Lane departure warning system safe operation key parameter testing method and device

Abstract

The present invention provides a method and device for testing key parameters for safe operation of a lane departure warning system, including: using a preset simulation algorithm to simulate a lane departure warning system and build a simulation scene; based on the simulated lane departure warning system and the simulation scene, selecting corresponding key parameters to be tested for testing according to a pre-selected test category through a test category-key parameter mapping relationship, setting different preset values ​​for the key parameters to be tested, performing lane departure warning simulation according to the preset values, and obtaining key parameter-related data of the test vehicle in the current driving state; analyzing the key parameter-related data to obtain the safety threshold boundary of the key parameter. The present invention tests the key parameters for safe operation of a lane departure warning system through a simulation algorithm, and calculates the safety threshold boundary of the key parameters through scene simulation, thereby contributing to a lane departure warning system with higher interpretability.

Description

Technical Field

[0001] The present invention relates to the field of assisted driving technology, and in particular to a method and device for testing key parameters for safe operation of a lane departure warning system. Background Art

[0002] According to statistics, unconscious lane departure caused by driver fatigue, sleepiness or negligence is the main cause of traffic accidents on highways. Lane Departure Warning System (LDWS) is a system that assists drivers to avoid or reduce traffic accidents caused by lane departure through alarms. It is an important part of the advanced driver assistance system. It can issue an alarm before the vehicle unconsciously deviates from the original lane, providing the driver with more reaction time and greatly reducing collision accidents caused by lane departure.

[0003] LDWS can sound an alarm before the vehicle deviates from the original lane unconsciously (the driver does not turn on the turn signal) when the speed exceeds a certain level. Specifically, LDWS detects lane lines in real time and estimates the deviation based on the steering wheel direction, vehicle speed, and the angle between the vehicle and the lane. If the deviation is greater than a threshold, an alarm will be sounded to remind the driver. This can not only assist the driver to effectively avoid accidents caused by the vehicle deviating from the lane and improve the driving safety of the vehicle, but also reduce the driver's operating burden and improve driving comfort. When the driver causes the vehicle to deviate from the lane due to operating errors, lack of concentration or physical fatigue, traffic accidents can be effectively avoided.

[0004] At present, when developing existing lane departure warning systems, general values ​​are usually used for the design of key parameters, the vehicle driving safety boundaries of key parameters are unknown, and the specific impact of specific key parameters on the performance of lane departure warning systems is not understood, resulting in low interpretability. Therefore, it is necessary to test the key parameters for safe operation of lane departure warning systems, so as to obtain the vehicle driving safety boundaries related to key parameters, clarify the impact caused by key parameters, and improve the interpretability of the developed warning system. Summary of the invention

[0005] The present invention provides a method and device for testing key parameters for safe operation of a lane departure warning system, which are used to solve the defects in the prior art and realize the calculation of the vehicle driving safety boundary related to key parameters, thereby obtaining a lane departure warning system with higher interpretability.

[0006] The present invention provides a method for testing key parameters of safe operation of a lane departure warning system, comprising:

[0007] Using a preset simulation algorithm to simulate a lane departure warning system and build a simulation scene; wherein the simulation scene at least includes a camera, a test vehicle, and a test road;

[0008] Based on the simulated lane departure warning system and the simulation scenario, the corresponding key parameters to be tested are selected for testing according to the pre-selected test category through the test category-key parameter mapping relationship, different preset values ​​are set for the key parameters to be tested, and lane departure warning simulation is performed according to the preset values ​​to obtain key parameter-related data of the test vehicle in the current driving state; wherein the key parameters to be tested include at least one of resolution, delay, sampling frame rate, and time packet loss rate, and the test category includes perception output accuracy test and quantization test;

[0009] The data related to the key parameters are analyzed to obtain the safety threshold boundaries of the key parameters.

[0010] According to a method for testing key parameters for safe operation of a lane departure warning system provided by the present invention, when the test category is a quantitative test and the key parameter to be tested is one of delay, time packet loss rate and resolution, the method based on the simulated lane departure warning system and the simulation scenario selects the corresponding key parameter to be tested for testing according to the pre-selected test category through a mapping relationship between the test category and the key parameter to be tested, sets different preset values ​​for the key parameter to be tested, performs lane departure warning simulation according to the preset values, and obtains key parameter-related data of the test vehicle in the current driving state, specifically including:

[0011] Based on the simulated lane departure warning system and the simulation scenario, a non-key parameter to be tested is set to a fixed value, and a lane departure warning simulation is performed under different preset values ​​of the key parameter to be tested, and a vehicle warning starting point under each preset value is obtained as the key parameter related data;

[0012] Among them, the vehicle warning starting point is the distance between the estimated trajectory point of the test vehicle and the lane line when the warning is issued.

[0013] According to a method for testing key parameters for safe operation of a lane departure warning system provided by the present invention, when the test category is a perception accuracy test and the key parameter to be tested is a resolution, the method is based on the simulated lane departure warning system and the simulation scenario, and according to a pre-selected test category, a corresponding key parameter to be tested is selected for testing through a mapping relationship between the test category and the key parameter to be tested, different preset values ​​are set for the key parameter to be tested, and a lane departure warning simulation is performed according to the preset values, so as to obtain key parameter-related data of the test vehicle in the current driving state, specifically including:

[0014] Adding a preset sensor to the simulation scene; wherein the preset sensor is used to detect the actual distance from the estimated motion trajectory point of the test vehicle to the lane line;

[0015] Based on the simulated lane departure warning system and the simulation scenario, the sampling frame rate is set to a fixed value, and lane departure warning simulation is performed at different resolution preset values, and the detection distance and actual distance at each resolution are obtained as key parameter related data; wherein the detection distance is the lateral distance output by the simulated lane departure warning system.

[0016] According to a method for testing key parameters for safe operation of a lane departure warning system provided by the present invention, analyzing the key parameter-related data to obtain the safety threshold boundary of the key parameter specifically includes:

[0017] Using the vehicle warning starting point as a measurement standard, drawing a three-dimensional analysis diagram of the key parameters to be measured and the vehicle warning starting point;

[0018] The safety threshold boundary is obtained according to the three-dimensional analysis graph.

