CN114954480B

CN114954480B - Safe driving early warning method and system, readable storage medium and vehicle

Info

Publication number: CN114954480B
Application number: CN202210894906.7A
Authority: CN
Inventors: 王晓亮; 张周平; 宋文; 孙萌; 杨光程
Original assignee: Jiangxi Isuzu Motors Co Ltd
Current assignee: Jiangxi Isuzu Motors Co Ltd
Priority date: 2022-07-28
Filing date: 2022-07-28
Publication date: 2022-11-22
Anticipated expiration: 2042-07-28
Also published as: CN114954480A

Abstract

The invention provides a safe driving early warning method, a system, a readable storage medium and a vehicle, wherein the method comprises the following steps: the sensing module actively acquires regional driving information and vehicle state information of a target vehicle at intervals of a first preset time, and sends the regional driving information and the vehicle state to the information center processing module; the information center processing module judges whether the target vehicle has an illegal operation intention according to the regional driving information and the vehicle state information, and the information center processing module sends the illegal operation intention corresponding to the illegal operation intention to the early warning prompting module so that the early warning prompting module executes a corresponding early warning strategy according to the illegal operation intention. According to the safety driving early warning method provided by the invention, whether the driver has bad driving behaviors or not is monitored in real time, and early warning is further carried out in advance to remind the driver to avoid in time, so that traffic violation is effectively reduced and driving safety is improved.

Description

Safe driving early warning method and system, readable storage medium and vehicle

Technical Field

The invention relates to the technical field of vehicle internet, in particular to a safe driving early warning method, a safe driving early warning system, a readable storage medium and a vehicle.

Background

Along with the improvement of living standard, the prevalence rate of car is higher and higher, and the driving of car is experienced, and comfort level and security, intelligent driving auxiliary function are more and more taken into account.

With the increasing of traffic flow year by year, the addition of sudden meteorological factors and artificial factors often makes limited traffic resources catch the mind, so that the road traffic state becomes more and more complicated, when a vehicle runs on a complicated traffic road, the vehicle generally can only be safely and civilized driven by the subjective awareness of a driver, and due to the influence of factors such as driving vision, traffic environment and the like, when the driver performs driving behaviors such as speeding, turning, lane changing and the like, the condition that the judgment on the road condition is inaccurate frequently occurs, so that the driving violation is caused, the driver is easy to violate the traffic regulations and deduct fine, and the traffic accident is easy to occur, so that the driving safety is influenced.

Disclosure of Invention

Based on the above, the invention aims to provide a safe driving early warning method, a safe driving early warning system, a readable storage medium and a vehicle, which are used for monitoring whether a driver has bad driving behaviors in real time and further early warning in advance so as to remind the driver to avoid in time, so that traffic violation is effectively reduced and driving safety is improved.

The safe driving early warning method provided by the invention is realized by a safe driving early warning system, the safe driving early warning system comprises a sensing module arranged behind a front windshield of a vehicle, an information center processing module arranged behind an automobile instrument panel or a central console and an early warning prompting module, and the safe driving early warning method comprises the following steps:

the sensing module actively acquires regional driving information and vehicle state information of a target vehicle at intervals of first preset time, and sends the regional driving information and the vehicle state information to the information center processing module;

the sensing module comprises a camera module and a vehicle-mounted GPS module, the camera module is used for acquiring traffic sign information and lane information of a target vehicle in a driving road, and the regional driving information comprises the traffic sign information and the lane information;

the vehicle-mounted GPS module is used for acquiring position information of a target vehicle every second preset time and acquiring current speed information of the target vehicle according to the position information at adjacent moments, wherein the vehicle state information comprises speed information;

the information center processing module judges whether the target vehicle has illegal operation intentions according to regional driving information and vehicle state information, wherein the illegal types of the illegal operation intentions comprise illegal speeding, illegal reverse driving, illegal lane changing, illegal overtaking and illegal turning;

the information center processing module comprises an MCU and a communication driving module, the communication driving module is used for establishing communication with the sensing module and the early warning prompting module, and the step of judging whether the target vehicle has illegal lane change comprises the following steps:

the MCU actively receives lane images which are sent by the camera module and correspond to a target lane at intervals of fourth preset time, and fits a lane simulation curve according to the trained image segmentation model so as to judge whether the target vehicle has an illegal lane change intention according to the fitted lane simulation curve;

the lane simulation curve is represented as:

