A driving safety intelligent identification monitoring method and system

Abstract

The application discloses a driving safety intelligent identification monitoring method and system, which comprises the following steps: obtaining the perimeter information of a vehicle in a current state by analyzing real-time images obtained by a high-definition camera, and then obtaining a vehicle perimeter safety prediction value according to a constructed perimeter safety prediction model; obtaining the motion state of the vehicle by a group of sensors, and then obtaining a vehicle motion safety prediction value according to a constructed motion safety prediction model; and then obtaining a comprehensive judgment value by a constructed vehicle safety early warning model, and comparing the comprehensive judgment value with a preset safety threshold to complete safety prediction. The algorithm program provided by the application is applied to a complex driving environment, plays a good prediction and alarm function on the safety of the current environment of the vehicle, and improves the accuracy and real-time performance of identification and prediction.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of driving safety recognition monitoring, and particularly relates to a driving safety intelligent recognition monitoring method and system. BACKGROUND

[0002] The existing driving safety monitoring technology mainly relies on human eye recognition and sensing image display, and the real-time performance and accuracy of this method are not high when it is used in complex environments, which is difficult to ensure driving safety, and the following technical problems exist:

[0003] 1. Low recognition accuracy: human eye recognition and sensing image display are difficult to ensure the recognition accuracy of complex and dynamic driving behaviors.

[0004] 2. Poor real-time performance: human eye recognition and sensing image display are difficult to realize real-time monitoring and early warning.

[0005] 3. Limited monitoring range: human eye recognition and sensing image display can only monitor the driving behaviors within a certain range, and cannot monitor the behaviors of vehicles at a long distance.

[0006] Therefore, there is an urgent need for a new technology that can automatically recognize and monitor driving safety to solve the above technical problems. SUMMARY

[0007] To solve the problems in the prior art, the application provides a driving safety intelligent recognition monitoring method and system, which solves the problems of low recognition accuracy, poor real-time performance and limited monitoring range in the prior art. The application can be used in complex driving environments and has good prediction and alarm functions for the safety of the current environment of the vehicle, improving the accuracy and real-time performance of recognition and prediction. The application solves the problem that the real-time performance and accuracy of the existing driving safety monitoring technology are not high when it is used in complex environments, which is difficult to ensure driving safety.

[0008] The application adopts the following technical solutions.

[0009] The application provides a driving safety intelligent recognition monitoring method, characterized by comprising:

[0010] obtaining the motion state of a target vehicle and the motion state of other vehicles around the target vehicle;

[0011] obtaining real-time images around the target vehicle in different motion states and extracting boundary data of the real-time images;

[0012] predicting the perimeter safety and motion safety of the target vehicle according to the boundary data of the real-time images; and establishing a vehicle safety warning model according to the perimeter safety prediction value and the motion safety prediction value;

[0013] The safety comprehensive value of the target vehicle is obtained based on a vehicle safety warning model, and an alarm is given when the safety comprehensive value is greater than a preset safety threshold.

[0014] Preferably, the motion state of the target vehicle and the motion state of other vehicles around the target vehicle are obtained by:

[0015] A sensor is arranged on the target vehicle, and the sensor includes a vehicle speed sensor, a steering angle sensor, a brake or acceleration sensor.

[0016] The motion state of the target vehicle and the motion state of other vehicles around the target vehicle are obtained by using the sensor.

[0017] Preferably, the motion state of the vehicle includes the driving speed V0 of the target vehicle, the maximum single steering angle ω of the target vehicle, the steering frequency P of the target vehicle in a rated time, and the acceleration λ of the target vehicle.

[0018] The motion state of the other vehicle includes the maximum driving speed V of the other vehicle when passing the target vehicle.

[0019] Preferably, real-time images around the target vehicle in different motion states are obtained, and the boundary data of the real-time images are extracted, including:

[0020] A camera is arranged directly in front of the roof of the vehicle, and the real-time images around the target vehicle in different motion states are obtained by using the camera.

[0021] An image data processor in the vehicle central control system receives the real-time images, and extracts the boundary data of the real-time images around the target vehicle in different motion states, including the number of vehicles α around the target vehicle, and the shortest distance L of the vehicles around the target vehicle from the target vehicle.

