Driving reminder method, device, computer equipment, storage medium and program product

Abstract

The present invention relates to the technical field of road safety early warning, and discloses a driving prompt method, device, computer equipment, storage medium and program product, wherein the method comprises: performing image recognition on a target scene in the driving environment of a target vehicle to obtain scene information, wherein the target scene is used to indicate a tunnel entrance and exit scene, and the scene information is used to indicate the scene characteristics of the target scene; based on the scene information, calculating the distance data between the target vehicle and the target scene; performing risk assessment based on the operating state parameters and distance data of the target vehicle to obtain a risk level, wherein the risk level is used to indicate the risk of collision between the target vehicle and the target scene; controlling the target vehicle according to the control information corresponding to the risk level to warn the driving object. The present invention warns the driving object in advance in the scenario where the target vehicle enters and exits the tunnel, reducing the probability of traffic accidents caused by the driving object's lack of concentration.

Description

Technical Field

[0001] The present invention relates to the technical field of road safety warning, and in particular to a driving warning method, device, computer equipment, storage medium and program product. Background Art

[0002] As the transportation network becomes increasingly rich, there are many tunnels in both urban and high-speed transportation networks. The driving safety issue in and out of tunnels is becoming more and more prominent. When entering and exiting tunnels, the drastic changes in light require some time for drivers to adapt, and this period of time is when accidents are most likely to occur, and once an accident occurs, it is a major accident involving multiple vehicles colliding.

[0003] However, in this scenario, most of the related driving reminder solutions use warning signs outside the tunnel, lights, ground road signs or some third-party navigation software to remind drivers to drive carefully through voice. However, for drivers who know the way, they often habitually ignore the reminders or even use navigation prompts. For novice drivers, they only pay attention to the situation inside the car and have no more energy to pay attention to external control information, which increases the probability of accidents to a certain extent. Summary of the invention

[0004] In view of this, the present invention provides a driving reminder method, device, computer equipment, storage medium and program product to solve the problem of high probability of accidents when entering and exiting tunnels.

[0005] In a first aspect, the present invention provides a driving prompt method, the method comprising:

[0006] Performing image recognition on a target scene in the driving environment of the target vehicle to obtain scene information, wherein the target scene is used to indicate a tunnel entrance and exit scene, and the scene information is used to indicate scene features of the target scene;

[0007] Based on the scene information, calculating the distance data between the target vehicle and the target scene;

[0008] Performing a risk assessment based on the operating state parameters of the target vehicle and the distance data to obtain a risk level, wherein the risk level is used to indicate the risk of the target vehicle colliding with the target scene;

[0009] The target vehicle is controlled according to control information corresponding to the risk level to warn the driving object.

[0010] In an embodiment of the present invention, firstly, image recognition is performed on the target scene in the driving environment of the target vehicle to obtain scene information, wherein the target scene is used to indicate the tunnel entrance and exit scene, and the scene information is used to indicate the scene characteristics of the target scene. Then, based on the scene information, the distance data between the target vehicle and the target scene can be calculated, and a risk assessment can be performed based on the operating state parameters of the target vehicle and the distance data to obtain a risk level, wherein the risk level is used to indicate the risk of collision of the target vehicle in the target scene. Next, the target vehicle can be controlled according to the control information corresponding to the risk level to warn the driving object, thereby giving the driving object an early warning in the scene where the target vehicle enters and exits the tunnel, thereby reducing the probability of traffic accidents caused by the driving object's inattention.

[0011] In an optional implementation, the operating status parameters include: real-time speed, acceleration;

[0012] The risk assessment is performed based on the operating state parameters of the target vehicle and the distance data to obtain a risk level, including:

[0013] Calculating the travel time of the target vehicle to the target scene based on the real-time speed, acceleration and distance data;

[0014] Based on preset association information, a risk level matching the travel time is acquired, wherein the preset association information is used to indicate an association relationship between the travel time and the risk level.

[0015] In an embodiment of the present invention, the driving time required for the target vehicle to reach the tunnel entrance and exit can be calculated, and the corresponding risk level can be determined based on the driving time, so as to provide multi-level warnings to the driving object based on the risk level to improve the effect of reminding the driving object to concentrate.

[0016] In an optional embodiment, the method further includes:

[0017] After the configuration instruction is detected, the preset association information is established based on the association relationship between the travel time indicated by the configuration instruction and the risk level.

[0018] In an embodiment of the present invention, the driving time required for the target vehicle to reach the tunnel entrance and exit can be calculated, and the corresponding risk level can be determined based on the driving time, so as to provide multi-level warnings to the driving object based on the risk level to improve the effect of reminding the driving object to concentrate.

[0019] In an optional implementation, the operating state parameters include: angular velocity, steering wheel angle;

[0020] The step of performing risk assessment based on the operating state parameter of the target vehicle and the distance data to obtain a risk level further includes:

[0021] Acquiring the angular velocity based on an angular velocity sensor, and acquiring the steering wheel angle based on a steering wheel angle sensor;

[0022] Based on the pedal sensor, obtaining pedal control data, wherein the pedal control data is used to indicate control data of an accelerator pedal and / or a brake pedal of the target vehicle;

[0023] When the angular velocity, the steering wheel angle and the pedal control data are unchanged, a risk assessment is performed based on the distance data to obtain a risk level.