[0019] According to a method for testing key parameters of safe operation of a lane departure warning system provided by the present invention, the lane departure warning system comprises a road video pre-processing module, a lane line detection module, a lane line tracking module, a departure warning module and a warning information post-processing module;

[0020] The road video pre-processing module is used to perform grayscale processing and threshold processing on the road image acquired by the camera to obtain a grayscale image and a binary image;

[0021] The lane line detection module is used to extract geometric features of the road boundary of the test road according to the grayscale image and the binarization image to obtain the current lane line;

[0022] The lane line tracking module is used to input the current lane line into a filter to obtain a lane estimation value, and replace the current lane line with the lane estimation value;

[0023] The deviation warning module is used to estimate the estimated motion trajectory point according to the dynamic parameters of the test vehicle in the current driving state, calculate the lateral distance from the estimated motion trajectory point to the boundary of the current lane line, compare the lateral distance with a preset safety threshold, obtain deviation information, and perform a deviation warning according to the deviation information;

[0024] The warning information post-processing module is used to visualize the current lane line and the deviation information, and output them to an oscilloscope or a video port for real-time observation.

[0025] According to a method for testing key parameters of safe operation of a lane departure warning system provided by the present invention, the lane departure warning system is simulated by using a preset simulation algorithm and a simulation scene is built, specifically comprising:

[0026] Use Matlab or Simulink to simulate the lane departure warning system and use Prescan to build the simulation scenario;

[0027] The test road includes a straight road and a curved road, and the visible lane markings on the road surface of the test road comply with the provisions of GB5768.

[0028] The present invention also provides a lane departure warning system safe operation key parameter testing device, comprising:

[0029] An algorithm building unit, used to simulate the lane departure warning system using a preset simulation algorithm and build a simulation scene; wherein the simulation scene at least includes a camera, a test vehicle, and a test road;

[0030] A simulation test unit, for selecting corresponding key parameters to be tested for testing based on the simulated lane departure warning system and the simulation scenario according to a pre-selected test category through a test category-key parameter mapping relationship, setting different preset values ​​for the key parameters to be tested, performing lane departure warning simulation according to the preset values, and obtaining key parameter-related data of the test vehicle in the current driving state; wherein the key parameters to be tested include at least one of resolution, latency, sampling frame rate, and time packet loss rate, and the test category includes perception output accuracy test and quantization test;

[0031] The analysis result unit is used to analyze the key parameter related data to obtain the safety threshold boundary of the key parameter.

[0032] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for testing key parameters for safe operation of a lane departure warning system as described in any one of the above is implemented.

[0033] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for testing key parameters for safe operation of a lane departure warning system.

[0034] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for testing key parameters for safe operation of a lane departure warning system.

[0035] The lane departure warning system safety operation key parameter testing method and device provided by the present invention simulates the lane departure warning system and builds a simulation scene by using a preset simulation algorithm; wherein the simulation scene at least includes a camera, a test vehicle and a test road; based on the simulated lane departure warning system and the simulation scene, the corresponding key parameter to be tested is selected for testing according to the pre-selected test category through the test category-key parameter mapping relationship, different preset values ​​are set for the key parameter to be tested, and lane departure warning simulation is performed according to the preset value to obtain the key parameter related data of the test vehicle in the current driving state; wherein the key parameter to be tested includes at least one of resolution, delay, sampling frame rate, and time packet loss rate, and the test category includes perception output accuracy test and quantization test; the key parameter related data is analyzed to obtain the safety threshold boundary of the key parameter. The present invention tests the key parameters of the safe operation of the lane departure warning system through a simulation algorithm, and calculates the safety threshold boundary of the key parameters through scene simulation, thereby contributing to a lane departure warning system with higher explanatory power. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 This is one of the flow charts of the key parameter testing method for safe operation of the lane departure warning system provided by the present invention;

[0038] Figure 2 This is the second flow chart of the key parameter testing method for safe operation of the lane departure warning system provided by the present invention;

[0039] Figure 3 It is a schematic diagram of the Hough transform image space and parameter space of an embodiment of the key parameters for safe operation of the lane departure warning system provided by the present invention;

[0040] Figure 4 This is a flow chart of the Hough algorithm of an embodiment of the key parameters for safe operation of the lane departure warning system provided by the present invention.

[0041] Figure 5 This is the third flow chart of the key parameter testing method for safe operation of the lane departure warning system provided by the present invention;

[0042] Figure 6It is a schematic diagram of a lane line tracking algorithm flow chart of an embodiment of a method for testing key parameters for safe operation of a lane departure warning system provided by the present invention;

[0043] Figure 7 1. It is a schematic diagram of lane line detection according to an embodiment of a method for testing key parameters for safe operation of a lane departure warning system provided by the present invention;

[0044] Figure 8 It is a real-time data graph at different resolutions of an embodiment of a method for testing key parameters for safe operation of a lane departure warning system provided by the present invention;

[0045] Fig. 9 It is a schematic diagram of warning starting points under different time delays and sampling frame rates in a straight road scene according to an embodiment of a method for testing key parameters for safe operation of a lane departure warning system provided by the present invention;

[0046] Fig.10 1. It is a schematic diagram of packet loss of an embodiment of a method for testing key parameters for safe operation of a lane departure warning system provided by the present invention;

[0047] Fig.11 It is a schematic diagram of warning starting points under different packet loss-sampling frame rates in a straight road scene according to an embodiment of a method for testing key parameters for safe operation of a lane departure warning system provided by the present invention;

[0048] Fig.12 It is a schematic diagram of warning starting points under different resolutions and sampling frame rates in a straight road scene according to an embodiment of a method for testing key parameters for safe operation of a lane departure warning system provided by the present invention;

[0049] Fig.13 It is a schematic diagram of warning starting points under different delays and sampling frame rates for a curved road scene with a curvature radius of 200m according to an embodiment of a method for testing key parameters for safe operation of a lane departure warning system provided by the present invention;

[0050] Fig.14 A schematic diagram of a warning starting point under different packet loss-sampling frame rates for a curved road scene with a curvature radius of 200m according to an embodiment of a method for testing key parameters for safe operation of a lane departure warning system provided by the present invention;

[0051] Fig.15 A schematic diagram of a warning starting point at different resolutions and sampling frame rates for a curved road scene with a curvature radius of 200m according to an embodiment of a method for testing key parameters for safe operation of a lane departure warning system provided by the present invention;

[0052] Fig.16A schematic diagram of the warning starting point under different delays and sampling frame rates for a curved road scene with a curvature radius of 400m according to an embodiment of a method for testing key parameters for safe operation of a lane departure warning system provided by the present invention;

[0053] Fig.17 A schematic diagram of a warning starting point under different packet loss-sampling frame rates for a curved road scene with a curvature radius of 400m according to an embodiment of a method for testing key parameters for safe operation of a lane departure warning system provided by the present invention;

[0054] Fig.18 A schematic diagram of a warning starting point at different resolutions and sampling frame rates for a curved road scene with a curvature radius of 400m according to an embodiment of a method for testing key parameters for safe operation of a lane departure warning system provided by the present invention;

[0055] Fig.19 It is a structural schematic diagram of a key parameter testing device for safe operation of a lane departure warning system provided by the present invention;

[0056] Fig. 20 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] Combine the following Figure 1-Figure 18 Describe the key parameters testing method for safe operation of the lane departure warning system of the present invention, Figure 1 FIG. 1 is one of the flow charts of the key parameter testing method for safe operation of the lane departure warning system provided by the present invention, such as Figure 1 As shown, the method includes:

[0059] Step 110: Use a preset simulation algorithm to simulate the lane departure warning system and build a simulation scene; wherein the simulation scene at least includes a camera, a test vehicle, and a test road.

