A road accuracy evaluation method and system for lane departure warning

Abstract

The application provides a road accuracy evaluation method and system for lane departure warning. The method comprises the following steps: installing a first camera on the left front wheel of a vehicle, installing a second camera on the right front wheel of the vehicle, and installing a third camera on the front windshield of the vehicle; calibrating the first camera and the second camera based on calibration software; setting a lane departure warning threshold; determining the relationship between the distance from the left front wheel outside to the left lane line obtained based on the first camera and the preset warning distance, or the relationship between the distance from the right front wheel outside to the right lane line obtained based on the second camera and the preset warning distance, to record an alarm event, a false alarm event or a missed alarm event; and counting each event to obtain the road accuracy of the vehicle to be evaluated. The application effectively reduces the road accuracy evaluation cost and the missed alarm rate and the false alarm rate in actual application.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a road accuracy evaluation method and system for lane departure warning. BACKGROUND

[0002] With the development of automatic driving technology, various automatic driving systems have emerged. Among them, the lane departure warning system (LDW) is one of the most basic automatic driving systems. It issues a warning message when the vehicle deviates from the lane to avoid corresponding driving accidents.

[0003] Before the lane departure warning system is finally applied to an automatic driving vehicle driving on a normal road, a large amount of data needs to be used for road accuracy evaluation to ensure that the vehicle deviation can be accurately and completely warned during actual application.

[0004] At present, the road accuracy evaluation of the lane departure warning system is mostly based on intelligent sensors of the evaluation level. That is, the corresponding data collected and analyzed during the repeated test process by the intelligent sensor, and the whole test process is guided. As can be seen, the road accuracy evaluation result is determined by the intelligent sensor, and the intelligent sensor is inevitably affected by its own performance during data collection and processing, which will inevitably cause errors, and thus lead to technical bottlenecks in reducing false negatives and false positives in the actual application of the vehicle lane departure warning system. The intelligent sensor of the evaluation level used in the road accuracy evaluation has high cost, so the cost of the road accuracy evaluation stage is high. SUMMARY

[0005] The present application aims to provide a road accuracy evaluation method and system for lane departure warning to improve the technical problems of high cost in the current road accuracy evaluation process of the lane departure warning system, and difficulty in further reducing the false negative rate and false positive rate in actual application.

[0006] To achieve the above-mentioned purpose, the present application proposes the following technical solutions:

[0007] In a first aspect, the present application provides a road accuracy evaluation method for lane departure warning, comprising:

[0008] installing a first camera on the left front wheel of the vehicle to obtain first video information from the outside of the left front wheel to the left lane line, installing a second camera on the right front wheel of the vehicle to obtain second video information from the outside of the right front wheel to the right lane line, and installing a third camera on the front windshield of the vehicle to obtain third video information of the vehicle driving;

[0009] The first camera is calibrated based on calibration software, with the tangent point between the left front wheel outside and the ground as the origin, and the reference points being the first length, the second length and the third length extending outward perpendicularly to the left front wheel; meanwhile, the second camera is calibrated based on calibration software, with the tangent point between the right front wheel outside and the ground as the origin, and the reference points being the first length, the second length and the third length extending outward perpendicularly to the right front wheel;

[0010] activating a lane departure warning system of the vehicle to be evaluated, and setting a lane departure warning threshold;

[0011] When the vehicle to be evaluated triggers the lane departure warning in actual road driving, and the distance between the left front wheel outside and the left lane line obtained based on the first camera is less than the preset warning distance or the distance between the right front wheel outside and the right lane line obtained based on the second camera is less than the preset warning distance, an alarm event is recorded once;

[0012] When the vehicle to be evaluated triggers the lane departure warning, and the distance between the left front wheel outside and the left lane line obtained based on the first camera is greater than the preset warning distance or the distance between the right front wheel outside and the right lane line obtained based on the second camera is greater than the preset warning distance, a false alarm event is recorded once;

[0013] When the distance between the left front wheel outside and the left lane line obtained based on the first camera is less than the preset warning distance or the distance between the right front wheel outside and the right lane line obtained based on the second camera is less than the preset warning distance, and the lane departure warning is not triggered, a missed alarm event is recorded once;

[0014] When the driving mileage of the vehicle to be evaluated in actual road driving reaches the preset evaluation driving mileage, the road accuracy of the vehicle to be evaluated is obtained based on the statistical results of the alarm event, the false alarm event and the missed alarm event.