[0024] In the embodiment of the present invention, it should be understood that when the above-mentioned angular velocity, steering wheel angle and pedal control data have not changed, it means that the driving subject has not controlled the driving state of the target vehicle and may be inattentive. At this time, since the above-mentioned target network model has detected the tunnel entrance and exit, a risk assessment can be performed based on the distance data between the target vehicle and the tunnel entrance and exit, so as to timely remind the driving subject and ensure driving safety.

[0025] In an optional embodiment, the method further includes:

[0026] Respectively detecting the angular velocity, the steering wheel angle and the pedal control data for change data when updating;

[0027] When any of the changed data exceeds the corresponding change threshold, the risk level is cleared.

[0028] In an embodiment of the present invention, it is possible to determine whether the driving subject has controlled the vehicle by detecting the change data when the angular velocity, steering wheel angle and pedal control data are updated, thereby determining whether the driving subject has left the distracted state, and when the driving subject leaves the distracted state, the risk level is cleared to cancel the warning.

[0029] In an optional implementation, performing risk assessment based on the distance data to obtain a risk level includes:

[0030] Obtaining the real-time speed and acceleration of the target vehicle;

[0031] Calculating a target speed when the target vehicle reaches the target scene based on the distance data, real-time speed and acceleration;

[0032] A risk assessment is performed based on the target speed to obtain a risk level.

[0033] In the embodiment of the present invention, it should be understood that when the above-mentioned angular velocity, steering wheel angle and pedal control data have not changed, it means that the driving subject has not controlled the driving state of the target vehicle and may be inattentive. At this time, since the above-mentioned target network model has detected the tunnel entrance and exit, a risk assessment can be performed based on the distance data between the target vehicle and the tunnel entrance and exit, so as to timely remind the driving subject and ensure driving safety.

[0034] In an optional implementation, performing image recognition on a target scene in a driving environment of a target vehicle to obtain scene information includes:

[0035] Based on a camera device, collecting image frames of the driving environment;

[0036] Based on the target network model, identifying the tunnel entrance and exit features and / or tunnel marking features in the image frame to obtain a recognition result;

[0037] The scene information is determined according to the recognition result.

[0038] In an embodiment of the present invention, tunnel entrance and exit features and / or tunnel marking features in the image frame of the driving environment can be identified through the target network model to obtain an identification result, thereby actively reminding the driver that he is about to reach the tunnel entrance and exit when the navigation software is not updated in time or the signal in the tunnel exit scene is poor and the driver cannot be reminded in time.

[0039] In an optional implementation, the scene information includes: scene features of a tunnel exit;

[0040] The method further comprises:

[0041] After obtaining the scene information, obtaining the cumulative time of the target vehicle entering the tunnel;

[0042] Based on the accumulated time, a confidence level of the identified scene feature is determined.

[0043] In an embodiment of the present invention, in a tunnel exit scenario, the recognition result of the scene features including the tunnel exit output by the target network model can be confidence verified according to the accumulated time of the target vehicle entering the tunnel, thereby reducing the probability of false triggering of the active reminder operation.

[0044] In an optional implementation, the control information includes: seat belt control information, buzzer control information, brake pedal control information;

[0045] The method further comprises:

[0046] Preset at least one risk level;

[0047] Corresponding target information is set for each risk level, wherein the target information includes at least one kind of control information.

[0048] In the embodiment of the present invention, corresponding target information can be set for each risk level, so that the target vehicle can be controlled by using multiple control methods to better warn the driving object and ensure driving safety.

[0049] In a second aspect, the present invention provides a driving reminder device, the device comprising:

[0050] A recognition module, used for performing image recognition on a target scene in the driving environment of the target vehicle to obtain scene information, wherein the target scene is used to indicate a tunnel entrance and exit scene, and the scene information is used to indicate scene features of the target scene;

[0051] A calculation module, used for calculating the distance data between the target vehicle and the target scene based on the scene information;

[0052] An assessment module, configured to perform risk assessment based on the operating state parameters of the target vehicle and the distance data to obtain a risk level, wherein the risk level is used to indicate a collision risk between the target vehicle and the target scene;

[0053] The early warning module is used to warn the driver of the target vehicle according to the control information corresponding to the risk level.

[0054] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the driving prompt method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0055] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the driving prompt method of the first aspect or any corresponding embodiment thereof.

[0056] In a fifth aspect, the present invention provides a computer program product, including computer instructions, and the computer instructions are used to enable a computer to execute the driving prompt method of the above-mentioned first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 is a schematic flow chart of a driving prompt method according to an embodiment of the present invention;

[0059] Figure 2 is a flow chart of another driving prompt method according to an embodiment of the present invention;

[0060] Figure 3 is a flow chart of another driving prompt method according to an embodiment of the present invention;

[0061] Figure 4 is a schematic diagram of the architecture of a driving reminder system according to an embodiment of the present invention;

[0062] Figure 5 is a structural block diagram of a driving prompt device according to an embodiment of the present invention;

[0063] Figure 6 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0065] In conjunction with the application scenarios on which the execution of the driving prompt method depends, the application scenarios are described here.