[0022] Preferably, according to the boundary data of the real-time images, a perimeter safety prediction value of the target vehicle is obtained based on a perimeter safety prediction model, wherein the perimeter safety prediction model satisfies the following relationship:

[0023]

[0024] Wherein, δ is the prediction value of the vehicle perimeter safety, α is the number of vehicles around the vehicle, L is the minimum distance L of the vehicles around the vehicle from the current vehicle, k1, k2 and k3 are adjustment constants, and dx is an integral operation.

[0025] Preferably, according to the boundary data of the real-time images, a motion safety prediction value of the target vehicle is obtained based on a motion safety prediction model, wherein the motion safety prediction model satisfies the following relationship:

[0026]

[0027] wherein, η is a vehicle motion safety prediction value, V is a maximum driving speed of a surrounding vehicle passing the current vehicle, V0 is a driving speed of the current vehicle, ω is a single maximum steering angle of the current vehicle, P is a steering frequency of the current vehicle in a rated time, t is the rated time, λ is an acceleration of the current vehicle, k4, k5, k6, k7, k8 and k9 are all adjustment constants, and dx is an integral operation.

[0028] Preferably, according to the perimeter safety prediction value and the motion safety prediction value, the vehicle safety warning model established satisfies the following relationship:

[0029]

[0030] wherein, θ is a comprehensive judgment value, δ is a vehicle perimeter safety prediction value, η is a vehicle motion safety prediction value, ζ1 and ζ2 are respectively a first warning adjustment coefficient and a second warning adjustment coefficient, and satisfy ζ1+ζ2≤2, and dx is an integral operation.

[0031] Preferably, the preset safety threshold includes a first safety threshold ω1 and a second safety threshold ω2, and ω2=ω1+Δ%, wherein Δ satisfies the following relationship:

[0032] Δ=e δ-η .

[0033] Preferably, when the comprehensive judgment value is higher than the safety threshold, the central control integrator sends a warning signal to the alarm unit, and the alarm unit alarms.

[0034] The application also provides a driving safety intelligent identification monitoring system, which is used for the driving safety intelligent identification monitoring method and characterized by comprising:

[0035] an information collection module, which is used for collecting the motion state of the current vehicle and the surrounding vehicles;

[0036] a safety prediction module, which is used for predicting the driving safety of the vehicle according to the motion state of the vehicle;

[0037] an alarm unit module, which is used for alarming when the comprehensive judgment value exceeds the safety threshold.

[0038] The beneficial effects of the present application are that, compared with the prior art, the present application provides a driving safety intelligent identification monitoring method and system, which obtains the perimeter information of the vehicle in the current state by analyzing the real-time image obtained by the high-definition camera, and then obtains the vehicle perimeter safety prediction value according to the constructed perimeter safety prediction model; the vehicle motion state is obtained by a group of sensors, and then the vehicle motion safety prediction value is obtained according to the constructed motion safety prediction model; then the comprehensive judgment value is obtained by the constructed vehicle safety warning model, and the safety threshold is compared to complete safety prediction. The prior art ignores the influence of the relative information of the motion state of the vehicle on the safety situation, so that the alarm is given in advance, and the present application solves the problem existing in the prior art by setting the safety threshold. The algorithm program provided by the present application is used in complex driving environment, which plays a good prediction alarm function for the safety of the current environment of the vehicle, improves the accuracy and real-time of identification and prediction, and solves the problem that the real-time and accuracy of the existing driving safety monitoring technology are not high when identifying in complex environment, and it is difficult to ensure driving safety. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 It is a flowchart of a driving safety intelligent identification monitoring method in the present application. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. The embodiments described in the present application are only a part of the embodiments of the present application, not all the embodiments. Based on the spirit of the present application, other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0041] The existing driving safety monitoring technology mainly relies on human eye identification and sensor image display. This way has low real-time and accuracy when identifying in complex environment, and it is difficult to ensure driving safety.

[0042] It should be noted that:

[0043] 1. High-definition camera: In order to obtain high-quality images, a high-definition camera is needed. Such a camera usually has higher resolution and lower noise level, which can provide clearer and more realistic images.