[0015] Further, before the lane departure warning system of the vehicle to be evaluated is activated and the lane departure warning threshold is set, the following steps are further included:

[0016] When the shooting error of the first camera and the second camera after calibration is greater than an error threshold, the first camera and the second camera are recalibrated.

[0017] Further, after the alarm event is recorded once, the following steps are further included:

[0018] The warning information is sent to the operation panel in the driving area to remind the driver to adopt the corresponding operation instruction to make it turn to a position greater than the lane departure warning threshold;

[0019] When it is determined that the to-be-tested vehicle does not receive the operation instruction feedback of the driver within the preset time period after the warning information sending time, a proactive control instruction is sent to the vehicle chassis system to make the to-be-tested vehicle turn back to a position greater than the lane deviation warning threshold.

[0020] Further, comprising:

[0021] Based on all false alarm events, missed alarm events and their time stamps, a curve graph is drawn; wherein the time point when the to-be-tested vehicle is driving on the actual road during the road accuracy evaluation is taken as the horizontal coordinate, and whether a false alarm event or a missed alarm event occurs at the corresponding time point is taken as the vertical coordinate; wherein the vertical coordinate value when a false alarm event occurs is recorded as 1, and the vertical coordinate value when a missed alarm event occurs is recorded as 2;

[0022] Based on the distribution law of false alarm events and missed alarm events in the curve graph, the lane deviation warning system is optimized.

[0023] Further, the lane deviation warning system of the to-be-evaluated vehicle is activated, and the lane deviation warning threshold is set, comprising:

[0024] The lane deviation warning system of the to-be-evaluated vehicle is activated, and the whole vehicle CAN information is input to the industrial computer for driving data collection;

[0025] The first lane deviation warning threshold is set to be less than 0.3m from the inside of the left lane line to the outside of the front left wheel of the to-be-tested vehicle, and the second lane deviation warning threshold is set to be less than 0.3m from the inside of the right lane line to the outside of the front right wheel of the to-be-tested vehicle.

[0026] In a second aspect, the technical scheme provides a road accuracy evaluation system for lane deviation warning, comprising:

[0027] A camera installation module is configured to install a first camera on the front left wheel of the vehicle to obtain first video information from the outside of the front left wheel to the left lane line, install a second camera on the front right wheel of the vehicle to obtain second video information from the outside of the front right wheel to the right lane line, and install a third camera on the front windshield of the vehicle to obtain third video information of the vehicle driving;

[0028] A camera calibration module is configured to calibrate the first camera based on calibration software, with the tangent point of the outside of the front left wheel and the ground as the origin, and the first length, the second length and the third length extending outward perpendicularly to the front left wheel as reference points; and calibrate the second camera with the tangent point of the outside of the front right wheel and the ground as the origin, and the first length, the second length and the third length extending outward perpendicularly to the front right wheel as reference points;

[0029] An alarm threshold setting module is configured to activate a lane departure warning system of the vehicle to be evaluated and set a lane departure alarm threshold;

[0030] A first judging module is configured to record an alarm event when the vehicle to be evaluated triggers the lane departure alarm in actual road driving and meets a condition that a distance from an outer side of a front left wheel to a left lane line obtained based on the first camera is less than a preset warning distance or a distance from an outer side of a front right wheel to a right lane line obtained based on the second camera is less than the preset warning distance.

[0031] A false alarm event is recorded when the lane departure alarm is triggered and meets a condition that the distance from the outer side of the front left wheel to the left lane line obtained based on the first camera is greater than the preset warning distance or the distance from the outer side of the front right wheel to the right lane line obtained based on the second camera is greater than the preset warning distance.