[0066] As the transportation network becomes increasingly rich, there are many tunnels in both urban and high-speed transportation networks. The driving safety issue in and out of tunnels is becoming more and more prominent. When entering and exiting tunnels, the drastic changes in light require some time for drivers to adapt, and this period of time is when accidents are most likely to occur, and once an accident occurs, it is a major accident involving multiple vehicles colliding.

[0067] However, in this scenario, most of the related driving reminder solutions use warning signs outside the tunnel, lights, ground road signs or some third-party navigation software to remind drivers to drive carefully through voice. However, for drivers who know the way, they often habitually ignore the reminders or even use navigation prompts. For novice drivers, they only pay attention to the situation inside the car and have no more energy to pay attention to external control information, which increases the probability of accidents to a certain extent.

[0068] Specifically, the relevant driving reminder schemes are mainly divided into two parts. The first part includes ground signs, warning lights, and road signs added by local road administration or urban construction at the entrance of the tunnel. This type of scheme can only serve as a reminder for drivers who are paying attention. However, most drivers who have accidents are not paying enough attention. The probability of not noticing the control information is very high, and the cost of setting up and maintaining reminder equipment is very expensive. In the second part, third-party navigation software will give voice prompts before entering the tunnel. This scheme forces drivers to use navigation software, which is undoubtedly unnecessary for drivers who know the road.

[0069] However, in these related driving reminder solutions, drivers are required to actively obtain external control information or actively use third-party software to get reminders. In addition, the existing solutions only provide reminders for entering tunnels, while in the tunnel exit scenario, the control information is almost ineffective. At the same time, due to poor signals in tunnels, navigation software may not be updated in time, and safety depends entirely on the driver's driving behavior.

[0070] Based on this, an embodiment of the present invention provides a driving prompt method, which includes: first, performing image recognition on a target scene in the driving environment of a target vehicle to obtain scene information, wherein the target scene is used to indicate a tunnel entrance and exit scene, and the scene information is used to indicate the scene characteristics of the target scene. Then, based on the scene information, the distance data between the target vehicle and the target scene can be calculated, and a risk assessment can be performed based on the operating state parameters of the target vehicle and the distance data to obtain a risk level, wherein the risk level is used to indicate the risk of a collision of the target vehicle in the target scene. Next, the target vehicle can be controlled according to the control information corresponding to the risk level to warn the driving object, thereby giving an early warning to the driving object in the scenario where the target vehicle enters and exits the tunnel, thereby reducing the probability of traffic accidents caused by the driving object's inattention.

[0071] According to an embodiment of the present invention, an embodiment of a driving prompt method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0072] In this embodiment, a driving prompt method is provided, which can be used in a vehicle terminal. Figure 1 is a flow chart of a driving prompt method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0073] Step S101 , performing image recognition on a target scene in a driving environment of a target vehicle to obtain scene information, wherein the target scene is used to indicate a tunnel entrance and exit scene, and the scene information is used to indicate scene features of the target scene.

[0074] In an embodiment of the present invention, during the driving process of the target vehicle, a road condition image can be obtained in real time through a visual sensor installed in the target vehicle, and the road condition image can be recognized through a preset network model to recognize the tunnel entrance and exit scene contained in the road condition image. For example, the preset network model can be a convolutional neural network (CNN) and its improved architecture. It should be understood that the preset network model can also adopt other types of neural networks. The selection of the neural network is based on the ability to realize the recognition of the tunnel entrance and exit scene contained in the road condition image, and the present invention does not specifically limit this.

[0075] After the preset network model recognizes the target scene, scene information of the target scene can be obtained, for example, a target road condition image containing the target scene collected by the above-mentioned visual sensor is obtained.

[0076] Step S102, based on the scene information, calculate the distance data between the target vehicle and the target scene.

[0077] In an embodiment of the present invention, after the preset network model recognizes the target scene, it can estimate the distance value between the target vehicle and the target scene based on the scene information to obtain the distance data. For example, the distance value is estimated through the target road condition image using stereo vision technology.

[0078] Specifically, when the above-mentioned target road condition image includes multiple frames of continuous image frames, the feature points of the target scene, such as corner points, edges, etc., can be identified and tracked. By comparing the position changes of these feature points in continuous image frames, combined with the motion parameters of the visual sensor and the size information of the target scene, the distance value between the target scene and the vehicle can be estimated.

[0079] It should be understood that the distance data between the target vehicle and the target scene can also be determined by other means, for example, by using a lidar to determine the distance value between the tunnel entrance and exit and the target vehicle. The present invention does not limit the method for determining the distance data, which is subject to what can be implemented.

[0080] Step S103, performing risk assessment based on the operating state parameters and distance data of the target vehicle to obtain a risk level, wherein the risk level is used to indicate the risk of collision of the target vehicle in the target scene.