Y=AX^5+BX^4+CX^3+DX^2+EX+F

x, Y respectively represents a space abscissa and an spatial ordinate of the target lane, and A, B, C, D, E, F respectively represents a quintic term constant, a quartic term constant, a cubic term constant, a quadratic term constant, a first term constant and a constant term of a quintic polynomial;

if the target vehicle has the violation operation intention, the information center processing module sends the violation type corresponding to the violation operation intention to the early warning prompting module, so that the early warning prompting module executes a corresponding early warning strategy according to the violation type.

In conclusion, according to the safe driving early warning method, whether the vehicle has the intention of bad driving behaviors such as violation overspeed, retrograde motion, lane change, overtaking and turning or not is monitored in real time, if the driver is monitored to have a certain bad driving behavior tendency in the driving process, early warning is sent out in advance, the driver is reminded to avoid in time, and the traffic violation rate of the driver is reduced, and the driving safety is improved. The method comprises the steps that regional driving information and vehicle state information of a target vehicle are obtained through real-time continuous monitoring of a perception module, then an information center processing module analyzes whether the target vehicle has an illegal operation intention according to the regional driving information and the vehicle state information, and when the illegal operation intention is judged to exist, a corresponding early warning strategy is executed by an early warning prompting module according to an illegal type corresponding to the obtained illegal operation intention so as to remind a driver of avoiding, and therefore the aim of assisting the driver in civilized safe driving is achieved.

Further, the step of actively receiving, by the MCU every fourth preset time, lane images corresponding to the target lane sent by the camera module, fitting a lane simulation curve according to the trained image segmentation model, and determining whether the target vehicle has an intention of changing lane in violation according to the fitted lane simulation curve further includes:

performing binarization semantic segmentation on the lane image by using a trained image segmentation model to obtain lane line elements and background elements in the lane image;

and acquiring coordinate information of all real feature points contained in the lane line according to the lane line elements, and projecting the lane image according to the coordinate information of all real feature points and a preset conversion matrix to obtain an overhead image corresponding to the lane image.

Further, the step of obtaining the coordinate information of all real feature points included in the lane line according to the lane line element, and projecting the lane image according to the coordinate information of all real feature points and a preset transformation matrix to obtain an overhead image corresponding to the lane image further includes:

performing five-frame image fitting on the lane line according to the coordinate information of all projection characteristic points contained in the overhead view image obtained after projection to obtain the lane simulation curve;

acquiring the distances between the target vehicle and a left lane line and a right lane line of the target lane respectively according to the lane simulation curve and the received real-time position of the vehicle sent by the vehicle-mounted GPS module, wherein the target lane is a solid lane in which the target vehicle runs currently;

judging whether the distance between the target vehicle and a left lane line or the distance between the target vehicle and a right lane line is smaller than a first preset distance threshold value or not;

and if the distance between the target vehicle and the left lane line or the distance between the target vehicle and the right lane line is smaller than a first preset distance threshold, judging that the target vehicle has an illegal lane changing operation intention.

Further, the lane image is projected according to the following formula:

wherein, x ', y ', and w ' respectively represent the three-dimensional coordinates of a certain projection characteristic point in the overlook image, u, v, and w respectively represent the three-dimensional coordinates of a certain projection characteristic point in the lane image, and a _ij Representing the variation parameters in a preset transformation matrix, where i =1, 2, 3,j =1, 2, 3.

Further, the step of determining that the target vehicle has the illegal turning operation includes:

when the MCU carries out target identification according to the received traffic sign information and the result is a turning prohibition identifier, judging whether the MCU receives steering request information sent by a vehicle body control module in a target vehicle every third preset time;

and if the MCU receives the steering request information, judging that the target vehicle has an illegal turning operation intention.

Further, the step of judging whether the target vehicle has the illegal speeding operation and the illegal reversing operation comprises the following steps:

when the MCU detects a speed limit sign from traffic sign information according to the trained target recognition model, a current speed limit value is obtained according to a recognition result, and the duration of the speed limit sign sent by the camera module is monitored;

the MCU actively receives the speed information of the target vehicle sent by the vehicle-mounted GPS module and judges whether the speed information is greater than the current speed limit value in the duration;

if the vehicle speed information is larger than the current speed limit value in the duration, judging that the target vehicle has an illegal overspeed operation intention;

and when the MCU identifies the reverse driving prohibition identification from the received traffic sign information, judging that the target vehicle has the illegal reverse driving operation intention.