[0032] A missed alarm event is recorded when the condition that the distance from the outer side of the front left wheel to the left lane line obtained based on the first camera is less than the preset warning distance or the distance from the outer side of the front right wheel to the right lane line obtained based on the second camera is less than the preset warning distance is met and the lane departure alarm is not triggered.

[0033] An accuracy rate obtaining module is configured to obtain a road accuracy rate of the vehicle to be evaluated based on a statistical result of the alarm event, the false alarm event and the missed alarm event when a driving mileage of the vehicle to be evaluated in actual road driving reaches a preset evaluation driving mileage.

[0034] Further, comprising:

[0035] A second judging module is configured to re-calibrate the first camera and the second camera when a shooting error of the first camera and the second camera after calibration is greater than an error threshold.

[0036] Further, comprising:

[0037] A first sending module is configured to send a warning information to an operation panel in a driving area to remind a driver to adopt a corresponding operation instruction to make the driver turn back to a position greater than the lane departure warning threshold.

[0038] A second sending module is configured to send an active control instruction to a vehicle chassis system to make the vehicle to be evaluated turn back to a position greater than the lane departure warning threshold when the vehicle to be evaluated does not receive a feedback of the operation instruction of the driver within a preset time period after the warning information is sent.

[0039] In a third aspect, the technical solution provides an electronic device, comprising at least one processor coupled with a memory, wherein the memory stores a computer program configured to be executed by the processor to perform the method.

[0040] In a fourth aspect, the technical solution provides a computer readable storage medium, which stores a computer program for performing the method.

[0041] According to the above technical solution, the technical solution of the present application provides a new road accuracy evaluation method for lane departure warning to improve the technical defects of the existing evaluation method, i.e., the difficulty in improving accuracy and the difficulty in reducing cost.

[0042] The inventor found that the defects in the current road accuracy evaluation of lane departure warning are caused by intelligent sensors. Specifically, on the one hand, the intelligent sensors are affected by their own errors, which makes it difficult to improve the road accuracy; on the other hand, the intelligent sensors are affected by their own costs, which makes it difficult to reduce the cost of the evaluation process. Therefore, the inventor considers designing a lane departure warning road accuracy evaluation method without the aid of intelligent sensors; and then considers that the camera is also a commonly used information auxiliary acquisition means in vehicles, which is low in cost and simple in data acquisition, and the corresponding calibration result is controllable and can be optimized. Therefore, the road accuracy evaluation method is designed based on the camera.

[0043] Specifically, the method comprises the following steps: first, a first camera is installed on the left front wheel of the vehicle to obtain first video information from the left front wheel outside to the left lane line, a second camera is installed on the right front wheel of the vehicle to obtain second video information from the right front wheel outside to the right lane line, and a third camera is installed on the front windshield of the vehicle to obtain third video information of the vehicle driving. Secondly, in order to ensure the accuracy of subsequent data acquisition, the first camera is calibrated based on calibration software, with the tangent point of the left front wheel outside and the ground as the origin, and the reference points being the first length, the second length and the third length extending outward perpendicular to the left front wheel. Similarly, the second camera is calibrated. Then, a lane departure warning threshold is set, and the corresponding alarm events, false alarm events and missed alarm events are obtained based on the numerical relationship between the lane departure alarm trigger and the distance between the first camera and the second camera and the lane line. Finally, when the driving mileage of the vehicle to be evaluated in actual road driving reaches the preset evaluation driving mileage, the road accuracy of the vehicle to be evaluated can be obtained based on the statistical results of the alarm events, the false alarm events and the missed alarm events.

[0044] It should be appreciated that all combinations of the foregoing concepts and additional concepts described in greater detail below (provided such concepts are not mutually inconsistent) are contemplated as being part of the inventive subject matter. For example, a system or article of manufacture can be one or more of the following: a process; a machine, manufacture, manufacture for use; an improvement; any combination of operations or interfaces; and / or other examples.