[0081] In an embodiment of the present invention, it is possible to determine whether the driver is inattentive by monitoring whether the operating state parameter has changed. Here, if the operating state parameter has not changed, the closer the distance between the target vehicle and the target scene, the higher the collision risk level.

[0082] For example, the risk level is divided into three levels. When the distance between the target vehicle and the target scene is detected to be 100 meters, there is a collision risk, and the risk level at this time is determined to be the first risk level. When the distance between the target vehicle and the target scene is detected to be 50 meters, the risk level can be increased to the second risk level. When the distance between the target vehicle and the target scene is detected to be 20 meters, the risk level can be increased to the third risk level.

[0083] Here, considering that the target scene is a tunnel entrance and exit, it can be preset that there are obstacles at the location of the tunnel entrance and exit, so as to calculate the risk level according to the preset obstacles.

[0084] Step S104, controlling the target vehicle according to the control information corresponding to the risk level to warn the driving object.

[0085] In the embodiment of the present invention, corresponding warning modes may be pre-set for different risk levels, and control information for controlling the target vehicle may be generated for the warning mode to control the target vehicle to arouse the attention of the driving subject.

[0086] For example, the warning method may include: vehicle brake jitter, seat belt clamping, sound and light alarm, etc., wherein each warning method may include control strategies corresponding to multiple risk levels. Specifically, vehicle brake jitter may apply a 5km / h braking deceleration to the vehicle within 200ms, and remind the driver to pay attention to safe driving through a strong physical reaction, while not affecting the rear vehicle to ensure driving safety. Seat belt clamping can control the tightening of the seat belt on the driver's seat, and achieve multi-level risk level warning by changing the clamping frequency. Sound and light alarms can provide display alarms through the central control instrument lights, and achieve multi-level risk level warnings by changing the buzzer frequency and light color.

[0087] It should be understood that the user can customize the control information corresponding to different risk levels according to their own needs, wherein one or more control information corresponding to each risk level can be set, and the control parameters in the control information can be customized.

[0088] For example, if there are three risk levels, the first level corresponding to the warning method can be seat belt tightening, the second level corresponding to the police can be sound and light alarm, and the third level corresponding to the warning method can be vehicle brake vibration. Here, users can customize the frequency of seat belt tightening, the light color of the sound and light alarm, and the buzzer frequency.

[0089] It can be seen from the above description that in an embodiment of the present invention, firstly, image recognition is performed on the target scene in the driving environment of the target vehicle to obtain scene information, wherein the target scene is used to indicate the tunnel entrance and exit scene, and the scene information is used to indicate the scene characteristics of the target scene. Then, based on the scene information, the distance data between the target vehicle and the target scene can be calculated, and a risk assessment can be performed based on the operating state parameters of the target vehicle and the distance data to obtain a risk level, wherein the risk level is used to indicate the risk of collision of the target vehicle in the target scene. Next, the target vehicle can be controlled according to the control information corresponding to the risk level to warn the driving object, thereby giving an early warning to the driving object in the scene where the target vehicle enters and exits the tunnel, reducing the probability of traffic accidents caused by the driving object's inattention.

[0090] In this embodiment, another driving prompt method is provided, which can be used in a vehicle terminal. Figure 2 is a flow chart of another driving prompt method according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0091] Step S201, performing image recognition on a target scene in the driving environment of a target vehicle to obtain scene information, wherein the target scene is used to indicate a tunnel entrance and exit scene, and the scene information is used to indicate scene features of the target scene.

[0092] Specifically, the above step S201 includes:

[0093] Step S2011: collecting image frames of the driving environment based on the camera device.

[0094] Step S2012: Based on the target network model, identify the tunnel entrance and exit features and / or tunnel marking features in the image frame to obtain a recognition result.

[0095] Step S2013, determining scene information according to the recognition result.

[0096] In an embodiment of the present invention, the above-mentioned tunnel entrance and exit features may include tunnel doorway features, and tunnel marking features may include ground road marking features, signboard marking features, light marking features, etc., which are used to indicate the entry and exit of the tunnel.

[0097] After determining that any of the above features are recognized, the target network model can output the feature to obtain a recognition result. Here, the confidence of the recognition result can be determined according to the number of features included in the recognition result, and the image frame corresponding to the recognition result whose confidence meets the confidence condition is used to determine the scene information. For example, the more features and feature types included in the recognition result, the higher the confidence of the recognition result.

[0098] Step S202: Calculate the distance data between the target vehicle and the target scene based on the scene information. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0099] Step S203, perform risk assessment based on the target vehicle's operating state parameters and distance data to obtain a risk level, wherein the risk level is used to indicate the risk of the target vehicle colliding with the target scene. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0100] Step S204: Control the target vehicle according to the control information corresponding to the risk level to warn the driver. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0101] In an embodiment of the present invention, tunnel entrance and exit features and / or tunnel marking features in the image frame of the driving environment can be identified through the target network model to obtain an identification result, thereby actively reminding the driver that he is about to reach the tunnel entrance and exit when the navigation software is not updated in time or the signal in the tunnel exit scene is poor and the driver cannot be reminded in time.

