CN107817018B - Test system and test method for lane line deviation alarm system - Google Patents

Abstract

The invention provides a test system of a lane line deviation alarm system, which comprises a data acquisition device, a data processing device and an interaction device for enabling the data acquisition device and the data processing device to be communicated with each other, wherein the data acquisition device comprises: two cameras respectively mounted on a vehicle body above left and right front wheels of a subject vehicle, the cameras being for obtaining image data including a contact point of a corresponding one of the left and right front wheels with a ground surface and a lane line on a corresponding side; a steering wheel angle sensor and a steering wheel acceleration sensor mounted to a steering wheel of the target vehicle; and an on-board diagnosis system provided for the target vehicle itself for obtaining status information of the target vehicle, the data processing device being configured to obtain a position of a contact point of the corresponding wheel with the ground based on the image data, perform lane line recognition, calculate a lane line width, and a vertical distance between the contact point and the lane line.

Description

Test system and test method for lane departure warning system

technical field

The invention relates to a test system and a test method of a lane line deviation alarm system.

Background technique

With the development of global urbanization and the popularization of automobiles, the transportation problem has been paid more and more attention by people. After analyzing the causes of a large number of fatal traffic accidents, it is found that the casualty accidents caused by the deviation of lane lines caused by subjective factors such as driver fatigue and negligence account for a large proportion. Therefore, a stable intelligent assisted driving system with correct early warning function is developed for the driver-the Lane Line Departure Warning System (LDW system), which obtains the road data ahead through the visual sensor, and combines the driving status of the vehicle such as the speed of the vehicle. And the relevant parameters such as the warning time set by the driver, to judge whether the car has a tendency to deviate from the driving lane. When there is a potential tendency to deviate, a lane departure warning is issued to the driver through image display, sound or vibration, etc., to assist the driver to avoid or reduce lane departure accidents.

However, in order to ensure the reliability of the lane departure warning system, the lane departure warning system needs to be tested and evaluated before use, so that it can timely and accurately warn the driver when the vehicle deviates, and has the lowest possible error. alarm rate.

SUMMARY OF THE INVENTION

An object of the present invention is to provide a test system capable of more accurately testing a lane departure warning system, and a test method using such a test system.

To this end, according to an aspect of the present invention, there is provided a test system for a lane departure warning system, comprising a data acquisition device, a data processing device, and an interaction device for enabling the data acquisition device and the data processing device to communicate with each other, wherein all the The data acquisition device includes: two cameras respectively installed on the vehicle body above the left front wheel and the right front wheel of the target vehicle, and the cameras are used to obtain the corresponding one of the left front wheel and the right front wheel and the ground. Image data including the contact point and the lane line on the corresponding side; the steering wheel angle sensor and the steering wheel acceleration sensor installed on the steering wheel of the target vehicle; and the on-board diagnostic system equipped with the target vehicle itself to obtain the status information of the target vehicle, so The data processing device is configured to obtain, based on the image data, the position of the contact point of the corresponding wheel with the ground, perform lane line recognition, calculate the width of the lane line, and the vertical distance between the contact point and the lane line. The camera of the present invention is installed on the vehicle body above the wheel of the vehicle, and collects the image of the contact point between the wheel and the ground and the lane line on the corresponding side. Compared with the system in the prior art, the installation position of the camera is more convenient Close to the reference point of the system under test, the accuracy rate is higher. In the technical solution of the present invention, the measured parameters include the steering wheel angle and the acceleration signal in addition to the lane line, the parameters of the vehicle itself, such as the vehicle speed, the LDW trigger signal, the lateral acceleration of the vehicle and other vehicle status information, which further improves the test results. reliability.

According to one embodiment, the vehicle state information includes at least one of vehicle speed, LDW trigger signal, and vehicle lateral acceleration.

According to one embodiment, the test system includes a calibration board for calibrating the two cameras. In particular, the calibration plate may be a micron-scale high-precision customized calibration plate. The advantages of the present invention also include providing a camera lens distortion correction step, which overcomes the negative effects of camera lens distortion known in the art, and eliminates camera attitude errors and human installation errors caused by camera installation.