[0044] 2. Real-time image: Real-time image means that the camera can continuously and uninterruptedly obtain images, rather than just taking a photo at a specific time point. This can provide continuous visual information to help the driver better understand the environment around the vehicle.

[0045] 3. Roof-mounted: The camera is mounted on the roof directly in front, which can provide a larger field of view and cover the area in front of and around the vehicle. Roof-mounted can also avoid airflow interference during vehicle driving and improve the stability of the camera.

[0046] 4. Data transmission: The acquired image data needs to be transmitted to the central control system for processing and display. This can be achieved through data lines, wireless transmission, etc. In order to ensure the stability and security of data transmission, appropriate transmission methods and encryption measures need to be selected.

[0047] 5. Central control system: The central control system is one of the control systems of the vehicle, responsible for receiving and processing data from various sensors and devices, and displaying the processed data to the driver. In this invention, after receiving the image data transmitted by the camera, the central control system processes the image through image processing algorithms to improve image clarity and quality, and displays the processed image on the central control screen.

[0048] As shown in Figure 1 , the embodiment 1 of the present invention provides a driving safety intelligent recognition monitoring method and system, which includes:

[0049] S1, set a high-definition camera on the roof directly in front to acquire real-time images of the front and surroundings of the vehicle;

[0050] S2, receive the real-time images through the image data processor in the central control system of the vehicle to acquire perimeter information under the current state of the vehicle;

[0051] The perimeter information acquired by the image data processor includes: the number of vehicles α around the vehicle and the minimum distance L between the vehicle and the surrounding vehicles.

[0052] S3, acquire the motion state of the current vehicle and the motion state of the surrounding vehicles through the sensors set on the vehicle body in real time;

[0053] Preferably, the sensors include a vehicle speed sensor, a steering angle sensor, and a brake / acceleration sensor.

[0054] Preferably, the vehicle speed sensor is set on the roof directly behind, the steering angle sensor is set directly below the vehicle head, and the brake / acceleration sensor is set directly below the vehicle tail.

[0055] The motion state of the current vehicle includes the driving speed V0 of the current vehicle, the maximum single steering angle ω of the current vehicle, the steering frequency P of the current vehicle within a rated time, and the acceleration λ of the current vehicle.

[0056] The motion state of the surrounding vehicles includes the maximum driving speed V of the surrounding vehicles passing through the current vehicle.

[0057] S4, constructing a perimeter safety prediction model and a motion safety prediction model to obtain a vehicle perimeter safety prediction value and a vehicle motion safety prediction value;

[0058] Further, the constructed perimeter safety prediction model is:

[0059]

[0060] wherein, δ is the prediction value of the vehicle perimeter safety, α is the number of vehicles around the vehicle, L is the minimum distance L of the vehicles around the vehicle from the current vehicle, k1, k2 and k3 are adjustment constants, and dx is an integral operation.

[0061] Preferably, k1 = -1.36, k2 = -1.29, and k3 = -1.

[0062] Further, the step of obtaining the adjustment constant is:

[0063] Step 1: First, determine the impact factors: α and L;

[0064] Step 2: Then determine the basic formula model, such as the four basic formulas in this model;

[0065] Step 3: Then input the basic formula into the simulation machine, and then input the obtained data set. This data set is obtained through experiments. During the experiment, different routes are determined, and the specific driving conditions of the corresponding routes are obtained to form a data set for input. The composition of the data set is (the number of vehicles around the vehicle at time T in route A, the minimum distance of the vehicles around the vehicle from the current vehicle at time T in route A, whether the driving computer of the vehicle to be tested at time T in route A is pre-alarmed). With these three basic data, more specific data can be collected to form an experimental data set, and then input.

[0066] Step 4: The simulation machine performs simulation operation to obtain a series of adjustment constants.

[0067] The main purpose of setting the adjustment constant is to make the operation more consistent with the integration of experimental data, and also to make the operation more robust.

[0068] Further, the constructed motion safety prediction model is:

[0069]

[0070] Wherein, η is a vehicle motion safety prediction value, V is a maximum driving speed of a vehicle passing through a current vehicle, V0 is a driving speed of the current vehicle, ω is a single maximum steering angle of the current vehicle, P is a steering frequency of the current vehicle in a rated time, t is the rated time, λ is an acceleration of the current vehicle, k4, k5, k6, k7, k8 and k9 are all adjustment constants, and dx is an integral operation.