[0045] For a more complete understanding of the foregoing and other aspects of the present application, reference is now made to the following descriptions taken in connection with the accompanying drawings in which: BRIEF DESCRIPTION OF DRAWINGS

[0046] The accompanying drawings are not intended to be drawn to scale. In the drawings, each identical, or nearly identical, component that is illustrated in various figures is represented with a like numeral. For purposes of clarity, not every component is called out in every drawing. There is now being described by way of example various aspects of the present application with reference to the attached drawings in which:

[0047] Figure 1 Flow chart for road accuracy evaluation method for lane departure warning in the present embodiment;

[0048] Figure 2 Flow chart for camera calibration result confirmation;

[0049] Figure 3 Flow chart for lane departure system activation and alarm threshold setting;

[0050] Figure 4 Post-processing flow chart for sending alarm event;

[0051] Figure 5 Flow chart for lane departure system optimization;

[0052] Figure 6 Block diagram of road accuracy evaluation system for lane departure warning described in the present embodiment;

[0053] Figure 7 Structural diagram of electronic device described in the present embodiment. DETAILED DESCRIPTION

[0054] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the described embodiments of this application without creative effort are within the scope of protection of this application. Unless otherwise defined, the technical or scientific terms used herein should have the ordinary meaning understood by those skilled in the art to which this application pertains.

[0055] The terms "first," "second," and similar words used in this patent application specification and claims do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Similarly, unless the context clearly indicates otherwise, the singular forms of "an," "a," or "the," etc., do not indicate a quantity limitation, but rather indicate the presence of at least one. Terms such as "comprising" or "including" mean that the element or object preceding "comprising" encompasses the features, integrals, steps, operations, elements, and / or components listed following "comprising" or "including," and do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or collections thereof. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; these relative positional relationships may change accordingly when the absolute position of the described object changes.

[0056] In existing technologies, lane departure warning systems primarily rely on evaluation-level smart sensors for road accuracy assessment. This leads to two main problems: firstly, the performance of these smart sensors during data acquisition and processing limits their ability to further reduce false alarm and missed detection rates in practical applications; secondly, the high cost of evaluation-level smart sensors used in road accuracy assessment keeps the overall cost of the assessment phase high. Therefore, this embodiment aims to provide a road accuracy assessment method for lane departure warning systems to address the aforementioned shortcomings in existing lane departure warning systems.

[0057] The following description, in conjunction with the accompanying drawings, details the road accuracy assessment method for lane departure warning disclosed in this embodiment.

[0058] like Figure 1 As shown, the method includes:

[0059] Step S102, installing the first camera on the left front wheel of the vehicle to obtain first video information from the outside of the left front wheel to the left lane line, installing the second camera on the right front wheel of the vehicle to obtain second video information from the outside of the right front wheel to the right lane line, and installing the third camera on the front windshield of the vehicle to obtain third video information of the vehicle driving.

[0060] In the embodiment, the first camera, the second camera and the third camera are all ordinary cameras.

[0061] Step S104, calibrating the first camera based on the calibration software, taking the tangent point of the left front wheel outside and the ground as the origin, and extending outwardly perpendicularly to the left front wheel by a first length, a second length and a third length as reference points; and at the same time, calibrating the second camera based on the calibration software, taking the tangent point of the right front wheel outside and the ground as the origin, and extending outwardly perpendicularly to the right front wheel by a first length, a second length and a third length as reference points.

[0062] In specific implementation, the first length is 0 m, the second length is 0.5 m, and the third length is 1 m.

[0063] As a preferred embodiment, in order to improve the accuracy of the distance data obtained by the first camera and the second camera subsequently, as shown in Figure 2 , the method further comprises:

[0064] Step S105, when the shooting error of the first camera and the second camera after calibration is greater than an error threshold, recalibrating the first camera and the second camera.

[0065] In the embodiment, the error threshold is 2 cm.

[0066] Step S106, activating the lane departure warning system of the vehicle to be evaluated, and setting a lane departure warning threshold.