According to one embodiment, the test system includes a power supply for powering the data acquisition device. According to one embodiment, the power source is an on-board power source or an external power source. Any other form of power supply can be provided.

According to one embodiment, the data processing device comprises a first data processing device and a second data processing device which are independent of each other and communicate with each other, wherein the calculation of the test results of the lane departure warning system is performed in the second data processing device. The data processing process and the data acquisition process, which consumes huge resources, are separated and executed on different data processing devices, which not only provides the data processing speed, but also realizes the real-time processing and real-time display of the data, and does not affect the data acquisition process. .

According to one embodiment, the testing system includes a memory for storing data collected from the data acquisition device and/or data calculated from the data processing device. The collected raw data and calculated data are stored for later use, which makes it possible to replay the data and generate test reports in a delayed manner, and provides data support for research and analysis on related topics and fields.

According to one embodiment, the reference error of the lane width is obtained by comparing the lane width calculated in the data processing device with the actual lane width measured manually.

According to another aspect of the present invention, a method for testing a lane departure warning system is provided, comprising: installing the testing system as described above, the installing step comprising mechanically installing a data acquisition device of the testing system, and electrically connecting the data acquisition device of the testing system through an interactive device. A data acquisition device and a data processing device; calibrate the camera to correct camera lens distortion; perform a test process, including a data acquisition process, a data processing process, and a data storage process; end the test or return to the steps of executing the test process.

According to one embodiment, the data collection process includes obtaining the image data by using the two cameras, obtaining the steering wheel angle and steering wheel acceleration by using the steering wheel angle sensor and the steering wheel acceleration sensor; and obtaining a target vehicle by using the on-board diagnostic system status data.

According to one embodiment, the data processing process includes, based on the image data:

Obtain the position of the contact point between the corresponding wheel and the ground;

Lane line recognition;

Use the calibration image to convert the image coordinate points into world coordinates;

Calculate lane line width; and

Calculate the vertical distance between the contact point and the lane line.

According to one embodiment, the method further includes manually measuring the lane line width, and comparing the manually measured lane line width with the lane line width calculated during data processing to obtain a reference error.

According to one embodiment, the method further comprises selecting the type of lane line prior to performing the data processing of the lane line recognition arrangement.

According to one embodiment, the types of lane lines include at least solid lane lines and dashed lane lines.

According to one embodiment, in the case where the dashed lane line is selected, the data processing process includes deriving the position of the vehicle and the lane line by combining the following: multiple frames of the image data that have been obtained; and each frame of image data is Get the speed and acceleration of the target vehicle at the moment.

According to one embodiment, the data saving process includes saving data obtained during data acquisition and data obtained during data processing.

According to one embodiment, the data processing device includes a first data processing device and a second data processing device, the data processing process is performed in the second data processing device, and the data acquisition process and the step of calibrating the camera are performed in the first data processing device performed in the device.

According to one embodiment, the method further includes the steps of data playback and test report generation.

The test system and test method of the lane departure warning system according to the present invention adopts cameras mounted on the wheels, and adds a step of calibrating the cameras before executing the test, which greatly improves the accuracy of the test results and realizes the real-time processing of data , real-time display, full storage and later backup of favorable results.

Description of drawings

The above and other features and advantages of the present application can be better understood from the preferred embodiments of the present application described below in conjunction with the accompanying drawings, wherein:

1 is a structural block diagram of a test system for a lane departure warning system according to the present invention;

2 is a flowchart of a testing method for a lane departure warning system according to the present invention.

Detailed ways

The test system and test method of the lane departure warning system according to the present invention will be described in detail below with reference to FIG. 1 and FIG. 2 , wherein FIG. 1 is a structural block diagram of the test system, and FIG. 2 is a flowchart of the test method.

According to the present invention, the test method for the lane departure system is firstly installed in the test system 100 according to the present invention shown in FIG. 1 , ie step S12 in FIG. 2 . The installation includes the mechanical installation of the corresponding components in the test system 100 to the target vehicle, as well as the electrical connections between the corresponding components in the test system.