[0060] It should be noted that the present invention is described using a lane departure warning system (LDWS) as an example, but this does not represent a limitation to the present invention. The lane departure warning system safe operation key parameter testing method provided by the present invention can be extended to the safe operation key parameter testing of any lane departure warning system.

[0061] The lane departure warning system (LDWS) mentioned in the embodiment of the present invention can obtain a lane image through a camera, and detect the distance between the lane lines on both sides through a lane line detection algorithm to determine whether the distance between the vehicle and the lane line is lower than a threshold. When the system determines that there is a deviation, the system should immediately issue a lane departure warning message and remind the driver.

[0062] Specifically, the fundamental purpose of the present invention is to propose the requirements of key indicators such as quantization, perception output accuracy and variance caused by key parameters of perception coding and decoding for vehicle driving safety boundaries. In some embodiments, the key parameters include latency, packet loss, resolution and bandwidth.

[0063] During the specific implementation process, based on the "Performance Requirements and Test Methods for Lane Departure Warning Systems for Intelligent Transport Systems" or the "Test Procedures for Autonomous Driving Functions of Intelligent Connected Vehicles" (Trial) formulated by the International Organization for Standardization (ISO) or the National Standard of the People's Republic of China (GB / T), in a simulation environment, the lane departure warning system is tested and analyzed for its safe working boundaries under the influence of key indicators such as delay / packet loss, quantification caused by resolution and bandwidth, and perception output accuracy and variance. A target perception model based on the detection method is established to obtain quantitative analysis results of key indicators.

[0064] Furthermore, the lane departure warning system is first explained: the lane departure warning system can obtain the lane image through the camera, and detect the distance between the lane lines on both sides through the lane line detection algorithm to determine whether the lateral distance between the vehicle and the lane line is lower than the threshold, and evaluate whether the vehicle's current driving state has the possibility of lane departure through the lane departure warning algorithm, and issue a warning when the system feels it is dangerous, and finally provide a warning signal to the driver through the display device; when the warning conditions are not met, the system should not have a false alarm; the warning system should be able to detect lane lines under different lighting conditions.

[0065] In order to simulate the lane departure warning system, a preset simulation algorithm is used for simulation, and the lane departure warning algorithm in the lane departure warning system is designed on the simulation platform, so as to realize the solidification of the lane departure warning algorithm on the hardware processing platform, which is used to process the data obtained by the camera to simulate the warning process. In other words, the overall simulation device includes an image acquisition sensor (camera), a hardware processing platform (solidified lane departure warning algorithm for simulating the lane departure warning system). In some embodiments, the simulation device also includes and warning signal display device.

[0066] In addition, a preset simulation algorithm is required to simulate the lane departure scenario, including the simulation of the camera, test vehicle and test road.

[0067] In some embodiments, simulating the lane departure warning system using a preset simulation algorithm and building a simulation scenario specifically includes:

[0068] Use Matlab or Simulink to simulate the lane departure warning system and use Prescan to build the simulation scenario;

[0069] The test road includes a straight road and a curved road, and the visible lane markings on the road surface of the test road comply with the provisions of GB5768.

[0070] Specifically, in this embodiment, the simulation experiment adopts Matlab\Simulink (2019 version) and Prescan (8.5.0 version) for joint simulation, and the lane departure warning algorithm design is realized by Matlab\Simulink, and the scenario design is realized by Prescan.

[0071] In a specific embodiment, when prescan builds a scene, Audi_A8_1 vehicle and camera are mainly used, wherein the parameters of the vehicle and the camera can be designed according to actual conditions, and the embodiment of the present invention does not limit this. The camera is mainly used to collect image data.

[0072] Furthermore, for the sensors needed in subsequent tests, the design is implemented through Prescan. In a specific embodiment, the sensor adopts LaneMarkerSensor. It can be understood that LaneMarkerSensor is an ideal sensor, which is mainly used to detect the actual distance between the vehicle and the lane line and the actual distance to the estimated point, so as to compare with the lane line detection of this experiment and record the actual warning starting point of each test.

[0073] In addition, for the test road, it should be emphasized that in order to increase the understanding of key parameters, the present invention does not impose specific restrictions on the conditions of the test road, but in order to be consistent with reality and increase the reference value of the test results, the visible lane markings on the road surface comply with the provisions of GB5768 and include both straight road scenes and curved road scenes.

[0074] In a specific embodiment, specific parameters of the straight road scene include: the length of the straight road is about 200m; the visible lane markings on the test road surface comply with the provisions of GB5768; the vehicle is located in the center of the lane at the beginning of the test, and the vehicle deviates to the left once after entering the test lane, and then deviates to the right once.

[0075] In a specific embodiment, the specific parameters of the curved road scene include: the length of the curve is 100m; the visible lane markings on the test road surface comply with the provisions of GB5768; the vehicle should be basically in the center of the lane at the beginning of the test, and when the vehicle enters the test lane for tracking and reaches a stable state, the vehicle can gradually deviate to the outside of the curve, and tests are conducted on curves with curvature radii of 200m and 400m respectively.

[0076] Furthermore, in order to increase the universality of the test results, in some embodiments, the conditions of the roads in most real situations are used as a reference, and the test road is set to an asphalt or concrete pavement on a dry platform by adjusting the parameters of the simulation platform; the horizontal visibility is greater than 1 km; the temperature is in the range of -20-40 degrees Celsius, and the test is carried out under daylight conditions.

[0077] Step 120: Based on the simulated lane departure warning system and the simulation scenario, select corresponding key parameters to be tested for testing according to a pre-selected test category through a test category-key parameter mapping relationship, set different preset values ​​for the key parameters to be tested, perform lane departure warning simulation according to the preset values, and obtain key parameter related data of the test vehicle in the current driving state; wherein the key parameters to be tested include at least one of resolution, delay, sampling frame rate, and time packet loss rate, and the test categories include perception output accuracy test and quantization test.