[0067] As a specific embodiment, as shown in Figure 3 , the activation of the lane departure warning system and the lane departure warning threshold are specifically performed by the following steps:

[0068] Step S1062, activating the lane departure warning system of the vehicle to be evaluated, and inputting the whole vehicle CAN (Controller Area Network) information to the industrial computer to collect driving data.

[0069] Step S1064, set the first lane deviation alarm threshold as the distance between the left front wheel of the vehicle to be tested and the inner side of the left lane line is less than 0.3m, and set the second lane deviation alarm threshold as the distance between the right front wheel of the vehicle to be tested and the inner side of the right lane line is less than 0.3m.

[0070] Step S108, when the vehicle to be evaluated triggers the lane deviation alarm in actual road driving and meets the condition that the distance between the left front wheel and the left lane line obtained based on the first camera is less than the preset early warning distance or the distance between the right front wheel and the right lane line obtained based on the second camera is less than the preset early warning distance, record an alarm event once;

[0071] When the lane deviation alarm is triggered and the condition that the distance between the left front wheel and the left lane line obtained based on the first camera is greater than the preset early warning distance or the distance between the right front wheel and the right lane line obtained based on the second camera is greater than the preset early warning distance is met, record a false alarm event once;

[0072] When the condition that the distance between the left front wheel and the left lane line obtained based on the first camera is less than the preset early warning distance or the distance between the right front wheel and the right lane line obtained based on the second camera is less than the preset early warning distance is met, and the lane deviation alarm is not triggered, record a missed alarm event once.

[0073] As a preferred embodiment, in order to effectively handle the abnormalities after the alarm event occurs to avoid driving accidents, as shown in Figure 4 After recording an alarm event once, the method further comprises:

[0074] Step S1092, send early warning information to the operation panel in the driving area to remind the driver to adopt corresponding operation instructions to make the vehicle turn back to a position greater than the lane deviation early warning threshold.

[0075] Step S1094, when it is judged that the vehicle to be tested does not receive the operation instruction feedback of the driver within a preset time period after the early warning information is sent, send an active control instruction to the vehicle chassis system to make the vehicle to be tested turn back to a position greater than the lane deviation early warning threshold.

[0076] Step S110, when it is judged that the driving mileage of the vehicle to be evaluated in actual road driving reaches a preset evaluation driving mileage, obtain the road accuracy of the vehicle to be evaluated based on the statistical results of the alarm event, the false alarm event and the missed alarm event.

[0077] As a preferred embodiment, as shown in Figure 5 In order to further improve the road accuracy of the lane deviation early warning system, the following operations are further performed:

[0078] Step S1122, based on all false positive events, false negative events and their time stamps when they occur, draw a curve; wherein the time point when the vehicle to be tested is actually driving on the road during the road accuracy evaluation is taken as the horizontal coordinate, and whether a false positive event or a false negative event occurs at the corresponding time point is taken as the vertical coordinate; wherein the vertical coordinate value when a false positive event occurs is recorded as 1, and the vertical coordinate value when a false negative event occurs is recorded as 2.

[0079] Step S1124, based on the distribution law of false positive events and false negative events in the curve, optimizing the lane deviation warning system.

[0080] The above procedures can be run in a processor, or can also be stored in a memory (or computer readable storage medium). The computer readable storage medium includes permanent and non-permanent, removable and non-removable media, and can be realized by any method or technology to store information. The information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. According to the definition herein, computer readable storage media does not include temporary computer readable media such as modulated data signals and carriers.

[0081] These computer programs can also be loaded into a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer implemented process, so that the instructions executed on the computer or other programmable device provide a process for implementing the functions specified in the flow Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The functions specified in one flow or multiple flows and / or blocks

[0082] Based on this, the embodiment also provides a road accuracy evaluation system for lane deviation warning. As shown in the figure, the system comprises: Figure 6

[0083] ​The camera installation module is configured to install a first camera on a left front wheel of the vehicle to obtain first video information of a left front wheel outer side to a left lane line, install a second camera on a right front wheel of the vehicle to obtain second video information of a right front wheel outer side to a right lane line, and install a third camera on a front windshield of the vehicle to obtain third video information of the vehicle driving.