[0102] In some optional implementations, the scene information includes: scene features of the tunnel exit, the Figure 1 The corresponding embodiments also include:

[0103] Step S11, after obtaining the scene information, obtain the cumulative time of the target vehicle entering the tunnel.

[0104] Step S12, determining the confidence level of the recognized scene features based on the accumulated time.

[0105] In an embodiment of the present invention, in a tunnel exit scenario, the recognition result of the target network model can be verified for confidence based on the cumulative time of the target vehicle entering the tunnel. Specifically, the timing can be started from the time when the target vehicle is detected to enter the tunnel, and the driving distance of the target vehicle in the tunnel can be calculated based on the cumulative time, so as to verify the confidence of the recognition result based on the driving distance.

[0106] Here, the actual length of the tunnel can be obtained according to the navigation software before entering the tunnel, and the driving distance of the target vehicle in the tunnel can be calculated in real time according to the accumulated time, and after the target network model outputs the recognition result, the confidence of the recognition result can be verified according to the comparison result between the driving distance and the actual length. It should be understood that the closer the driving distance is to the actual length, the higher the confidence of the recognition result.

[0107] In an embodiment of the present invention, in a tunnel exit scenario, the recognition result of the scene features including the tunnel exit output by the target network model can be confidence verified according to the accumulated time of the target vehicle entering the tunnel, thereby reducing the probability of false triggering of the active reminder operation.

[0108] In this embodiment, another driving prompt method is provided, which can be used in a vehicle terminal. Figure 3 is a flow chart of another driving prompt method according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0109] Step S301, perform image recognition on a target scene in the driving environment of the target vehicle to obtain scene information, wherein the target scene is used to indicate the tunnel entrance and exit scene, and the scene information is used to indicate the scene features of the target scene. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0110] Step S302: Calculate the distance data between the target vehicle and the target scene based on the scene information. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0111] Step S303, performing risk assessment based on the running state parameters and distance data of the target vehicle to obtain a risk level, wherein the risk level is used to indicate the risk of collision between the target vehicle and the target scene.

[0112] Specifically, the above-mentioned running state parameters include: real-time speed and acceleration. The above-mentioned step S303 includes:

[0113] Step S3031, based on the real-time speed, acceleration and distance data, calculate the travel time for the target vehicle to reach the target scene.

[0114] Step S3032: based on preset association information, obtain the risk level that matches the travel time, wherein the preset association information is used to indicate the association relationship between the travel time and the risk level.

[0115] In the embodiment of the present invention, the real-time speed of the target vehicle can be obtained in real time through the speed sensor installed in the target vehicle. The acceleration sensor detects the acceleration of the target vehicle in real time. , and obtain the calculated distance data above Then, the kinematic formula , calculate the travel time of the target vehicle to the target scene .

[0116] Next, you can find the travel time based on the preset association information Corresponding risk level, in the preset associated information, driving time Inversely proportional to the risk level, i.e., travel time The shorter the time, the higher the risk level. For example, when the risk level is divided into three levels, When , it can correspond to the first risk level, When the , it can correspond to the third risk level.

[0117] It should be understood that the user can customize the above preset association information according to their own usage requirements, which specifically includes the following process:

[0118] After the configuration instruction is detected, preset association information is established based on the association relationship between the travel time indicated by the configuration instruction and the risk level.

[0119] In the embodiment of the present invention, the configuration instructions may configure the following contents: the total number of risk levels, and the correlation between each risk level and the travel time.

[0120] Specifically, when configuring the total number of risk levels through configuration instructions, the user can instruct to increase or decrease the total number of risk levels through configuration instructions. For example, when the total number of risk levels is three, it can be instructed to increase the number of levels within the maximum total number (five levels), or to instruct to reduce the total number to the minimum total number (one level).

[0121] In addition, when configuring the association between each risk level and the driving time through configuration instructions, the user can instruct to increase or decrease the driving time corresponding to each risk level through configuration instructions. For example, when configuring the driving time corresponding to the first risk level, the driving time can be increased to the maximum driving time corresponding to the first level (15s), or the driving time can be reduced to the shortest driving time corresponding to the first level (5s).

[0122] Step S304: Control the target vehicle according to the control information corresponding to the risk level to warn the driver. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0123] In an embodiment of the present invention, the driving time required for the target vehicle to reach the tunnel entrance and exit can be calculated, and the corresponding risk level can be determined based on the driving time, so as to provide multi-level warnings to the driving object based on the risk level to improve the effect of reminding the driving object to concentrate.

[0124] In some optional implementations, the operating state parameters include: angular velocity, steering wheel angle, and the step S103 further includes:

[0125] Step S21, obtaining an angular velocity based on an angular velocity sensor, and obtaining a steering wheel angle based on a steering wheel angle sensor.

[0126] Step S22: acquiring pedal control data based on the pedal sensor, wherein the pedal control data is used to indicate control data of an accelerator pedal and / or a brake pedal of the target vehicle.

[0127] Step S23, when the angular velocity, steering wheel angle and pedal control data have not changed, risk assessment is performed based on the distance data to obtain a risk level.