According to the present invention, as shown in FIG. 1 , the test system 100 generally includes a data acquisition device 31 and a data processing device 11 , and an interaction device 21 located between the data acquisition device 31 and the data processing device 11 for interactive communication. The data acquisition device 31 includes an image data acquisition device and a parameter data acquisition device.

Typically, the image data acquisition device may be a camera or any other image acquisition device known in the art. In the present invention, the image data acquisition device includes two cameras 317 and 319, which are respectively installed on the vehicle body just above the two front wheels of the vehicle, and are used to generate at least the corresponding lane line including the corresponding wheel and the corresponding lane beside the wheel. image data inside. Accordingly, the testing system 100 further includes a camera mounting structure for mounting the camera on the vehicle body, and the camera mounting structure may have any suitable form known in the art, which will not be described in detail here.

The parameter data acquisition device first includes a parameter sensor installed on the corresponding part of the vehicle for the purpose of testing of the present invention to obtain relevant parameters, for example, in the present invention, it includes a steering wheel angle sensor 311 for obtaining the steering wheel angle of the vehicle and a Steering wheel acceleration sensor 313 that obtains the acceleration of the steering wheel of the vehicle. The parameter data acquisition device also includes an on-board diagnostic system 315 equipped on the vehicle itself, for example, for acquiring vehicle status information, specifically, the vehicle status information includes, but is not limited to, vehicle speed, LDW trigger signal, vehicle lateral acceleration, and the like. It should be understood by those skilled in the art that the parameter data acquisition device of the present invention is not limited to those listed above, but may also include any other device for obtaining any other desired parameters.

According to the present invention, the interaction device 21 includes a network switch 215 that transmits image data from the image data acquisition device to the data processing device 11 , and an on-board bus communication system 213 that transmits parameter data from the on-board diagnostic system 315 to the data processing device 11 . , and transmit the steering wheel angle and steering wheel acceleration from the steering wheel angle sensor 311 and the steering wheel acceleration sensor 313 to the sensing unit access module 211 of the data processing device 11 .

The data processing device 11 includes a first data processing device and a second data processing device mainly used for image processing. For example, in the present invention, the first data processing device and the second data processing device may be a PC and a processing unit, respectively. However, those skilled in the art should understand that the first data processing apparatus and the second data processing apparatus according to the present invention are obviously not limited to this configuration method.

In this first step S12, the installation of the testing system 100 includes the following mechanical installation: using the camera installation structure to install the above two cameras 317 and 319 on the vehicle body above the left front wheel and the right front wheel, respectively; The acceleration sensor 313 and the steering wheel angle sensor 311 are mounted on the steering wheel of the target vehicle; and the calibration plate 51 is ready to be placed under the camera to be calibrated.

The installation of the test system 100 also includes the following electrical connection operations: electrically connecting the steering wheel angle sensor 311 , the steering wheel acceleration sensor 313 , the on-board diagnostic system 315 and the above two cameras 317 and 319 to the power supply 41 . The power source may be any off-the-shelf on-board power source, such as a cigarette lighter, or any available external additional power source.

The communication between the data processing device 11 and the sensing unit access module 211 and the vehicle bus communication system 213 can be accomplished through a conventional USB interface, while the communication between the data processing device 11 and the network switch 215 is realized through Gigabit Ethernet.

In this step S12, the mechanical installation of the test system to the vehicle body, the communication between the data acquisition device 31 of the test system 100 and the data processing device 11, the placement of the calibration board 51 and other necessary auxiliary installation operations are completed.

Next, step S14 is performed: calibration of the camera to correct the lens distortion of the camera. The calibration of the camera is performed by the calibration plate 51 installed in step S12. Calibration plate 51 may be any type of calibration plate known in the art. As an example, the camera lens parameters can be calibrated using a 20-micron-level high-precision custom calibration board. According to the present invention, the calibration step of the camera realizes the distortion correction function of the camera lens, which makes the installation of the camera easier and more flexible, and only needs to ensure that the wheels and lane lines are within the field of view of the camera lens. This eliminates any human error related to the installation of the camera, so that the image results obtained by the present invention avoid interfering factors with the installation height of the camera, the installation posture of the camera, and the like, so that the image results are more accurate.