[0071] Preferably, k4=-1.32, k5=-1, k6=-1.5 or -1.501, k7=-1.33, k8=-0.72, and k9=-1.

[0072] S5, a vehicle safety warning model is constructed, a comprehensive judgment value is obtained according to a vehicle perimeter safety prediction value and a vehicle motion safety prediction value, and the comprehensive judgment value is compared with a preset safety threshold value, and when the comprehensive judgment value exceeds the safety threshold value, a warning is performed.

[0073] Further, the constructed vehicle safety warning model is:

[0074]

[0075] Wherein, θ is the comprehensive judgment value, δ is the vehicle perimeter safety prediction value, η is the vehicle motion safety prediction value, ζ1 and ζ2 are respectively a first warning adjustment coefficient and a second warning adjustment coefficient, and satisfy ζ1+ζ2≤2, and dx is the integral operation.

[0076] Preferably, ζ1=1.32 and ζ2=0.67.

[0077] The preset safety threshold value includes a first safety threshold value ω1 and a second safety threshold value ω2, and ω2=ω1+Δ%, wherein Δ satisfies the following relationship:

[0078] Δ=e δη-1 .

[0079] Further, the second safety threshold value ω2 is 4.79 or 4.791.

[0080] When the comprehensive judgment value is higher than the safety threshold value, the central control integrator sends a warning signal to the alarm unit, and the alarm unit sends an alarm.

[0081] Embodiment 2 of the present application provides a driving safety intelligent identification system, the driving safety intelligent identification monitoring system is a system used by the foregoing driving safety intelligent identification monitoring method, and includes:

[0082] An information collection module is used to collect motion states of a current vehicle and surrounding vehicles.

[0083] A safety prediction module is used to predict vehicle driving safety according to the vehicle motion state.

[0084] An alarm unit module is configured to alarm when the comprehensive judgment value exceeds the safety threshold.

[0085] In order to verify the technical effect of the present application, operation simulation is carried out in a simulation simulator, and part of the generated data materials are shown in Table 1 below:

[0086] Table 1: Performance simulation data table

[0087]

[0088]

[0089] The present application has the beneficial effect that, compared with the prior art, the present application provides a driving safety intelligent recognition monitoring method and system, which analyzes the perimeter information of the vehicle under the current state after obtaining the real-time image through the high-definition camera, and then obtains the vehicle perimeter safety prediction value according to the constructed perimeter safety prediction model; the vehicle motion state is obtained through a group of sensors, and then the vehicle motion safety prediction value is obtained according to the constructed motion safety prediction model; then the comprehensive judgment value is obtained through the constructed vehicle safety early warning model, and the safety prediction is completed by comparing the preset safety threshold. The prior art ignores the influence of the relative information of the motion state of the vehicle on the safety situation, so that the alarm is given in advance, and the present application solves the problems existing in the prior art by setting the safety threshold. The algorithm program provided by the present application is applied to complex driving environments, which plays a good prediction alarm function for the safety of the current environment of the vehicle, improves the accuracy and real-time performance of recognition and prediction, and solves the problem that the real-time performance and accuracy of the existing driving safety monitoring technology are not high when identifying in a complex environment, and it is difficult to ensure driving safety.

[0090] The present disclosure can be a system, a method, and / or a computer program product. The computer program product can include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present disclosure.

[0091] Computer readable storage media can be tangible storage media which can retain and store instructions for use by an instruction execution device. Computer readable storage media can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer readable storage media include the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

[0092] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0093] Computer readable program instructions for carrying out operations of the present disclosure can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages such as the "C" programming language or similar programming languages. The computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0094] Finally, it should be noted that the above-mentioned embodiments are merely used to illustrate the technical solutions of the present application, rather than limiting the present application, and although the present application has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that the specific embodiments of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and any modification or equivalent replacement without departing from the spirit and scope of the present application should be covered in the protection scope of the claims of the present application.