Further, the information hub processing module sends the violation type corresponding to the violation operation intention to the early warning prompting module, so that the early warning prompting module executes a corresponding early warning policy according to the violation type, including:

after the MCU obtains the violation type of the target vehicle, the violation operation intention of the target vehicle is sent to the early warning prompting module through the communication driving module;

the early warning prompt module calls out corresponding prompt information from a preset database according to the violation operation intention, performs voice broadcast according to the prompt information, and controls the steering wheel of the target vehicle to vibrate for a fifth preset time.

According to the vehicle safe driving early warning system of the embodiment of the invention, the system comprises:

the sensing module is used for actively acquiring regional driving information and vehicle state information of a target vehicle at intervals of first preset time and sending the regional driving information and the vehicle state information to the information center processing module;

the perception module includes camera module and on-vehicle GPS module, wherein:

the camera module is used for acquiring traffic sign information and lane information of a target vehicle in a running road, and the regional driving information comprises the traffic sign information and the lane information;

the vehicle-mounted GPS module is used for acquiring the position information of the target vehicle at intervals of second preset time, and acquiring the current speed information of the target vehicle according to the position information of adjacent moments, wherein the vehicle state information comprises speed information;

the information center processing module is used for judging whether the target vehicle has illegal operation intentions according to the regional driving information and the vehicle state information, wherein the illegal types of the illegal operation intentions comprise illegal speeding, illegal reverse driving, illegal lane changing, illegal overtaking and illegal turning;

the information center processing module comprises an MCU and a communication driving module, wherein:

the communication driving module is used for establishing communication with the sensing module and the early warning prompting module, and the step of judging whether the target vehicle has an illegal lane change comprises the following steps:

the MCU is used for actively receiving lane images which are sent by the camera module and correspond to a target lane at intervals of fourth preset time, fitting a lane simulation curve according to the trained image segmentation model, and judging whether a target vehicle has an illegal lane change intention according to the fitted lane simulation curve;

and the early warning prompting module is used for receiving the violation type corresponding to the violation operation intention sent by the information center processing module and executing a corresponding early warning strategy according to the violation type if the violation operation intention exists in the target vehicle.

In another aspect, the present invention further provides a readable storage medium storing one or more programs, which when executed by a processor implement the safety driving warning method as described above.

Another aspect of the present invention also provides a vehicle comprising a memory and a processor, wherein:

the memory is used for storing computer programs;

the processor is used for realizing the safe driving early warning method when executing the computer program stored in the memory.

Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.

Drawings

Fig. 1 is a flowchart of a safety driving warning method according to a first embodiment of the present invention;

fig. 2 is a flowchart of a safety driving warning method according to a second embodiment of the present invention;

fig. 3 is a schematic structural diagram of a safety driving warning system according to a third embodiment of the present invention.

The following detailed description will further illustrate the invention in conjunction with the above-described figures.

Detailed Description

To facilitate an understanding of the invention, the invention will now be described more fully with reference to the accompanying drawings. Several embodiments of the invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

Referring to fig. 1, a flowchart of a safety driving warning method according to a first embodiment of the present invention is shown, where the method includes steps S01 to S03, where:

step S01: the sensing module actively acquires regional driving information and vehicle state information of a target vehicle at intervals of first preset time, and sends the regional driving information and the vehicle state information to the information center processing module;

step S02: the information center processing module judges whether the target vehicle has illegal operation intentions according to regional driving information and vehicle state information, wherein the illegal types of the illegal operation intentions comprise illegal speeding, illegal reverse driving, illegal lane changing, illegal overtaking and illegal turning;

step S03: if the target vehicle has the violation operation intention, the information center processing module sends the violation type corresponding to the violation operation intention to the early warning prompting module, so that the early warning prompting module executes a corresponding early warning strategy according to the violation type.