[0078] First, based on the constructed simulation scenario and the lane departure warning system simulated by the algorithm, different preset values ​​of the key parameters to be tested are set to simulate the entire process of lane departure warning.

[0079] Specifically, the simulation of the entire lane departure warning process includes: LDWS first obtains real-time road images during vehicle driving through image sensors (cameras), and then the algorithm solidified on the hardware processing platform (simulating lane departure warning system) extracts the geometric features of the road and the dynamic parameters of the vehicle (distance and speed), and then uses the lane departure warning algorithm to evaluate whether the vehicle's current driving state has the possibility of lane departure. When the vehicle's lateral distance exceeds the preset threshold, a warning signal is actively issued, and finally a warning signal is provided to the driver through the display device.

[0080] In some embodiments, the lane departure warning system includes a road video pre-processing module, a lane line detection module, a lane line tracking module, a departure warning module, and a warning information post-processing module;

[0081] The road video pre-processing module is used to perform grayscale processing and threshold processing on the road image acquired by the camera to obtain a grayscale image and a binary image;

[0082] The lane line detection module is used to extract geometric features of the road boundary of the test road according to the grayscale image and the binarization image to obtain the current lane line;

[0083] The lane line tracking module is used to input the current lane line into a filter to obtain a lane estimation value, and replace the current lane line with the lane estimation value;

[0084] The deviation warning module is used to estimate the estimated motion trajectory point according to the dynamic parameters of the test vehicle in the current driving state, calculate the lateral distance from the estimated motion trajectory point to the boundary of the current lane line, compare the lateral distance with a preset safety threshold, obtain deviation information, and perform a deviation warning according to the deviation information;

[0085] The warning information post-processing module is used to visualize the current lane line and the deviation information, and output them to an oscilloscope or a video port for real-time observation.

[0086] Specifically, the information collection part first collects the relative position relationship between the vehicle and the lane line through the on-board camera and sensors, and then the decision-making part analyzes the information collected by the sensor to determine whether the lateral offset of the vehicle is within the normal range. If the lateral offset of the vehicle exceeds the preset deviation threshold, the control part will issue a warning to the driver.

[0087] For each module, Figure 2 FIG. 1 is a schematic diagram of a process flow of a lane departure warning system simulated by an embodiment of the present invention. Figure 2 As shown, the information collection part is completed by a camera, and this embodiment will not be elaborated here. It can be understood that in the lane departure warning system, a vehicle-mounted monocular camera is generally used, and the video image input by the vehicle-mounted monocular camera is an M×N×3 color image array, also known as an RGB image. Naturally, it should be pointed out that for the convenience of description, the embodiment of the present invention adopts the setting of a monocular camera for illustration, which does not mean a limitation of the present invention. The key parameter test method for safe operation of the lane departure warning system provided by the present invention can be simulated with any camera. In some embodiments, the camera provided by Prescan is used to acquire road images. It should be pointed out that the camera can adjust the resolution, installation position, sampling frame rate, etc. to meet the test requirements.

[0088] The decision-making part includes video pre-processing module, lane line detection module and lane line tracking module.

[0089] In the video pre-processing module, two types of images are processed to meet subsequent functional requirements, namely grayscale images and binary images. The grayscale image can be obtained by grayscale processing the road image obtained by the camera, and the binary image can be obtained by threshold processing the road image obtained by the camera.

[0090] It can be understood that the threshold processing of an image refers to: turning the image pixels into an image with only (0 and 1), at which time an image with obvious black and white effect can be obtained. Grayscale images and binary images are used for lane line detection and recognition.

[0091] It should be noted that the present invention does not limit the specific methods of grayscale processing and binarization processing, and any method can be used in actual operation.

[0092] In the lane detection module, the lane mathematical model is first selected. The lane mathematical model is determined by analyzing the basic shape of the road, and the lane is estimated by calculating its parameters. Currently, the commonly used lane detection models are mainly the following: straight line, curve and complex model.

[0093] In a straight road scene, the lane line is usually a straight line. This embodiment uses a straight line model for illustration. The straight line model is the most commonly used model in the road model because its algorithm structure is simple, the amount of calculation is relatively small, and the effectiveness is very strong. Its basic principle is: by calculating the relevant parameters of the straight line model, the detection of the road boundary line is constrained because its detection accuracy is very high. However, the actual road lines are not all standard straight lines, but when the vehicle is running at a slow speed or in the close view of the road image, the road line can be approximately represented by a straight line model. Its mathematical expression can be expressed by the following formula:

[0094] y=kx+b

[0095] Where x and y are the horizontal and vertical coordinates of the image, k is the slope of the line, and b is the intercept of the line.

[0096] In order to extract the straight line geometric features and construct the straight line model of the lane line, the lane line detection module uses a straight line detection algorithm to determine the lane line. In some embodiments, the Hough algorithm is used to find the straight lane line in the image. At this time, since the left and right lane lines are mapped as two straight lines that intersect at the front point in the monocular camera, they can be detected by the Hough algorithm. The biggest advantage of the Hough transform to extract lane lines is that it is not affected by some factors such as straight line gaps and noise. The Hough transform has the following steps: cumulative statistics, peak location, threshold selection and verification.

[0097] Specifically, two coordinate systems are given in the Hough transform, namely the image coordinate system and the parameter coordinate system. Through a dual relationship between the two spaces, the points in the image coordinate system are mapped to the straight lines in the parameter coordinate system, and finally the straight lines are identified, such as Figure 3 (a) is the image space, and (b) is the parameter space. The basic principle is that the line correspondence in the image coordinate system is a set of multiple lines intersecting at one point in the parameter coordinate system. By calculating the peak value in the parameter coordinate system, the coordinates of the target line are obtained, and then the image coordinate system is returned through the dual relationship. Finally, the corresponding parameters of the desired line are obtained, and the detection of the current lane line in the image is completed.

[0098] Furthermore, if the line is perpendicular to the x-axis, the slope of K will be close to infinity, which is not conducive to the next step of calculation. To solve this kind of problem, the parameter space of the Hough transform is usually a polar coordinate space, and the dual relationship between its points and lines is shown as follows:

[0099] p=xcosθ+ysinθ

[0100] Where p is the polar diameter and θ is the polar angle. Assuming that the coordinates of a point in the image coordinate system are (x0, y0), then:

[0101]

[0102] After using polar coordinates, no matter how the slope and intercept of the line are changed, the values ​​of p and θ are within a certain range. Through the dual relationship, the pixel points in the image coordinate system can be mapped to the parameter coordinate system to obtain a set of sine curves. When this set of curves has an intersection, the point is the target line to be detected in the image coordinate system. Its implementation form is as follows: Figure 4 shown.