[0128] In an embodiment of the present invention, the above-mentioned vehicle sensors may also include the above-mentioned angular velocity sensor and the first-level pedal sensor to respectively obtain the angular velocity of the target vehicle during driving, the steering wheel angle, and the control data of the driving object when controlling the accelerator pedal and / or brake pedal in real time.

[0129] It should be understood that when the above angular velocity, steering wheel angle and pedal control data do not change, it means that the driver does not control the driving state of the target vehicle and may be distracted. At this time, since the above target network model has detected the tunnel entrance and exit, it can be based on the distance data S, the above real-time speed And acceleration Conduct a risk assessment to obtain a risk level.

[0130] In some optional implementations, the above step S23 includes:

[0131] Step a1, obtaining the real-time speed and acceleration of the target vehicle.

[0132] Step a2, based on the distance data, real-time speed and acceleration, calculate the target speed when the target vehicle reaches the target scene.

[0133] Step a3: perform risk assessment based on the target speed to obtain a risk level.

[0134] In the embodiment of the present invention, when performing risk assessment, the kinematic formula Calculate the arrival speed of the target vehicle when it arrives at the target scene , and assume that there are virtual obstacles in the target scene to A collision risk calculation is performed to obtain a risk level.

[0135] Specifically, after calculating the above arrival speed After that, we can get the arrival speed The associated risk level, or the collision risk is calculated in real time, that is, the acceleration of the target vehicle when colliding with the above virtual obstacle is calculated to obtain a risk level matching the acceleration.

[0136] In the embodiment of the present invention, it should be understood that when the above-mentioned angular velocity, steering wheel angle and pedal control data have not changed, it means that the driving subject has not controlled the driving state of the target vehicle and may be inattentive. At this time, since the above-mentioned target network model has detected the tunnel entrance and exit, a risk assessment can be performed based on the distance data between the target vehicle and the tunnel entrance and exit, so as to timely remind the driving subject and ensure driving safety.

[0137] In some optional implementations, the above step S103 further includes:

[0138] Step S31, respectively detecting the angular velocity, the steering wheel angle and the pedal control data to update the change data.

[0139] Step S32: when any changed data exceeds the corresponding change threshold, the risk level is cleared.

[0140] In an embodiment of the present invention, after detecting that the driving subject controls the target vehicle, it can be considered that the driving subject is not in a distracted state, so the risk level can be reset to zero, thereby canceling the warning. Here, whether the driving subject controls the target vehicle can be determined by the angular velocity, steering wheel angle and pedal control data of the target vehicle.

[0141] In specific implementation, corresponding change thresholds can be set for the above angular velocity, steering wheel angle and pedal control data, respectively. When any change data is detected to exceed the corresponding change threshold, it can be determined that the driver is not in a distracted state. For example, if the change thresholds of the steering wheel angle and angular velocity of the target vehicle are detected to exceed their respective change thresholds at the same time, the risk level is cleared.

[0142] In an embodiment of the present invention, it is possible to determine whether the driving subject has controlled the vehicle by detecting the change data when the angular velocity, steering wheel angle and pedal control data are updated, thereby determining whether the driving subject has left the distracted state, and when the driving subject leaves the distracted state, the risk level is cleared to cancel the warning.

[0143] In some optional implementations, the control information includes: seat belt control information, buzzer control information, brake pedal control information, the above Figure 1 The corresponding embodiments also include:

[0144] Step S41, presetting at least one risk level.

[0145] Step S42, setting corresponding target information for each risk level, wherein the target information includes at least one kind of control information.

[0146] In the embodiment of the present invention, corresponding warning modes are set in advance for different risk levels, and control information for controlling the target vehicle is generated for the warning mode to control the target vehicle to arouse the attention of the driving object.

[0147] For example, the warning method may include: vehicle brake vibration, seat belt clamping, sound and light alarm, etc., wherein the control information corresponding to vehicle brake vibration may be brake pedal control information, the control information corresponding to seat belt clamping may be seat belt control information, and the control information corresponding to sound and light alarm may be buzzer control information. Figure 1 The corresponding embodiments are described and will not be repeated here.

[0148] It should be understood that the user can customize the control information corresponding to different risk levels according to their own needs, wherein one or more corresponding target information can be set for each risk level, and the control parameters in the target information can be customized.

[0149] For example, if there are three risk levels, the first level corresponding to the warning method can be seat belt tightening, the second level corresponding to the police can be sound and light alarm, and the third level corresponding to the warning method can be vehicle brake vibration. Here, users can customize the frequency of seat belt tightening, the light color of the sound and light alarm, and the buzzer frequency.

[0150] In the embodiment of the present invention, corresponding target information can be set for each risk level, so that the target vehicle can be controlled by using multiple control methods to better warn the driving object and ensure driving safety.