[0084] The camera calibration module is configured to calibrate the first camera based on calibration software, with a tangent point of the left front wheel outer side and the ground as an origin, and with a first length, a second length and a third length extending outward perpendicularly to the left front wheel as reference points; and calibrate the second camera based on the calibration software, with a tangent point of the right front wheel outer side and the ground as the origin, and with the first length, the second length and the third length extending outward perpendicularly to the right front wheel as the reference points.

[0085] The alarm threshold setting module is configured to activate a lane departure warning system of the vehicle to be evaluated, and set a lane departure alarm threshold.

[0086] The first judgment module is configured to record an alarm event when the vehicle to be evaluated triggers the lane departure alarm in actual road driving, and meets a condition that a distance between the left front wheel outer side and the left lane line obtained based on the first camera is less than a preset warning distance or a distance between the right front wheel outer side and the right lane line obtained based on the second camera is less than the preset warning distance.

[0087] The first judgment module is configured to record a false alarm event when the vehicle to be evaluated triggers the lane departure alarm, and meets a condition that the distance between the left front wheel outer side and the left lane line obtained based on the first camera is greater than the preset warning distance or the distance between the right front wheel outer side and the right lane line obtained based on the second camera is greater than the preset warning distance.

[0088] The first judgment module is configured to record a missed alarm event when the vehicle to be evaluated meets a condition that the distance between the left front wheel outer side and the left lane line obtained based on the first camera is less than the preset warning distance or the distance between the right front wheel outer side and the right lane line obtained based on the second camera is less than the preset warning distance, and the lane departure alarm is not triggered.

[0089] The accuracy rate obtaining module is configured to obtain a road accuracy rate of the vehicle to be evaluated based on a statistical result of the alarm event, the false alarm event and the missed alarm event when a driving mileage of the vehicle to be evaluated in actual road driving reaches a preset evaluation driving mileage.

[0090] The system is configured to implement the steps of the above method, and thus the description has been made and will not be repeated here.

[0091] For example, the system further comprises:

[0092] The second judging module is configured to re-calibrate the first camera and the second camera when the shooting error of the first camera and the second camera after calibration is greater than the error threshold.

[0093] For example, the system further comprises:

[0094] The first sending module is configured to send a pre-warning information to an operation panel of a driving area to remind a driver to adopt a corresponding operation instruction to make the driver turn back to a position greater than the lane deviation pre-warning threshold.

[0095] The second sending module is configured to send an active control instruction to a vehicle chassis system to make the vehicle under test turn back to a position greater than the lane deviation pre-warning threshold when it is judged that the vehicle under test does not receive the operation instruction feedback of the driver within a preset time period after the pre-warning information is sent.

[0096] For another example, the system further comprises:

[0097] The curve drawing module is configured to draw a curve based on all false alarm events, missed alarm events and time stamps when they occur; wherein a time point when the vehicle under test is actually driving on a road is taken as the horizontal coordinate, and whether a false alarm event or a missed alarm event occurs at the corresponding time point is taken as the vertical coordinate; wherein the vertical coordinate value when a false alarm event occurs is recorded as 1, and the vertical coordinate value when a missed alarm event occurs is recorded as 2.

[0098] The system optimization module is configured to optimize the lane deviation pre-warning system based on the distribution law of the false alarm events and the missed alarm events in the curve.

[0099] For another example, the alarm threshold setting module in the system comprises:

[0100] The communication link unit is configured to activate the lane deviation pre-warning system of the vehicle to be evaluated, and input the whole vehicle CAN information to the industrial computer to collect driving data.

[0101] The threshold setting unit is configured to set the first lane deviation alarm threshold as the distance between the outside of the front left wheel of the vehicle under test and the inside of the left lane line being less than 0.3m, and set the second lane deviation alarm threshold as the distance between the outside of the front right wheel of the vehicle under test and the inside of the right lane line being less than 0.3m.