[0103] In the lane tracking module, it is understood that the lane tracking module is designed to improve the accuracy of lane recognition. Without the lane tracking module, the vibration of the vehicle body during driving, the change of light brightness, etc. will cause the collected image to jump, or due to special reasons such as damaged lane markings and dirty road surface, one or several frames of images will not be able to recognize the lane line at all, so the lane departure warning will be inaccurate, resulting in false alarms or missed alarms. Figure 5This is a schematic diagram of the framework flow of the lane line tracking module. Specifically, the target tracking method is adopted, and the multiple frames of lane information that have been detected are used as samples to input the filter. The optimal estimated value output by the filter is used to replace the current observation value. This will make the image detection result more stable, and there will be no problems such as false alarms caused by drastic fluctuations in the detection results of adjacent frames. Therefore, the use of the filter algorithm to track the lane line can greatly improve the stability and anti-interference of the system. In one embodiment, the Kalman filter is used to determine the lane estimation value. The specific implementation process is as follows: Figure 6 shown.

[0104] Furthermore, the control part includes a deviation warning module and a warning information post-processing module.

[0105] As for the departure warning module, it can be understood that in the prior art, the commonly used lane departure warning algorithms include a warning model based on the current position (CCP model), a warning model based on the future deviation amount (FOD model), a warning model based on the time when the vehicle will cross the lane boundary (TLC model), and a lane warning model based on the lateral distance. The above-mentioned warning algorithms have high warning accuracy and low false alarm rate, which basically meet the needs of intelligent transportation. However, the disadvantage is that these warning algorithms require complex camera calibration, which increases the complexity of the algorithm and affects the real-time performance of the warning system. In addition, there will be bumps during the driving of the vehicle, which will affect the accuracy of the camera calibration, thereby reducing the accuracy of the algorithm. In order to improve the complexity of the existing algorithm, increase the operating speed of the system, and avoid the trouble caused by camera calibration, this embodiment uses lateral distance to design a warning model to meet the real-time requirements of intelligent transportation.

[0106] Specifically, when the lateral distance of the vehicle changes within the set safety threshold, it is safe. The lateral distance is the lateral distance from the estimated motion trajectory point to the lane boundary by calculating, such as Figure 7 As shown in the figure, the lateral distance safety judgment obtains the vehicle deviation information by comparing the lateral distance with the preset safety threshold. The deviation information includes whether it is deviated and whether it is safe. An estimate is made based on this judgment. When changing lanes, the lane change state should be identified. When the distance d from the estimated point to the left side of the lane line is l When the distance is lower than the safe threshold, the lane inclination value will exceed a certain threshold. At this time, the vehicle deviates from the left lane and the right distance d r Same reason.

[0107] Furthermore, in some embodiments, the threshold is set to D = 0.4 × W (where W is the width of the image, i.e., pixels), when min(d l ,d r) When d > D, it indicates that the vehicle is driving safely; otherwise, if at a certain moment min(d l , d r ) < D, it means that the vehicle is deviating, and the system issues an alarm to prompt the driver to change the driving state. If d l < D, it is considered that the vehicle deviates to the left lane; if d r < D, it indicates that the vehicle deviates to the right lane.

[0108] In the post - processing module of the warning information, after obtaining information such as the current lane line and deviation information, it is necessary to process this information for real - time observation output to an oscilloscope or video port. For example, based on the joint simulation of Matlab / Simulink and Prescan to realize the algorithm research of the lane departure warning system, draw the lane line, and mark the lane line using the drawing line function. In some embodiments, it is also possible to draw a schematic diagram from the driver's perspective.

[0109] After that, based on the data obtained from the simulation (referred to as key parameter - related data), test the failure boundary of LDWS in the simulation system under the quantization, perception output accuracy, and variance conditions caused by different key parameters. Among them, the significance of the failure boundary is to find the safety threshold boundary with error as the guide.

[0110] During the actual operation process, the key parameters include resolution, delay, packet loss rate of time, etc. Extract one or more of them as the key parameters to be measured, and the rest are non - key parameters to be measured. Set the non - key parameters to be measured as fixed values, and at the same time set different preset values for the key parameters to be measured and conduct simulations, so as to use the multiple data obtained during the simulation as the key parameter - related data for safety operation analysis.

[0111] During the analysis process, it is necessary to conduct a quantitative test on the impact of key parameters on safe operation. For example, study the impact of key parameters on safe operation through vehicle warning points. At the same time, since the output accuracy may also affect safe operation, it is also necessary to conduct a perception test on the output accuracy. In addition, the mean absolute error and / or variance can also be used as indicators for analysis.

[0112] It should be noted that there is a pre - set mapping relationship between the test category - key parameter to be measured. Specifically, when the test category is the perception accuracy test, the key parameter to be measured is the resolution. When the test category is the quantization test, the key parameter to be measured is one of the delay, packet loss rate of time, and resolution.

[0113] In some embodiments, when the test category is a perception accuracy test and the key parameter to be tested is resolution, the method based on the simulated lane departure warning system and the simulation scenario, selecting the corresponding key parameter to be tested for testing according to the pre-selected test category through a test category-key parameter to be tested mapping relationship, setting different preset values ​​for the key parameter to be tested, performing lane departure warning simulation according to the preset values, and obtaining key parameter related data of the test vehicle in the current driving state specifically includes:

[0114] Adding a preset sensor to the simulation scene; wherein the preset sensor is used to detect the actual distance from the estimated motion trajectory point of the test vehicle to the lane line;

[0115] Based on the simulated lane departure warning system and the simulation scenario, the sampling frame rate is set to a fixed value, and lane departure warning simulation is performed at different resolution preset values, and the detection distance and actual distance at each resolution are obtained as key parameter related data; wherein the detection distance is the lateral distance output by the simulated lane departure warning system.

[0116] Specifically, when the test category is the perception accuracy test, the key parameter to be tested is the resolution. At this time, the perception output accuracy test can be carried out, that is, the output accuracy is used as an indicator for testing and analysis. It can be understood that the accuracy of the lane line distance detected by the camera in the system will directly affect the output accuracy of the system. This part can also be called the perception output accuracy test. During the implementation process, a sensor is added to the simulation scene. The sensor can use an ideal sensor to detect the actual distance between the estimated trajectory point and the lane line. It can be understood that the lateral distance detected by the simulated lane departure warning system is the detection distance, which has a certain deviation. Subsequent analysis is carried out by comparing the detection distance and the actual distance.