[0151] In summary, in an embodiment of the present invention, first, image recognition can be performed on the target scene in the driving environment of the target vehicle to obtain scene information, wherein the target scene is used to indicate the tunnel entrance and exit scene, and the scene information is used to indicate the scene characteristics of the target scene. Then, based on the scene information, the distance data between the target vehicle and the target scene can be calculated, and a risk assessment can be performed based on the operating state parameters of the target vehicle and the distance data to obtain a risk level, wherein the risk level is used to indicate the risk of the target vehicle colliding in the target scene. Next, the target vehicle can be controlled according to the control information corresponding to the risk level to warn the driving object, thereby giving the driving object an early warning in the scenario where the target vehicle enters and exits the tunnel, thereby reducing the probability of traffic accidents caused by the driving object's inattention.

[0152] In this embodiment, a driving reminder system is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "unit" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0153] This embodiment provides a driving reminder system, such as Figure 4 The figure shows the architecture diagram of the driving warning system, including: a visual sensor, a vehicle sensor, a risk assessment unit, and a vehicle control unit, wherein the vehicle sensor includes the above-mentioned speed sensor, acceleration sensor, angular velocity sensor, pedal sensor, and steering wheel angle sensor.

[0154] The visual sensor is used to perform image recognition on the target scene in the driving environment of the target vehicle to obtain scene information.

[0155] The vehicle sensor is used to obtain the above-mentioned operating status parameters, wherein the operating status parameters include: real-time speed, acceleration, angular velocity pedal control data and steering wheel angle.

[0156] The risk assessment unit is used to perform risk assessment on the operating status parameters and distance data of the target vehicle, obtain the risk level, and acquire control information corresponding to the risk level.

[0157] The vehicle control unit is used to control the target vehicle according to the control information to warn the driving object.

[0158] In this embodiment, a driving reminder device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0159] This embodiment provides a driving reminder device, such as Figure 5 As shown, including:

[0160] The recognition module 501 is used to perform image recognition on a target scene in the driving environment of the target vehicle to obtain scene information, wherein the target scene is used to indicate a tunnel entrance and exit scene, and the scene information is used to indicate scene features of the target scene;

[0161] A calculation module 502 is used to calculate the distance data between the target vehicle and the target scene based on the scene information;

[0162] An assessment module 503, used to perform risk assessment based on the operating state parameters and distance data of the target vehicle to obtain a risk level, wherein the risk level is used to indicate the collision risk between the target vehicle and the target scene;

[0163] The warning module 504 is used to warn the driver of the target vehicle according to the control information corresponding to the risk level.

[0164] In some optional implementations, the operating state parameters include: real-time speed, acceleration; the evaluation module 503 is further used to:

[0165] Based on the target vehicle's operating status parameters and distance data, a risk assessment is performed to obtain the risk level, including:

[0166] Calculate the travel time of the target vehicle to the target scene based on real-time speed, acceleration and distance data;

[0167] Based on preset association information, a risk level matching the travel time is obtained, wherein the preset association information is used to indicate an association relationship between the travel time and the risk level.

[0168] In some optional implementations, the evaluation module 503 is further configured to:

[0169] After the configuration instruction is detected, preset association information is established based on the association relationship between the travel time indicated by the configuration instruction and the risk level.

[0170] In some optional implementations, the operating state parameters include: angular velocity, steering wheel angle; the evaluation module 503 is further used for:

[0171] Acquire an angular velocity based on an angular velocity sensor, and acquire a steering wheel angle based on a steering wheel angle sensor;

[0172] Acquiring pedal control data based on a pedal sensor, wherein the pedal control data is used to indicate control data of an accelerator pedal and / or a brake pedal of a target vehicle;

[0173] When the angular velocity, steering wheel angle and pedal control data have not changed, a risk assessment is performed based on the distance data to obtain a risk level.

[0174] In some optional implementations, the evaluation module 503 is further configured to:

[0175] Detect the change data when the angular velocity, steering wheel angle and pedal control data are updated respectively;

[0176] When any change data exceeds the corresponding change threshold, the risk level will be cleared.

[0177] In some optional implementations, the evaluation module 503 is further configured to:

[0178] Get the real-time speed and acceleration of the target vehicle;

[0179] Calculate the target speed of the target vehicle when it reaches the target scene based on distance data, real-time speed and acceleration;

[0180] A risk assessment is performed based on the target speed to obtain a risk level.

[0181] In some optional implementations, the identification module 501 is further configured to:

[0182] Based on the camera device, image frames of the driving environment are collected;

[0183] Based on the target network model, identifying the tunnel entrance and exit features and / or tunnel marking features in the image frame to obtain a recognition result;

[0184] The scene information is determined based on the recognition result.

[0185] In some optional implementations, the scene information includes: scene features of the tunnel exit; the above device is also used for:

[0186] After obtaining the scene information, the cumulative time of the target vehicle entering the tunnel is obtained;

[0187] Based on the accumulated time, the confidence of the recognized scene features is determined.

[0188] In some optional implementations, the control information includes: seat belt control information, buzzer control information, brake pedal control information; the above device is also used for:

[0189] Preset at least one risk level;

[0190] Corresponding target information is set for each risk level, wherein the target information includes at least one type of control information.

[0191] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0192] The driving reminder device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0193] The embodiment of the present invention also provides a computer device having the above Figure 5 The driving reminder device shown.

[0194] See also Figure 6 , Figure 6 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 6 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 10 is taken as an example.

