user.

[0142] It can be seen that, by combining the jitter characteristics of the face of the user and the matching degree of the actual face action and the target face action, the possibility of drunk driving of the user can be determined, the judgment accuracy of whether the user is drunk driving can be further improved, the drunk driving behavior of the user can be further constrained, the probability of drunk driving behavior can be further reduced, and the driving safety can be improved.

[0143] Further, in actual operation, the reaction speed of the user's facial action prompt signal, the shaking characteristics of the user's face, and the matching degree between the actual facial action and the target facial action can be combined to determine the possibility of the user's drunk driving, which can further improve the accuracy of the judgment on whether the user has drunk driving behavior, can strengthen the constraint on the user's drunk driving behavior, further reduce the probability of drunk driving behavior, and improve driving safety.

[0144] Based on the same inventive concept, the embodiment provides a vehicle control device as shown in Figure 2 The device comprises:

[0145] The driving intention detection module 21 is configured to detect whether the user has a driving intention for the target vehicle.

[0146] The signal generation module 22 is configured to generate a facial action prompt signal when it is detected that the user has a driving intention for the target vehicle, wherein the facial action prompt signal comprises a target facial action that needs to be performed by the user.

[0147] The image acquisition module 23 is configured to acquire a facial image set of the user.

[0148] The matching degree determination module 24 is configured to determine an actual matching degree between the actual facial action of the user and the target facial action according to the facial image set.

[0149] The driving judgment module 25 is configured to determine whether the target vehicle responds to the driving operation of the user according to the actual matching degree and a preset matching degree.

[0150] Further, the matching degree determination module 24 comprises:

[0151] The reaction time determination submodule is configured to determine an actual reaction time of the user in response to the facial action prompt signal according to the facial image set.

[0152] The matching degree determination submodule is configured to determine an actual matching degree between the actual facial action of the user and the target facial action according to the facial image set when the actual reaction time is less than a preset reaction time.

[0153] Further, the device further comprises:

[0154] The shaking frequency determination module is configured to determine an actual shaking frequency of the face of the user according to the facial image set after the facial image set of the user is acquired.

[0155] The driving judgment module 25 is configured to determine whether the target vehicle responds to the driving operation of the user according to the actual matching degree, the preset matching degree, and the actual shaking frequency and a preset shaking frequency.

[0156] Further, the device further comprises:

[0157] The action updating module is configured to update the target facial action included in the facial action prompting signal and reacquire the facial image set of the user when it is determined that the target vehicle prohibits responding to the driving operation of the user.

[0158] The driving judgment module 25 is configured to determine whether the target vehicle responds to the driving operation of the user according to the reacquired facial image set of the user.

[0159] Further, the device further comprises:

[0160] The action monitoring module is configured to monitor whether the user has the eating action after it is determined that the target vehicle responds to the driving operation of the user.

[0161] The signal generating module 22 is configured to generate a retest prompting signal including a retest facial action required to be performed by the user after it is determined that the user has the eating action.

[0162] The image acquiring module 23 is configured to acquire a retest image set of the user.

[0163] The driving judgment module 25 is configured to determine whether the target vehicle continues to respond to the driving operation of the user according to the retest image set.

[0164] Further, the driving intention detection module 21 is configured to:

[0165] acquire a seat signal and a safety belt signal of a driving seat of the target vehicle and an ignition signal of the target vehicle;

[0166] determine whether the user has the driving intention to the target vehicle according to the seat signal, the safety belt signal and the ignition signal.

[0167] Further, the target facial action includes at least one of an eye action, a mouth action and an expression action.

[0168] Based on the same inventive concept, the embodiment provides an electronic device as shown in Figure 3 The electronic device comprises:

[0169] a processor 31;

[0170] a memory 32 for storing instructions executable by the processor 31;

[0171] The processor 31 is configured to execute to implement the vehicle control method as provided in the foregoing.

[0172] Based on the same inventive concept, the embodiment provides a non-transitory computer readable storage medium, when instructions in the storage medium are executed by the processor 31 of the electronic device, the electronic device can execute to implement the vehicle control method as provided in the foregoing.

[0173] Since the electronic device introduced in the embodiment is the electronic device used for implementing the method for processing information in the embodiment of the present application, based on the method for processing information introduced in the embodiment of the present application, those skilled in the art can understand the specific implementation of the electronic device of the embodiment and various changes thereof, so how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the electronic device used for implementing the method for processing information in the embodiment of the present application is implemented by those skilled in the art, it belongs to the scope of the present application.

[0174] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media containing computer usable program code (including but not limited to disk memory, CD-ROM, optical memory, etc.).

[0175] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the 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 produce a device that implements the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that carries out the function specified in one or more blocks.