[0117] In a specific embodiment, the sampling frame rate of the camera is set to 25 Hz, and different resolutions (1280×960, 1600×1200, 2048×1536, 2560×1920, 3840×2160) are given for simulation, and real-time data of actual distance and detection distance at different resolutions are obtained.

[0118] In some embodiments, when the test category is a quantitative test and the key parameter to be tested is one of latency, time packet loss rate and resolution, the method based on the simulated lane departure warning system and the simulation scenario, selecting the corresponding key parameter to be tested for testing according to the pre-selected test category through the test category-key parameter to be tested mapping relationship, setting different preset values ​​for the key parameter to be tested, performing lane departure warning simulation according to the preset values, and obtaining key parameter related data of the test vehicle in the current driving state specifically includes:

[0119] Based on the simulated lane departure warning system and the simulation scenario, a non-key parameter to be tested is set to a fixed value, and a lane departure warning simulation is performed under different preset values ​​of the key parameter to be tested, and a vehicle warning starting point under each preset value is obtained as the key parameter related data;

[0120] Among them, the vehicle warning starting point is the distance between the estimated trajectory point of the test vehicle and the lane line when the warning is issued.

[0121] Specifically, when the test category is a quantitative test, the key parameter to be tested is one of latency, time packet loss rate and resolution. At this time, a quantitative test can be performed, for example, to quantify the impact of each key parameter to be tested on safe operation as a vehicle warning starting point indicator for testing and analysis. The vehicle warning starting point refers to the distance between the vehicle and the lane line when a warning is issued when the vehicle deviates.

[0122] It can be understood that, in order to further explain the quantitative test, the present invention further illustrates two types of scenarios, namely, a straight road scenario and a curved road scenario.

[0123] In some embodiments, in a straight road scenario, the test is described from three perspectives: latency test, packet loss test, and resolution test.

[0124] In the case of delay testing, it can be understood that in an unreliable communication scenario, there is a delay in relying on the camera to detect the lane line position, and the delay will reduce the performance of the system. In a specific embodiment, for the delay under unreliable communication, this embodiment uses the delay module of the Simulink library, sets the camera resolution (i.e., the non-key parameter to be tested under this test) to 1280×920 (1.3 million), sets different time delays (i.e., the key parameter to be tested) for simulation experiments, and sets different sampling frame rates for simulation experiments for comparative analysis. The key parameter related data obtained are shown in Table 1:

[0125] Table 1. Vehicle warning starting points under different delays and sampling frame rates

[0126]

[0127] In the case of packet loss testing, it can be understood that in communication networks, data transmission is usually bursty, that is, after a data is lost during transmission, the probability of the next data being lost is greater than the probability of successful transmission. This characteristic is usually expressed by a Fig.10 The Markov chain with two states is shown in Figure 1. Where σ(k) = 1 means that the data is not lost when it is transmitted through the network, and the system is in a closed loop state; σ(k) = 2 means that the data is lost when it is transmitted through the network, and the system is in an open loop state. The state transition probability matrix of the Markov chain is

[0128]

[0129] For example, when the packet loss probability is 0.2, P 11 =0.80; P 12 =0.20; P 21 =0.75; P 22 =0.25; the state transition probability matrix is ​​shown in Table 2.

[0130] Table 2 Markov chain state transition probability matrix

[0131]

[0132]

[0133] As shown in Table 2, it can be understood that if there is no packet loss at the previous moment, the probability of packet loss at the next moment is 20%; if there is packet loss at the previous moment, the probability of packet loss at the next moment increases to 25%. It should be noted that packet loss does not mean that the data is directly 0, but that the data keeps the value at the most recent moment in history until the latest data is received, so packet loss is equivalent to a random delay.

[0134] In view of the packet loss under unreliable communication, this embodiment adopts the above-mentioned packet loss method, sets the camera resolution (i.e., the non-key parameter to be tested under this test) to 1280×920 (1.3 million), sets different packet loss rates (i.e., the key parameter to be tested) for simulation experiments, and sets different sampling frame rates for simulation experiments for comparative analysis. The key parameter related data obtained are shown in Table 3:

[0135] Table 3. Vehicle warning starting points under different packet loss and sampling frame rates

[0136]

[0137] In the case of resolution test, it can be understood that the LDWS system detects the lane line position through the camera, so the resolution of the camera is very important and will affect the warning performance of the system. The control delay (i.e., the non-key parameter to be tested under this test) is the same, and different resolutions (i.e., the key parameter to be tested) are set for simulation experiments. In order to conduct comparative analysis, different sampling frame rates are set for simulation experiments. The warning starting point of the vehicle under different experiments (i.e., key parameter related data) is recorded in Table 4.

[0138] Table 4 Vehicle warning starting points at different resolutions and sampling frame rates

[0139]

[0140]

[0141] In some embodiments, in a curved road scenario, the test is described from three perspectives: latency test, packet loss test, and resolution test.

[0142] This embodiment will test and analyze a curved road scene with a curvature radius of 200m and a curved road scene with a curvature radius of 400m respectively.

[0143] For a curved road scene with a curvature radius of 200m:

[0144] In the case of delay testing, this embodiment uses the delay module of the Simulink library, sets the camera resolution (i.e., the non-key parameter to be tested in this test) to 1280×920 (1.3 million), sets different time delays (i.e., the key parameter to be tested) for simulation experiments. In order to conduct comparative analysis, different sampling frame rates are set for simulation experiments at the same time. The key parameter related data obtained are shown in Table 5. Since the left warning and the right warning are basically the same, this embodiment only analyzes the left warning.

[0145] Table 5 Vehicle warning starting points under different delays and sampling frame rates

[0146]

[0147] In the case of packet loss test, for packet loss under unreliable communication, this embodiment adopts the above packet loss method, sets the camera resolution (i.e., non-key parameter to be tested under this test) to 1280×920 (1.3 million), sets different packet loss rates (i.e., key parameters to be tested) for simulation experiments, and sets different sampling frame rates for simulation experiments for comparative analysis. The key parameter related data obtained are shown in Table 6. Since the left warning and the right warning are basically the same, this embodiment only analyzes the left warning.

[0148] Table 6 Vehicle warning starting points under different packet loss and sampling frame rates

[0149]

[0150] In the case of resolution test, it can be understood that the LDWS system detects the lane line position through the camera, so the resolution of the camera is very important and will affect the warning performance of the system. The control delay (i.e., the non-key parameter to be tested under this test) is the same, and different resolutions (i.e., the key parameter to be tested) are set for simulation experiments. In order to conduct comparative analysis, different sampling frame rates are set for simulation experiments. The warning starting point of the vehicle under different experiments (i.e., key parameter related data) is recorded in Table 7. Since the left warning and the right warning are basically the same, this embodiment only analyzes the left warning.