After the step S14 of calibrating the camera, the testing method according to the present invention may proceed to S16: Start testing?

If it is confirmed to start the test, the data collection step S18 is executed, which includes sub-step S182: obtaining the target image from the camera; sub-step S184: obtaining the corresponding sensor measurement result from the corresponding sensor; and sub-step S186: CAN card data collection.

The target image obtained in sub-step S182 should at least clearly contain the contact point of the wheel and the ground on the same side of the vehicle as the camera, and the image of the corresponding lane line on the side of the wheel; the data obtained in sub-step S184 should at least include Steering wheel angle and steering wheel acceleration; and the data obtained in sub-step S186 should at least include vehicle speed, lateral acceleration, and LDW trigger signal including trigger or not, trigger time T, etc.

After the above-mentioned data is collected and stored, the testing method according to the present invention proceeds to step S20: an image processing step. Unlike the other steps, this step is carried out in the second data processing device.

The image processing step 20 includes sub-step S202: select the type of lane line; sub-step S204: obtain the position of each wheel and the ground contact point from the image data from each camera; sub-step S206: identify the lane line; sub-step S208: use the calibration image Converting the image coordinates into world coordinates; sub-step S210 : calculating the vertical distance between the contact point of the wheel and the ground and the lane line; and sub-step S212 : calculating the width of the lane line.

As an advantage of the present invention, the testing method of the present invention includes the sub-step S202 of selecting a lane line type, which solves the problem of image recognition of dashed lane lines. Specifically, the lane types may include at least solid lane lines, such as yellow and white solid lane lines, or dashed lane lines, such as yellow and white dashed lane lines. For example, the choice of lane type can be selected by the tester through a human-machine interface, such as through a touch screen, mouse, keyboard, and the like.

If the selected lane line is a solid lane line, the image obtained from the camera always includes the lane line, and the identification is relatively simple. If the dashed lane line is selected, there is a situation where the lane line cannot be found in the image of the camera. At this time, the identification of the lane line is realized by the memory algorithm. Specifically, the memory algorithm includes comprehensively considering the position of the lane line in the coordinate system in the previous frames of the camera image, the speed and acceleration of the target vehicle at the corresponding moment of each frame of the image and other parameters to calculate the motion trajectory of the target vehicle, so as to obtain the target vehicle. Location information of the vehicle and lane lines in the image.

Optionally, the testing method according to the present invention further includes manually measuring the width of the lane line, and comparing the actually measured width of the lane line with the calculated width of the lane line to obtain a reference error of the lane line width.

After the image processing step S20 is completed, the result storage step S22 is performed. The stored results include the data collected in step S18 and the data calculated in step S20.

Step S22: Stop the test? If it stops, go to the end step S24, and if it needs to re-test, go back to the step S18.

As mentioned above, according to the test system and test method of the present invention, because the camera is installed above the front wheel of the car, and the wheel is used as the measurement target, the contact point between the wheel and the ground is directly obtained, which is different from the camera installed on the front of the car in the prior art. Compared with measuring the distance between the camera installation point and the lane line, the accuracy rate is higher, and it is closer to the reference point of the LDW function.

In addition, according to the test system of the present invention, the parameters used not only include the position of the camera installation point, but also need to measure the steering wheel angle, steering wheel acceleration and other data. There are many physical quantities used for measurement as the reference point of the LDW function, which improves the test results. reliability of results.

According to the present invention, the step of performing camera calibration before starting the test makes the test of the present invention not affected by the focal length of the camera lens and the installation posture of the camera. Based on the known distances between physical points on the high-precision calibration board, the vertical distance between the lane line and the wheel touchdown point can be calculated in real time. The target value can be easily calculated using the calibrated camera lens parameters using the calibration board.