[0195] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0196] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0197] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0198] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0199] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0200] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0201] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0202] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A driving reminder method, characterized in that: The method comprises: Performing image recognition on a target scene in the driving environment of the target vehicle to obtain scene information, wherein the target scene is used to indicate a tunnel entrance and exit scene, and the scene information is used to indicate scene features of the target scene; Based on the scene information, calculating the distance data between the target vehicle and the target scene; Performing a risk assessment based on the operating state parameters of the target vehicle and the distance data to obtain a risk level, wherein the risk level is used to indicate the risk of the target vehicle colliding with the target scene; Controlling the target vehicle according to the control information corresponding to the risk level to give an early warning to the driving object; Wherein, the operating state parameters include: angular velocity, steering wheel angle; the risk assessment based on the operating state parameters of the target vehicle and the distance data to obtain the risk level includes: Acquiring the angular velocity based on an angular velocity sensor, and acquiring the steering wheel angle based on a steering wheel angle sensor; Based on the pedal sensor, obtaining pedal control data, wherein the pedal control data is used to indicate control data of an accelerator pedal and / or a brake pedal of the target vehicle; When the angular velocity, the steering wheel angle and the pedal control data are unchanged, performing risk assessment based on the distance data to obtain a risk level; The risk assessment is performed based on the distance data to obtain the risk level, including: Obtaining the real-time speed and acceleration of the target vehicle; Calculating a target speed when the target vehicle reaches the target scene based on the distance data, real-time speed and acceleration; Perform risk assessment based on the target speed to obtain a risk level; Wherein, determining whether the driving subject is inattentive by monitoring whether the operating state parameter changes includes: Respectively detecting the angular velocity, the steering wheel angle and the pedal control data for change data when updating; When any of the changed data exceeds the corresponding change threshold, the risk level is cleared.

2. The method according to claim 1, characterized in that The operating status parameters include: real-time speed and acceleration; The risk assessment is performed based on the operating state parameters of the target vehicle and the distance data to obtain a risk level, including: Calculating the travel time of the target vehicle to the target scene based on the real-time speed, acceleration and distance data; Based on preset association information, a risk level matching the travel time is acquired, wherein the preset association information is used to indicate an association relationship between the travel time and the risk level.

3. The method according to claim 2, characterized in that The method further comprises: After the configuration instruction is detected, the preset association information is established based on the association relationship between the travel time indicated by the configuration instruction and the risk level.

4. The method according to claim 1, characterized in that The performing image recognition on the target scene in the driving environment of the target vehicle to obtain scene information includes: Based on a camera device, collecting image frames of the driving environment; Based on the target network model, identifying the tunnel entrance and exit features and / or tunnel marking features in the image frame to obtain a recognition result; The scene information is determined according to the recognition result.

5. The method according to claim 1, characterized in that The scene information includes: scene features of the tunnel exit; The method further comprises: After obtaining the scene information, obtaining the cumulative time of the target vehicle entering the tunnel; Based on the accumulated time, a confidence level of the identified scene feature is determined.

6. The method according to claim 1, characterized in that The control information includes: seat belt control information, buzzer control information, brake pedal control information; The method further comprises: Preset at least one risk level; Corresponding target information is set for each risk level, wherein the target information includes at least one kind of control information.

7. A driving reminder device, characterized in that: The device comprises: A recognition module, used for performing image recognition on a target scene in the driving environment of the target vehicle to obtain scene information, wherein the target scene is used to indicate a tunnel entrance and exit scene, and the scene information is used to indicate scene features of the target scene; A calculation module, used for calculating the distance data between the target vehicle and the target scene based on the scene information; An evaluation module is used to perform risk evaluation based on the operating state parameters of the target vehicle and the distance data to obtain a risk level, wherein the operating state parameters include: angular velocity, steering wheel angle; the risk evaluation based on the operating state parameters of the target vehicle and the distance data to obtain a risk level includes: obtaining the angular velocity based on an angular velocity sensor, and obtaining the steering wheel angle based on a steering wheel angle sensor; obtaining pedal control data based on a pedal sensor, wherein the pedal control data is used to indicate control data of an accelerator pedal and / or a brake pedal of the target vehicle; when the angular velocity, the steering wheel angle and the pedal control data are unchanged, obtaining the risk level based on the distance The data is used to perform risk assessment to obtain a risk level; wherein, the risk assessment based on the distance data to obtain a risk level includes: obtaining the real-time speed and acceleration of the target vehicle; based on the distance data, the real-time speed and acceleration, calculating the target speed when the target vehicle reaches the target scene; performing risk assessment based on the target speed to obtain a risk level; wherein, determining whether the driving object has a lack of concentration by monitoring whether the operating state parameters have changed includes: respectively detecting the change data when the angular velocity, the steering wheel angle and the pedal control data are updated; when any of the change data exceeds the corresponding change threshold, the risk level is cleared; The early warning module is used to control the target vehicle according to the control information corresponding to the risk level to warn the driving object.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the driving prompt method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the driving prompt method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to enable a computer to execute the driving prompt method according to any one of claims 1 to 6.

Images