It should be noted that the safe driving early warning method is realized by a safe driving early warning system, the system comprises a sensing module installed behind a front windshield of a vehicle, an information center processing module installed behind an automobile instrument panel or a center console, and an early warning prompt module, the sensor sensing module in the figure is the sensing module, wherein:

the perception module mainly comprises a camera module and a vehicle-mounted GPS module which are arranged behind a front windshield. Wherein a plurality of high definition digtal cameras that include in the camera module all link to each other with information center processing module through CAN FD interface, and on-vehicle GPS module passes through RS485 communication bus and links to each other with center processing module. The camera module is internally provided with an AI chip, and can sense traffic markers, lane information and the like in a driving road through a built-in target recognition algorithm and a lane line recognition algorithm, so that regional driving information is acquired; the vehicle-mounted GPS module is used for receiving satellite positioning signals, and can determine road types and current vehicle speeds on an open road to realize vehicle motion state estimation, and it should be noted that the built-in AI chip may also be disposed in the MCU in the information center processing module to enable the MCU to realize dual functions of identification and control.

The information center processing module mainly comprises an MCU and a communication driving module. The MCU receives signals from the vehicle-mounted GPS module and the camera module, and determines driving conditions against regulations, such as overspeed, retrograde motion, violation lane changing, violation turning, violation overtaking and the like through internal operation logic. The internal software architecture of the MCU is similar to a finite state machine, and different driver reminding information strategies can be formulated under different violation driving conditions. After the operating mode violating the regulations appears outside, driver reminds the tactics and can be sent for acoustics through communication drive module and remind module, steering wheel vibrations module, screen display module to the realization is released driver and is reminded information.

The early warning prompt module comprises an acoustic prompt module, a steering wheel vibration module, a screen display module and the like. The acoustic reminding module is a functional module for playing a pre-stored acoustic signal in the information center processing module through a loudspeaker, and can remind a driver of standardizing driving operation by voice; the steering wheel vibration module is a vibration function module which drives the eccentric device to vibrate through a direct current motor arranged in the steering wheel, receives a vibration simulation signal from the information center processing module and can vibrate the steering wheel at a fixed frequency to remind a driver; the screen display module issues vehicle violation state reminding through screens of a liquid crystal instrument, a liquid crystal central control and the like of the vehicle based on the driver reminding strategy so as to realize fusion of traffic information reminding.

Referring to fig. 2, a flowchart of a safety driving warning method according to a second embodiment of the present invention is shown, the method includes steps S101 to S104, wherein:

step S101: the sensing module actively acquires regional driving information and vehicle state information of a target vehicle at intervals of first preset time, and sends the regional driving information and the vehicle state information to the information center processing module;

it should be noted that, after the entire vehicle is powered on, the safety driving early warning system starts to work, the sensing module therein collects regional driving information and vehicle state information about a target vehicle once every first preset time, the target vehicle is a vehicle equipped with the safety driving early warning system, and the regional driving information refers to road condition information where a target is located, such as traffic sign information, lane information, traffic light information, and the like.

Specifically, this perception module includes camera module and on-vehicle GPS module, wherein:

the camera module is used for acquiring traffic sign information and lane information of a target vehicle in a running road, the vehicle-mounted GPS module is used for acquiring position information of the target vehicle at intervals of second preset time and acquiring current speed information of the target vehicle according to the position information at adjacent moments, and the vehicle state information comprises speed information.

It should be noted that the first preset time is set to continuously monitor the relevant information of the target vehicle in real time, that is, the camera collects the area driving information once every first preset time, the second preset time is generally not longer than the first preset time, and the purpose of setting the second preset time is to monitor the speed of the target vehicle at a high frequency so as to improve the accuracy of the obtained real-time speed value of the vehicle.

Step S102: the information center processing module judges whether the target vehicle has illegal operation intentions according to regional driving information and vehicle state information, wherein the illegal types of the illegal operation intentions comprise illegal speeding, illegal reverse driving, illegal lane changing, illegal overtaking and illegal turning;

it is important to explain that the information center processing module comprises an MCU and a communication driving module, and the communication driving module is used for establishing communication with the perception module and the early warning prompt module.

It should be noted that, in the process of determining whether the target vehicle has the illegal lane change intention, the MCU actively receives lane images corresponding to the target lane sent by the camera module at intervals of a fourth preset time, and fits a lane simulation curve according to the trained image segmentation model, so as to determine whether the target vehicle has the illegal lane change intention according to the fitted lane simulation curve.