According to the present invention, the collection of data (including image data and parameter data), the storage of the collected data, and the calibration of camera lens parameters are performed in the first data processing device. The image processing step 20, which is computationally complex, requires large-capacity storage and high computing power, and thus requires higher configuration, is performed in the second data processing device. The second data processing device is independent of the first data processing device, enabling real-time calculation and optional real-time display of the data collected in the first data processing device (including image data and parameter data), and very advantageously, It does not affect the next round of data collection in the first data processing device.

Optionally, the data processing apparatus according to the present invention, ie at least one or both of the first data processing apparatus and the second data processing apparatus, includes a large-capacity memory for storing data in step S22. Optionally, external storage can be provided if necessary.

Further, since the test system of the present invention realizes real-time calculation, the data collected or obtained by technology in each stage can be effectively stored, which makes it possible to extract or return the stored data after the test process is over. , for follow-up further research or later to form a test report.

The above has been described in terms of various embodiments of the invention, but the invention is not limited to the embodiments described above and illustrated in the drawings. Features described in relation to one embodiment are equally applicable to other embodiments of the invention, and features of different embodiments can be combined with each other to form new embodiments. Various modifications and variations of the above-described embodiments may be made by those skilled in the art without departing from the spirit and scope defined by the following claims.

Claims (8)

1. A method for testing a lane line deviation warning system, the system comprising a data acquisition device, a data processing device, and an interactive device that enables the data acquisition device and the data processing device to communicate with each other, wherein the data acquisition device comprises: Two cameras installed on the vehicle body above the left and right front wheels of the target vehicle respectively, the cameras are used to obtain the contact point of the corresponding one of the left and right front wheels with the ground and the corresponding side The image data including the lane lines of the target vehicle; the steering wheel angle sensor and the steering wheel acceleration sensor installed on the steering wheel of the target vehicle; and the on-board diagnostic system equipped by the target vehicle itself, which is used to obtain the status information of the target vehicle, wherein the system also includes a memory , used to store the data collected from the data acquisition device and the data calculated from the data processing device, the method includes the steps of: mechanically installing the data acquisition device of the test system, and electrically connecting the data acquisition device of the test system through the interactive device device and data processing device; calibrate the camera of the test system to perform camera lens distortion correction; execute the test process, including the data acquisition process, the data processing process, and the data storage process; end the test or return to the step of executing the test process, wherein , the data collection process includes using the two cameras to obtain the image data, using the steering wheel angle sensor and the steering wheel acceleration sensor to obtain the steering wheel angle and steering wheel acceleration; and using the on-board diagnostic system to obtain the state data of the target vehicle, Wherein, the data processing process includes: based on the image data: obtaining the position of the contact point between the corresponding wheel and the ground; selecting the lane line type and lane line recognition; using the calibration image to convert the image coordinate points into world coordinates; calculating the lane line width; and calculating the vertical distance between the contact point and the lane line; and when the result of lane line recognition is a dashed lane line, the position of the dashed lane line in the coordinate system in the previous frames of camera images can be comprehensively considered , The speed and acceleration of the target vehicle at the corresponding moment of each frame of image are calculated to calculate the motion trajectory of the target vehicle and obtain the position of the vehicle and the dashed lane line, wherein the data storage process includes saving the data obtained in the data collection process and in the data processing. The data obtained during the process is used for data playback and test report generation. 2. The method of claim 1, wherein the state information includes at least one of a vehicle speed of the target vehicle, an LDW trigger signal, and a lateral acceleration of the target vehicle. 3. The method of claim 1, wherein the system includes a calibration plate for the calibration operation. 4. The method of claim 3, wherein the calibration plate is a micron-scale high precision custom calibration plate. 5. The method of claim 1, wherein the system includes a power source for powering the data acquisition device. 6. The method of claim 5, wherein the power source is an on-board power source or a power source additionally mounted to the vehicle. 7. The method according to any one of claims 1-6, wherein the data processing device comprises a first data processing device and a second data processing device independent of each other and in communication with each other, wherein the lane departure warning is calculated The test results of the system are carried out in the second data processing device. 8. The method according to any one of claims 1-6, wherein the method further comprises manually measuring the width of the lane line, and comparing the width of the lane line measured manually with the lane width calculated in the data processing process The line width is compared to obtain the reference error of the lane line width.

Images