[0151] Table 7 Vehicle warning starting points at different resolutions and sampling frame rates

[0152]

[0153] For a curved road scene with a curvature radius of 400m:

[0154] In the case of delay testing, this embodiment uses the delay module of the Simulink library, sets the camera resolution (i.e., the non-key parameter to be tested in this test) to 1280×920 (1.3 million), sets different time delays (i.e., the key parameter to be tested) for simulation experiments. In order to conduct comparative analysis, different sampling frame rates are set for simulation experiments at the same time. The key parameter related data obtained are shown in Table 8. Since the left warning and the right warning are basically the same, this embodiment only analyzes the left warning.

[0155] Table 8 Vehicle warning starting point under different delays and sampling frame rates

[0156]

[0157] In the case of packet loss test, for packet loss under unreliable communication, this embodiment adopts the above packet loss method, sets the camera resolution (i.e., non-key parameter to be tested under this test) to 1280×920 (1.3 million), sets different packet loss rates (i.e., key parameters to be tested) for simulation experiments, and sets different sampling frame rates for simulation experiments for comparative analysis. The key parameter related data obtained are shown in Table 9. Since the left warning and the right warning are basically the same, this embodiment only analyzes the left warning.

[0158] Table 9 Vehicle warning starting points under different packet loss and sampling frame rates

[0159]

[0160] In the case of resolution test, it can be understood that the LDWS system detects the lane line position through the camera, so the resolution of the camera is very important and will affect the warning performance of the system. The control delay (i.e., the non-key parameter to be tested under this test) is the same, and different resolutions (i.e., the key parameter to be tested) are set for simulation experiments. In order to conduct comparative analysis, different sampling frame rates are set for simulation experiments. The warning starting point of the vehicle under different experiments (i.e., key parameter related data) is recorded in Table 10. Since the left warning and the right warning are basically the same, this embodiment only analyzes the left warning.

[0161] Table 10 Vehicle warning starting points at different resolutions and sampling frame rates

[0162]

[0163]

[0164] Step 130: Analyze the key parameter related data to obtain the safety threshold boundary of the key parameter.

[0165] Furthermore, when the test category is a perception accuracy test, the data obtained at the same resolution are plotted in the same data graph. Based on the above embodiment, the data graph is as follows: Figure 8 As shown, Figure 8 (a)-(e) show the data graphs of 1280×960 resolution, 1600×1200 resolution, 2048×1536 resolution, 2560×1920 resolution, and 3840×2160 resolution respectively. Figure 8 It can be seen that the lane detection module can detect the lateral distance of the estimated point under these five resolutions, and the LDWS system can achieve early warning well. Since the minimum resolution of the camera usually used in actual operation is 1280×960, the cameras used can basically meet the requirements of safe operation.

[0166] In addition, it can be seen that the size of the resolution will affect the warning performance of the vehicle. In theory, as the resolution increases, the warning performance of LDWS will improve. Compared with the ideal sensor, the lane line detection algorithm designed in the embodiment of the present invention has a certain deviation, but its impact can be ignored. The system can meet our test objectives. The sampling frame rate of lane line tracking in LDWS is the same as the sampling frame rate of the warning system.

[0167] When the test category is a quantitative test, in some embodiments, analyzing the key parameter related data to obtain the safety threshold boundary of the key parameter specifically includes:

[0168] Using the vehicle warning starting point as a measurement standard, drawing a three-dimensional analysis diagram of the key parameters to be measured and the vehicle warning starting point;

[0169] The safety threshold boundary is obtained according to the three-dimensional analysis graph.

[0170] Further, based on the above embodiment, in the delay test of the straight road scene, the estimated point deviation threshold is set to D = 0.4 × W (where W is the width of the image, i.e., the pixel point). It can be seen from Table 1 that the impact of delay on LDWS is significant, and its impact increases with the increase of delay. In each set of tests, the warning starting point is used as a criterion, and a three-dimensional analysis diagram of delay, sampling frame rate and warning starting point is given. The analysis diagrams of left warning and right warning are shown in Figure 1. Fig. 9 (a) and (b). Fig. 9 ,When the vehicle's warning starting point is less than or equal to 0, the LDWS system fails. This time is set as the failure boundary of the system under time delay, and its threshold curve is shown in the figure.

[0171] Furthermore, based on the above embodiment, in the packet loss test of the straight road scene, it can be seen from Table 3 that the packet loss rate has a certain impact on LDWS. When the packet loss rate reaches a certain value, the warning effect of LDWS will be reduced. In each set of tests, the warning starting point is used as a criterion to provide a three-dimensional analysis diagram of the packet loss rate, sampling frame rate and warning starting point. The analysis diagrams of the left warning and the right warning are as follows: Fig.11 (a) and (b). Fig.11 ,When the packet loss rate of the transmitted data reaches a certain value, the warning performance of the LDWS system will change, and its threshold curve is shown in the figure. From 11(a), it can be seen that due to the loss of lane line detection data, the warning cannot accurately obtain the information required for the warning, resulting in the interruption of the warning signal, which leads to the phenomenon of misleading the driver or the delay of the warning starting point. When the sampling frame rate of the system is 25Hz, the warning starting point is delayed when the packet loss rate reaches 35%, and when the sampling frame rate is higher than 25Hz, the warning starting point is delayed when the packet loss rate is 40%. When the packet loss rate exceeds the threshold, as the packet loss rate increases, the warning performance of the system gradually decreases.

[0172] Further, based on the above embodiment, in the resolution test of the straight road scene, taking into account the resolution size of the camera in actual application, five groups of different resolutions are taken, and the warning performance of LDWS is tested at each group of resolutions. It can be seen from Table 4 that the warning performance of the system will improve with the increase of resolution, and a three-dimensional analysis diagram is given as follows: Fig.12 As shown, the analysis diagram of left warning and right warning is as follows Fig.12 (a) and (b). Fig.12, assuming that the system parameter when the vehicle's warning starting point is delayed by 0.02m is used as the threshold, the threshold curve is shown in the figure. As can be seen from the figure, when the sampling frame rate and resolution are both low, the system's warning system is reduced. Under the five different resolutions of this embodiment, LDWS can achieve warning.