Specifically, after acquiring a lane image, the MCU performs binarization semantic segmentation on the lane image by using a trained image segmentation model to obtain lane line elements and background elements in the lane image; and then acquiring coordinate information of all real feature points contained in a lane line according to the lane line elements, projecting the lane image according to the coordinate information of all real feature points and a preset conversion matrix to obtain an overhead view image corresponding to the lane image, and performing five-frame image fitting on the lane line according to the coordinate information of all projected feature points contained in the overhead view image obtained after projection to obtain the lane simulation curve.

Specifically, the lane image is projected according to the following formula:

wherein, x ', y ', w ' respectively represent the three-dimensional coordinates of a certain projection feature point in the overlook image, u, v, w respectively represent the three-dimensional coordinates of a certain projection feature point in the lane image, a _ij Representing the variation parameters in a preset transformation matrix, where i =1, 2, 3,j =1, 2, 3.

In addition, the expression of the lane simulation curve is as follows:

Y=AX^5+BX^4+CX^3+DX^2+EX+F

x, Y represents the space abscissa and ordinate of the target lane, and A, B, C, D, E, F represents the quintic constant, the quartic constant, the cubic constant, the quadratic constant, the first constant and the constant term of the quintic polynomial.

It should be noted that, by obtaining a fifth-order polynomial of the left and right lanes in the image, and then estimating the distance between the vehicle and the left and right lane lines by the fifth-order polynomial, it is determined whether the line pressing risk is caused. Because the image shot by the camera can be regarded as a two-dimensional coordinate grid in practice, the grid where the lane lines are connected can obtain a plurality of points, and the points are fitted by an algorithm to form a fifth-order polynomial.

Further, five parameters A, B, C, D, E are generated by setting the form of a fifth-order polynomial, so that the position of the lane line is determined, and thenShooting the corresponding relation between the image space coordinate and the real space coordinate through a camera, and then corresponding the A, B, C, D, E parameter with the distance between the vehicle and the lane lines on the two sides to obtain f ₁ (A, B, C, D, E) is the distance between the target vehicle and the left lane, f ₂ (A, B, C, D, E) is the distance between the target vehicle and the right lane, where f ₁ Means the left-side distance, f, obtained based on the mapping relationship between the image space and the real space coordinates under the parameter representation of a fifth-order polynomial ₂ The right-side distance is obtained based on the mapping relation between the image space and the real space coordinate under the fifth-order polynomial parameter representation.

Further, after the right side distance and the left side distance are obtained, whether the right side distance or the left side distance exceeds a first preset distance threshold value is judged, if the distance of one side of the right side distance or the left side distance exceeds the first preset distance threshold value, it is indicated that the target vehicle has a line pressing risk, namely, an illegal lane changing intention exists, and in the embodiment, the first preset distance threshold value needs to be larger than zero so as to play a role of monitoring in advance.

Further, the step of judging that the target vehicle has the illegal turning operation comprises the following steps:

when the MCU carries out target identification according to the received traffic sign information and the result is a turning prohibition identifier, the MCU judges whether steering request information sent by a vehicle body control module in a target vehicle is received or not every third preset time; and if the MCU receives the steering request information, judging that the target vehicle has an illegal turning operation intention. That is, the MCU may determine that the target vehicle has an illegal turning operation intention after it is monitored that the driver has an intention to turn and the steering prohibition flag is acquired.

The step of judging that the target vehicle has the illegal overspeed operation intention comprises the following steps:

when the MCU detects a speed limit sign from traffic sign information according to the trained target recognition model, a current speed limit value is obtained according to a recognition result, and the duration of the speed limit sign sent by the camera module is monitored; the MCU actively receives the speed information of the target vehicle sent by the vehicle-mounted GPS module and judges whether the speed information is greater than the current speed limit value in the duration; if the vehicle speed information is larger than the current speed limit value in the duration, judging that the target vehicle has an illegal overspeed operation intention; namely, if the camera module continuously sends the speed limit identification and the real-time speed monitored in the process exceeds the speed limit value in the speed limit identification, the target vehicle is judged to have the illegal overspeed operation intention.