[0102] Since the system is built based on the method, it also has the advantage of improving the road accuracy of the lane deviation pre-warning system in actual application, and effectively reduces the evaluation cost.

[0103] The embodiment also provides an electronic device. As shown in Figure 7As shown, it comprises at least one processor, the processor is coupled with a memory, the memory stores a computer program, the computer program is configured to be executed by the processor to perform the above method.

[0104] The embodiment also provides a computer readable storage medium, which stores a computer program for performing the above method.

[0105] Although the present application has been disclosed with the preferred embodiments as above, it is not intended to limit the present application. Those skilled in the art can make various modifications and improvements without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application should be subject to the scope defined by the claims.

Claims

1. A road accuracy evaluation method for a lane departure warning, characterized by, The application comprises the following steps: installing a first camera on the left front wheel of the vehicle to obtain first video information from the left front wheel to the left lane line, installing a second camera on the right front wheel of the vehicle to obtain second video information from the right front wheel to the right lane line, and installing a third camera on the front windshield of the vehicle to obtain third video information of the vehicle driving; calibrating the first camera based on a calibration software, taking the tangent point of the left front wheel and the ground as the origin, and extending outward perpendicularly to the left front wheel by a first length, a second length and a third length as the reference points; meanwhile, calibrating the second camera based on the tangent point of the right front wheel and the ground as the origin, and extending outward perpendicularly to the right front wheel by a first length, a second length and a third length as the reference points; activating the lane departure warning system of the vehicle to be evaluated, and setting the lane departure warning threshold; judging whether to record an alarm event when the lane departure warning is triggered in the actual road driving of the vehicle to be evaluated, and the distance from the left front wheel to the left lane line obtained based on the first camera is less than the preset warning distance or the distance from the right front wheel to the right lane line obtained based on the second camera is less than the preset warning distance; judging whether to record a false alarm event when the lane departure warning is triggered, and the distance from the left front wheel to the left lane line obtained based on the first camera is greater than the preset warning distance or the distance from the right front wheel to the right lane line obtained based on the second camera is greater than the preset warning distance; judging whether to record a missed alarm event when the distance from the left front wheel to the left lane line obtained based on the first camera is less than the preset warning distance or the distance from the right front wheel to the right lane line obtained based on the second camera is less than the preset warning distance, and the lane departure warning is not triggered; judging whether the driving mileage of the vehicle to be evaluated in the actual road driving reaches the preset evaluation driving mileage, and obtaining the road accuracy of the vehicle to be evaluated based on the statistical results of the alarm event, the false alarm event and the missed alarm event.

2. The road accuracy evaluation method for a lane departure warning according to claim 1, characterized in that, Before the steps of activating the lane departure warning system of the vehicle to be evaluated, and setting the lane departure warning threshold, the application comprises the following steps: re-calibrating the first camera and the second camera when the shooting error of the first camera and the second camera after calibration is greater than the error threshold.

3. The road accuracy evaluation method for a lane departure warning according to claim 1, characterized in that, After the step of recording an alarm event, the application comprises the following steps: sending warning information to the operation panel of the driving area to remind the driver to adopt the corresponding operation instruction to make the vehicle turn to a position greater than the lane departure warning threshold; judging whether the vehicle to be evaluated receives the operation instruction feedback of the driver within the preset time period after the sending time of the warning information, and sending a proactive control instruction to the vehicle chassis system to make the vehicle to be evaluated turn to a position greater than the lane departure warning threshold.

4. The road accuracy evaluation method for a lane departure warning according to claim 1, characterized by, The application comprises the following steps: a curve is plotted based on all the false alarm events, the missed alarm events and their time stamps; wherein the time points when the vehicle to be tested is actually driving on the road are taken as the horizontal coordinates, and whether a false alarm event or a missed alarm event occurs at the corresponding time point is taken as the vertical coordinate; wherein the vertical coordinate value when a false alarm event occurs is recorded as 1, and the vertical coordinate value when a missed alarm event occurs is recorded as 2; the lane departure warning system is optimized based on the distribution law of the false alarm events and the missed alarm events in the curve.