[0176] These computer program instructions can also be stored in a computer readable memory capable of directing the computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer readable memory produce a product including instruction apparatus, which implements the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that carries out the function specified in one or more blocks.

[0177] These computer program instructions can also be loaded into a computer or other programmable data processing device, so that a series of operation steps are performed on the computer or other programmable device to produce a computer implemented process, so that the instructions executed on the computer or other programmable device provide a means for implementing the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1steps of the functions specified in the block or blocks.

[0178] While the preferred embodiments of the application have been described, additional variations and modifications can be made to the preferred embodiments by those of skill in the art once they have the benefit of the present disclosure. Therefore, the appended claims are intended to encompass within their scope all possible variations and modifications of the preferred embodiments.

[0179] It is apparent that those skilled in the art can, without departing from the spirit and scope of the application, make various changes and modifications of the application. Thus, it is intended that the present application cover all modifications and variations of this application provided they come within the scope of the appended claims and their equivalents.

Claims

1. A vehicle control method, characterized in that, The method includes: Detect whether the user has the intention to drive the target vehicle; When the system detects that the user has the intention to drive the target vehicle, a facial action prompt signal is generated. The facial action prompt signal includes a target facial action that the user needs to perform. The target facial action includes at least one of eye movements, mouth movements, and facial expressions. Eye movements include blinking, closing eyes, looking left, looking right, looking up, and looking down. Mouth movements include opening the mouth, closing the mouth, and sticking out the tongue. Facial expressions refer to a combination of all facial movements, including smiling, crying, and surprised expressions. Collect the user's facial image set; The actual matching degree between the user's actual facial movements and the target facial movements is determined based on the facial image set. Based on the actual matching degree and the preset matching degree, it is determined whether the target vehicle responds to the user's driving operation.

2. The method as described in claim 1, characterized in that, Determining the actual matching degree between the user's actual facial movements and the target facial movements based on the facial image set includes: The actual reaction time of the user in response to the facial action prompt signal is determined based on the facial image set; When the actual reaction time is less than the preset reaction time, the actual matching degree between the user's actual facial movements and the target facial movements is determined based on the facial image set.

3. The method as described in claim 1, characterized in that, After acquiring the user's facial image set, the method further includes: The actual shaking frequency of the user's face is determined based on the set of facial images; The step of determining whether the target vehicle responds to the user's driving operation based on the actual matching degree and the preset matching degree includes: Based on the actual matching degree, the preset matching degree, the actual shaking frequency, and the preset trembling frequency, it is determined whether the target vehicle responds to the user's driving operation.

4. The method as described in claim 1, characterized in that, When it is determined that the target vehicle is prohibited from responding to the user's driving operations, the method further includes: Update the target facial movements included in the facial movement cue signal, and re-acquire the user's facial image set; Whether the target vehicle responds to the user's driving operation is determined based on the re-acquired set of facial images of the user.

5. The method as described in claim 1, characterized in that, After determining that the target vehicle is responding to the user's driving operation, the method further includes: Monitor whether the user is eating or drinking; After determining that the user has made a eating motion, a retest prompt signal is generated, which includes the facial motion that the user needs to perform for the retest. Collect the user's retest image set; The determination of whether the target vehicle continues to respond to the user's driving operations is based on the retest image set.

6. The method as described in claim 1, characterized in that, The detection of whether a user intends to drive the target vehicle includes: Acquire the driver's seat occupancy signal and seat belt signal of the target vehicle, as well as the ignition signal of the target vehicle; Based on the passenger signal, the seatbelt signal, and the ignition signal, determine whether the user has the intention to drive the target vehicle.

7. A vehicle control device, characterized in that, The device includes: The driving intent detection module is used to detect whether the user has a driving intent towards the target vehicle; The signal generation module is used to generate a facial action prompt signal when it detects that the user has a driving intention towards the target vehicle. The facial action prompt signal includes a target facial action that the user needs to perform. The target facial action includes at least one of eye movements, mouth movements, and facial expressions. Eye movements include blinking, closing eyes, looking left, looking right, looking up, and looking down. Mouth movements include opening the mouth, closing the mouth, and sticking out the tongue. Facial expressions refer to a combination of all facial movements, including smiling, crying, and surprised expressions. The image acquisition module is used to acquire a set of facial images of the user; A matching degree determination module is used to determine the actual matching degree between the user's actual facial movements and the target facial movements based on the facial image set; The driving judgment module is used to determine whether the target vehicle responds to the user's driving operation based on the actual matching degree and the preset matching degree.

8. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute a vehicle control method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform a vehicle control method as described in any one of claims 1 to 6.

Images