The method for judging the target vehicle to have the illegal converse operation intention comprises the following steps: when the MCU identifies the illegal retrograde motion prohibition identifier from the received traffic sign information, the target vehicle is judged to have the illegal retrograde motion operation intention, it needs to be noted that for a one-way road, the illegal retrograde motion prohibition identifier is generally set, and on the basis, whether the identifier is obtained through monitoring, and then whether the intention of the illegal retrograde motion operation exists is triggered.

The step of judging that the target vehicle has the illegal overtaking operation intention comprises the following steps: if the MCU monitors scenes such as railway crossings, intersections, narrow bridges, curves, tunnels and the like through the scene classification model, the camera module detects a front target vehicle, and the MCU detects that a driver toggles a steering lamp deflector rod and accelerates, so that the driver is determined to have the intention of overtaking. Or if the MCU detects the mark for forbidding passing, the camera module detects a front target vehicle, and the MCU detects that the driver dials the steering lamp deflector rod and operates at an accelerated speed, so as to confirm that the driver has the intention of passing.

Various illegal driving intentions are monitored, and various possible bad driving behaviors of a driver are standardized, so that the traffic violation rate is effectively reduced, and the driving safety is improved.

Step S103: after the MCU obtains the illegal operation intention of the target vehicle, the illegal operation intention of the target vehicle is sent to the early warning prompting module through the communication driving module;

step S104: the early warning prompt module calls out corresponding prompt information from a preset database according to the violation operation intention, performs voice broadcast according to the prompt information, and controls the steering wheel of the target vehicle to vibrate for a fifth preset time.

By way of example and not limitation, if the monitored violation operation intention is violation turning, the corresponding early warning strategy is as follows: the voice reminds the driver to 'do not turn left' or 'do not turn right'; the steering wheel vibrates for 3s; and displaying a character prompt of 'forbidding left turning' or 'forbidding right turning' on the vehicle-mounted screen for 3s.

If the monitored violation operation intention is violation overspeed, the corresponding early warning strategy is as follows: the voice reminds the driver of 'Do not overspeed'; the vehicle screen displays the word prompt of 'Do not overspeed', which lasts for 3s.

If the monitored illegal operation intention is illegal lane change, the corresponding early warning strategy is as follows: the voice reminds the driver of 'no pressing line'; the steering wheel vibrates for 3s; the vehicle-mounted screen displays a character prompt of 'do not change lanes, and you press a line', and the prompt lasts for 3s.

If the monitored illegal operation intention is illegal overtaking, the corresponding early warning strategy is as follows: the voice reminds the driver to 'do not overtake'; the steering wheel vibrates for 3s; the vehicle screen displays the word prompt of 'do not overtake' for 3s.

If the monitored violation operation intention is violation reverse driving, the corresponding early warning strategy is as follows: the voice reminds the driver of 'forbidding the retrograde motion'; the steering wheel vibrates for 3s; and displaying a character prompt of 'forbidding reverse running' on the vehicle-mounted screen for 3s.

In conclusion, according to the safe driving early warning method, through monitoring whether the vehicle has the intention of bad driving behaviors such as violation overspeed, retrograde motion, lane changing, overtaking and turning in real time, if the driver is monitored to have a certain bad driving behavior tendency in the driving process, early warning is sent out in advance, so that the driver is reminded of avoiding in time, the traffic violation rate of the driver is reduced, and the driving safety is improved. The method comprises the steps that regional driving information and vehicle state information of a target vehicle are obtained through real-time continuous monitoring of a perception module, then an information center processing module analyzes whether the target vehicle has an illegal operation intention according to the regional driving information and the vehicle state information, and when the illegal operation intention is judged to exist, a corresponding early warning strategy is executed by an early warning prompting module according to an illegal type corresponding to the obtained illegal operation intention so as to remind a driver of avoiding, and therefore the aim of assisting the driver in civilized safe driving is achieved.