Claims

1. A driving safety intelligent identification and monitoring method, characterized in that: include: Obtaining the motion state of the target vehicle and the motion states of other vehicles around the target vehicle; Acquire real-time images around the target vehicle in different motion states and extract boundary data of the real-time images; Based on the boundary data of the real-time image, the perimeter safety and motion safety of the target vehicle are predicted respectively; Establish a vehicle safety warning model based on perimeter safety prediction values ​​and motion safety prediction values; According to the boundary data of the real-time image, based on the perimeter safety prediction model, the perimeter safety prediction value of the target vehicle is obtained, wherein the perimeter safety prediction model satisfies the following relationship: Where δ is the predicted value of vehicle perimeter safety, α is the number of vehicles around the vehicle, L is the minimum distance between the surrounding vehicles and the current vehicle, k1, k2, and k3 are adjustment constants, and dx is the integral operation; According to the boundary data of the real-time image, based on the motion safety prediction model, the motion safety prediction value of the target vehicle is obtained, wherein the motion safety prediction model satisfies the following relationship: Where η is the predicted value of vehicle motion safety, V is the maximum speed of surrounding vehicles when passing the current vehicle, V0 is the current vehicle's speed, ω is the current vehicle's maximum single steering angle, P is the current vehicle's steering frequency within a rated time, t is the rated time, λ is the current vehicle's acceleration, k4, k5, k6, k7, k8, and k9 are adjustment constants, and dx is the integral operation; Obtain the comprehensive safety value of the target vehicle based on the vehicle safety warning model, and issue an alarm when the comprehensive safety value exceeds the preset safety threshold; The preset safety thresholds include: a first safety threshold ω1, a second safety threshold ω2, and ω2=ω1+Δ%, where Δ satisfies the following relationship: Δ=e δη-1 Among them, δ is the predicted value of vehicle perimeter safety, and η is the predicted value of vehicle motion safety.

2. The driving safety intelligent identification and monitoring method according to claim 1, characterized in that: Obtaining the motion state of the target vehicle and the motion states of other vehicles around the target vehicle includes: Setting sensors on the target vehicle; the sensors include: vehicle speed sensor, steering angle sensor, brake or acceleration sensor; Sensors are used to obtain the motion state of the target vehicle and the motion states of other vehicles around the target vehicle.

3. The driving safety intelligent identification and monitoring method according to claim 2, characterized in that: The vehicle's motion state includes: the target vehicle's speed V0, the target vehicle's single maximum steering angle ω, the target vehicle's steering frequency P within a rated time, and the target vehicle's acceleration λ; The motion states of other vehicles include: the maximum driving speed V of other vehicles when they pass the target vehicle.

4. The driving safety intelligent identification and monitoring method according to claim 1, characterized in that: Acquire real-time images around the target vehicle in different motion states, and extract boundary data from the real-time images, including: A camera is set up in front of the roof, and the camera is used to obtain real-time images around the target vehicle in different motion states; The image data processor in the vehicle's central control system receives real-time images and extracts boundary data of the real-time images around the target vehicle in each motion state, including: the number of vehicles α around the target vehicle and the shortest distance L between the vehicles around the target vehicle and the target vehicle.

5. The driving safety intelligent identification and monitoring method according to claim 4, characterized in that: According to the perimeter safety prediction value and the motion safety prediction value, the established vehicle safety warning model satisfies the following relationship: Among them, θ is the comprehensive judgment value, δ is the vehicle perimeter safety prediction value, η is the vehicle motion safety prediction value, ζ1 and ζ2 are the first warning adjustment coefficient and the second warning adjustment coefficient, respectively, and ζ1+ζ2≤2, and dx is the integral operation.

6. The driving safety intelligent identification and monitoring method according to claim 1, characterized in that: When the comprehensive safety value is higher than the safety threshold, the central control integrator sends a warning signal to the alarm unit, and the alarm unit issues an alarm.

7. A driving safety intelligent recognition and monitoring system, wherein the driving safety intelligent recognition and monitoring system is a system used in the driving safety intelligent recognition and monitoring method according to any one of claims 1 to 6, characterized in that: include: Information collection module, used to collect the motion status of the current vehicle and surrounding vehicles; Safety prediction module, used to predict vehicle driving safety based on vehicle motion status; The alarm unit module is used to issue an alarm when the comprehensive judgment value exceeds the safety threshold.

Images