5. The road accuracy evaluation method for lane departure warning according to claim 1, characterized in that, the lane departure warning system of the vehicle to be evaluated is activated, and a lane departure alarm threshold is set, comprising: the lane departure warning system of the vehicle to be evaluated is activated, and the whole vehicle CAN information is input into the industrial computer for driving data collection; the first lane departure alarm threshold is set as the distance from the outside of the front left wheel of the vehicle to the inside of the left lane line being less than 0.3m, and the second lane departure alarm threshold is set as the distance from the outside of the front right wheel of the vehicle to the inside of the right lane line being less than 0.3m.

6. A road accuracy assessment system for a lane departure warning, characterized in that comprising: a camera installation module for installing a first camera on the front left wheel of the vehicle to obtain first video information from the outside of the front left wheel to the left lane line, installing a second camera on the front right wheel of the vehicle to obtain second video information from the outside of the front right wheel to the right lane line, and installing a third camera on the front windshield of the vehicle to obtain third video information of the vehicle driving; a camera calibration module for calibrating the first camera based on calibration software, taking the tangent point of the outside of the front left wheel and the ground as the origin, and taking the reference points at the first length, the second length and the third length extending outward perpendicularly to the front left wheel; and calibrating the second camera based on calibration software, taking the tangent point of the outside of the front right wheel and the ground as the origin, and taking the reference points at the first length, the second length and the third length extending outward perpendicularly to the front right wheel; an alarm threshold setting module for activating the lane departure warning system of the vehicle to be evaluated, and setting the lane departure alarm threshold; a first judgment module for recording an alarm event when the lane departure alarm of the vehicle to be evaluated is triggered during actual road driving, and the distance from the outside of the front left wheel to the left lane line based on the first camera is less than the preset warning distance or the distance from the outside of the front right wheel to the right lane line based on the second camera is less than the preset warning distance; a false alarm event is recorded when the lane departure alarm is triggered, and the distance from the outside of the front left wheel to the left lane line based on the first camera is greater than the preset warning distance or the distance from the outside of the front right wheel to the right lane line based on the second camera is greater than the preset warning distance; a missed alarm event is recorded when the distance from the outside of the front left wheel to the left lane line based on the first camera is less than the preset warning distance or the distance from the outside of the front right wheel to the right lane line based on the second camera is less than the preset warning distance, and the lane departure alarm is not triggered. An accuracy rate obtaining module is configured to, when the driving mileage of the vehicle to be evaluated in actual road driving reaches a preset evaluation driving mileage, obtain the road accuracy rate of the vehicle to be evaluated based on the statistical results of the alarm events, the false alarm events and the missed alarm events.

7. The road accuracy assessment system for lane departure warning according to claim 6, characterized in that, The application further discloses a computer readable storage medium. A second judging module is configured to, when the shooting error of the first camera and the second camera after calibration is greater than an error threshold, re-calibrate the first camera and the second camera.

8. The road accuracy assessment system for lane departure warning according to claim 6, characterized in that, The application further discloses a computer readable storage medium. A first sending module is configured to send a pre-warning information to an operation panel in a driving area to remind a driver to adopt a corresponding operation instruction to make the driver turn back to a position greater than a lane deviation pre-warning threshold. A second sending module is configured to, when the vehicle to be measured does not receive the operation instruction feedback of the driver within a preset time period after the sending time of the pre-warning information, send an active control instruction to a vehicle chassis system to make the vehicle to be measured turn back to a position greater than the lane deviation pre-warning threshold.

9. An electronic device, comprising: The computer program is configured to be run by the processor to execute the method in any one of claims 1-5.

10. A computer-readable storage medium, characterized in that, The computer program is configured to be run by the processor to execute the method in any one of claims 1-5.

Images