Referring to fig. 3, a schematic structural diagram of a safety driving warning system according to a third embodiment of the present invention is shown, where the system includes:

the sensing module 10 is used for actively acquiring regional driving information and vehicle state information of a target vehicle at intervals of first preset time, and sending the regional driving information and the vehicle state information to the information center processing module;

perception module 10 includes camera module and on-vehicle GPS module, wherein:

the information center processing module 20 is configured to determine whether the target vehicle has an illegal operation intention according to the regional driving information and the vehicle state information, where the illegal type of the illegal operation intention includes illegal speeding, illegal reverse driving, illegal lane changing, illegal overtaking and illegal turning;

information center processing module 20 includes MCU and communication drive module, wherein:

the communication driving module is used for establishing communication with the sensing module and the early warning prompting module, and the step of judging whether the target vehicle has illegal lane changing comprises the following steps:

the MCU is also used for carrying out binarization semantic segmentation on the lane image by adopting the trained image segmentation model so as to obtain lane line elements and background elements in the lane image;

acquiring coordinate information of all real feature points contained in a lane line according to the lane line elements, and projecting the lane image according to the coordinate information of all real feature points and a preset conversion matrix to obtain an overhead image corresponding to the lane image;

the MCU is also used for carrying out five-frame image fitting on the lane line according to the coordinate information of all projection characteristic points contained in the overhead view image obtained after projection to obtain the lane simulation curve;

if the distance between the target vehicle and the left lane line or the distance between the target vehicle and the right lane line is smaller than a first preset distance threshold, judging that the target vehicle has an illegal lane changing operation intention;

the MCU is also used for judging whether the steering request information sent by the vehicle body control module in the target vehicle is received or not at intervals of third preset time when the target is identified according to the received traffic marking information and the result is the turn prohibition identification;

the MCU is also used for judging that the target vehicle has an illegal turning operation intention if the steering request information is received;

when a speed limit sign is detected from traffic sign information according to a trained target recognition model, obtaining a current speed limit value according to a recognition result, and monitoring the duration of the speed limit sign sent by the camera module;

actively receiving the speed information of the target vehicle sent by the vehicle-mounted GPS module, and judging whether the speed information is greater than the current speed limit value in the duration;

when a reverse driving prohibition identifier is identified from the received traffic sign information, determining that the target vehicle has an illegal reverse driving operation intention;

and the early warning prompting module 30 is configured to receive, if the target vehicle has an illegal operation intention, an illegal type corresponding to the illegal operation intention sent by the information center processing module, and execute a corresponding early warning policy according to the illegal type.

In conclusion, according to the safe driving early warning system, whether the vehicle has the intention of bad driving behaviors such as violation overspeed, retrograde motion, lane change, overtaking and turning or not is monitored in real time, if the driver is monitored to have a certain bad driving behavior tendency in the driving process, early warning is sent out in advance, the driver is reminded to avoid in time, and the traffic violation rate of the driver is reduced, and the driving safety is improved. The method comprises the steps that regional driving information and vehicle state information of a target vehicle are obtained through real-time continuous monitoring of a perception module, then an information center processing module analyzes whether the target vehicle has an illegal operation intention according to the regional driving information and the vehicle state information, and when the illegal operation intention is judged to exist, a corresponding early warning strategy is executed by an early warning prompting module according to an illegal type corresponding to the obtained illegal operation intention so as to remind a driver of avoiding, and therefore the aim of assisting the driver in civilized safe driving is achieved.

In another aspect of the present invention, a readable storage medium is further provided, on which one or more programs are stored, and the programs, when executed by a processor, implement the above-mentioned safety driving warning method.

In another aspect of the present invention, a vehicle is further provided, which includes a memory and a processor, where the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so as to implement the above-mentioned safety driving warning method.

Those of skill in the art will understand that the logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be viewed as implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.

In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

The above examples are merely illustrative of several embodiments of the present invention, and the description thereof is more specific and detailed, but not to be construed as limiting the scope of the invention. It should be noted that various changes and modifications can be made by those skilled in the art without departing from the spirit of the invention, and these changes and modifications are all within the scope of the invention. Therefore, the protection scope of the present invention should be subject to the appended claims.

Claims

1. A safe driving early warning method is realized by a safe driving early warning system, and is characterized in that the safe driving early warning system comprises a sensing module arranged behind a front windshield of a vehicle, an information center processing module arranged behind an automobile instrument panel or a central console and an early warning prompting module, and the safe driving early warning method comprises the following steps:

the vehicle-mounted GPS module acquires the position information of a target vehicle every second preset time and acquires the current speed information of the target vehicle according to the position information of adjacent moments, wherein the vehicle state information comprises speed information;

the information center processing module judges whether the target vehicle has an illegal operation intention according to regional driving information and vehicle state information, wherein the illegal types of the illegal operation intention comprise illegal speeding, illegal reverse driving, illegal lane changing, illegal overtaking and illegal turning;

the MCU actively receives lane images which are sent by the camera module and correspond to a target lane at intervals of fourth preset time, and fits a lane simulation curve according to the trained image segmentation model, so as to judge whether a target vehicle has an illegal lane changing intention according to the fitted lane simulation curve, wherein the method specifically comprises the following steps:

projecting the lane image according to the following formula:

wherein, x ', y ', w ' respectively represent the three-dimensional coordinates of a certain projection feature point in the overlook image, u, v, w respectively represent the three-dimensional coordinates of a certain projection feature point in the lane image, a _ij Representing a variation parameter in a preset transformation matrix, wherein i =1, 2, 3,j =1, 2, 3;

if the distance between the target vehicle and a left lane line or the distance between the target vehicle and a right lane line is smaller than a first preset distance threshold, judging that the target vehicle has an illegal lane changing operation intention;

the lane simulation curve is represented as:

Y=AX^5+BX^4+CX^3+DX^2+EX+F

determining the positions of the lane lines according to the quintic constant of the quintic polynomial, and corresponding the quintic constant to the distances between the target vehicle and the lane lines on two sides based on the mapping relation between the image space coordinate and the real space coordinate under the parameter representation of the quintic polynomial to obtain the distance between the target vehicle and the left lane line and the distance between the target vehicle and the right lane line;

2. The safe driving early warning method according to claim 1, wherein the step of determining that the target vehicle has the illegal turning operation comprises:

3. The safe driving early-warning method according to claim 2, wherein the step of judging whether the target vehicle has the illegal speeding operation and the illegal reversing operation comprises the following steps of:

4. The safe driving early-warning method according to claim 3, wherein the information center processing module sends the violation type corresponding to the violation operation intention to the early-warning prompting module, so that the early-warning prompting module executes a corresponding early-warning strategy according to the violation type, and the method comprises the following steps of:

and the early warning prompt module calls out corresponding prompt information from a preset database according to the illegal operation intention, performs voice broadcast according to the prompt information, and controls the steering wheel of the target vehicle to vibrate for a fifth preset time.

5. A safe driving early warning system, the system comprising:

the sensing module is used for actively acquiring regional driving information and vehicle state information of a target vehicle at intervals of first preset time, and sending the regional driving information and the vehicle state information to the information center processing module;

the information center processing module is used for judging whether the target vehicle has an illegal operation intention according to the regional driving information and the vehicle state information, wherein the illegal types of the illegal operation intention comprise illegal speeding, illegal reverse driving, illegal lane changing, illegal overtaking and illegal turning;

the communication driving module is used for establishing communication with the sensing module and the early warning prompting module, and the step of judging whether the target vehicle has illegal lane change comprises the following steps:

the MCU is used for actively receiving lane images which are sent by the camera module and correspond to a target lane at intervals of fourth preset time, fitting a lane simulation curve according to the trained image segmentation model, and judging whether a target vehicle has an illegal lane change intention according to the fitted lane simulation curve, and specifically comprises the following steps:

projecting the lane image according to the following formula:

the lane simulation curve is represented as:

Y=AX^5+BX^4+CX^3+DX^2+EX+F

the MCU is also used for determining the positions of the lane lines according to a quintic constant of the quintic polynomial, and corresponding the quintic constant to the distances between the target vehicle and the lane lines on two sides based on the mapping relation between the image space coordinate and the real space coordinate under the expression of the quintic polynomial parameters to obtain the distance between the target vehicle and the left lane line and the distance between the target vehicle and the right lane line;

6. A readable storage medium, characterized in that the readable storage medium stores one or more programs which, when executed by a processor, implement the safe driving warning method as claimed in any one of claims 1 to 4.

7. A vehicle, comprising a memory and a processor, wherein:

the memory is used for storing computer programs;

the processor is configured to implement the safety driving warning method according to any one of claims 1 to 4 when executing the computer program stored in the memory.