[0173] Furthermore, based on the above embodiment, in the delay test of the curved road scene with a curvature radius of 200m, it can be seen from Table 5 that the influence of delay on LDWS is significant, and its influence increases with the increase of delay. In each set of tests, the warning starting point is used as a criterion, and a three-dimensional analysis diagram of delay, sampling frame rate and warning starting point is given. The analysis diagram is as follows: Fig.13 As shown in the figure, it can be seen that the threshold of the curve is generally larger than that of the straight road. This is because there is a certain deviation between the lateral distance of the estimated point under the curve and the lateral distance between the current vehicle and the lane line, which prompts the warning starting point to be advanced, which will lead to the phenomenon of early warning, but the system can give normal warning within a safe range.

[0174] Further, based on the above embodiment, in the packet loss test of the curved road scene with a curvature radius of 200m, in each set of tests, the warning starting point is used as a criterion to provide a three-dimensional analysis diagram of the packet loss rate, the sampling frame rate and the warning starting point. The analysis diagram is as follows: Fig.14 As shown in the figure, it can be seen that under this curve, when the packet loss rate reaches 40%, the system's warning starting point is delayed.

[0175] Further, based on the above embodiment, in the resolution test of the curved road scene with a curvature radius of 200m, considering the resolution size of the camera in actual applications, we took five groups of different resolutions and tested the warning performance of LDWS at each group of resolutions. It can be seen from Table 7 that the warning performance of the system will improve with the increase of resolution, and the three-dimensional analysis diagram is given as follows: Fig.15 shown.

[0176] Furthermore, based on the above embodiment, in the delay test of the curved road scene with a curvature radius of 400m, it can be seen from Table 8 that the impact of delay on LDWS is significant, and its impact increases with the increase of delay. In each set of tests, the warning starting point is used as a criterion, and a three-dimensional analysis diagram of delay, sampling frame rate and warning starting point is given. The analysis diagrams of left warning and right warning are as follows: Fig.16 As shown in the figure, it can be seen that the threshold curve of the curve is basically the same as that of the straight road, because the road under the curve is basically close to a straight line.

[0177] Further, based on the above embodiment, in the packet loss test of the curved road scene with a curvature radius of 400m, in each set of tests, the warning starting point is used as a criterion to provide a three-dimensional analysis diagram of the packet loss rate, sampling frame rate and warning starting point. The analysis diagrams of the left warning and the right warning are as follows: Fig.17 As shown in the figure, at this curve, when the sampling frame rate is between 25-40Hz, when the packet loss rate reaches 40%, the system's warning starting point is delayed, and when the sampling frame rate is 60Hz, the system's delay with the police starting point occurs when the packet loss rate is 45%.

[0178] Further, based on the above embodiment, in the resolution test of the curved road scene with a curvature radius of 200m, taking into account the resolution size of the camera in actual applications, five groups of different resolutions are taken, and the warning performance of LDWS is tested at each group of resolutions. It can be seen from Table 10 that the warning performance of the system will improve with the increase of resolution, and a three-dimensional analysis diagram is given as follows: Fig.18 shown.

[0179] Furthermore, after step 130, the method further includes: outputting an analysis report.

[0180] The lane departure warning system safety operation key parameter testing method provided by the present invention simulates the lane departure warning system and builds a simulation scene by using a preset simulation algorithm; wherein the simulation scene at least includes a camera, a test vehicle and a test road; based on the simulated lane departure warning system and the simulation scene, the corresponding key parameter to be tested is selected for testing according to the pre-selected test category through the test category-key parameter mapping relationship, different preset values ​​are set for the key parameter to be tested, and lane departure warning simulation is performed according to the preset value to obtain the key parameter related data of the test vehicle in the current driving state; wherein the key parameter to be tested includes at least one of resolution, delay, sampling frame rate, and time packet loss rate, and the test category includes perception output accuracy test and quantization test; the key parameter related data is analyzed to obtain the safety threshold boundary of the key parameter. The present invention tests the key parameters of the safe operation of the lane departure warning system through a simulation algorithm, and calculates the safety threshold boundary of the key parameters through scene simulation, thereby contributing to a lane departure warning system with higher explanatory power.

[0181] The lane departure warning system key parameter testing device for safe operation provided by the present invention is described below. The lane departure warning system key parameter testing device for safe operation described below and the lane departure warning system key parameter testing method for safe operation described above can be referenced to each other. Fig.19 : is a schematic diagram of the structure of the key parameter testing device for safe operation of the lane departure warning system provided by the present invention, such as Fig.19 As shown, the device comprises:

[0182] An algorithm building unit 210 is used to simulate a lane departure warning system using a preset simulation algorithm and build a simulation scene; wherein the simulation scene at least includes a camera, a test vehicle, and a test road;

[0183] A simulation test unit 220 is used to select corresponding key parameters to be tested for testing based on the simulated lane departure warning system and the simulation scenario according to a pre-selected test category through a test category-key parameter mapping relationship, set different preset values ​​for the key parameters to be tested, perform lane departure warning simulation according to the preset values, and obtain key parameter-related data of the test vehicle in the current driving state; wherein the key parameters to be tested include at least one of resolution, delay, sampling frame rate, and time packet loss rate, and the test category includes perception output accuracy test and quantization test;

[0184] The analysis result unit 230 is used to analyze the key parameter related data to obtain the safety threshold boundary of the key parameter.

[0185] According to a lane departure warning system safe operation key parameter testing device provided by the present invention, when the test category is a quantitative test and the key parameter to be tested is one of delay, time packet loss rate and resolution, the device is based on the simulated lane departure warning system and the simulation scenario, and according to the pre-selected test category, the corresponding key parameter to be tested is selected through the test category-key parameter to be tested mapping relationship for testing, different preset values ​​are set for the key parameter to be tested, and lane departure warning simulation is performed according to the preset values ​​to obtain key parameter related data of the test vehicle in the current driving state, specifically including:

[0186] Based on the simulated lane departure warning system and the simulation scenario, a non-key parameter to be tested is set to a fixed value, and a lane departure warning simulation is performed under different preset values ​​of the key parameter to be tested, and a vehicle warning starting point under each preset value is obtained as the key parameter related data;

[0187] Among them, the vehicle warning starting point is the distance between the estimated trajectory point of the test vehicle and the lane line when the warning is issued.

[0188] According to a lane departure warning system safe operation key parameter testing device provided by the present invention, when the test category is a perception accuracy test and the key parameter to be tested is resolution, the device is based on the simulated lane departure warning system and the simulation scenario, and according to the pre-selected test category, a corresponding key parameter to be tested is selected for testing through a test category-key parameter to be tested mapping relationship, different preset values ​​are set for the key parameter to be tested, and a lane departure warning simulation is performed according to the preset values, so as to obtain key parameter related data of the test vehicle in the current driving state, specifically including:

[0189] Adding a preset sensor to the simulation scene; wherein the preset sensor is used to detect the actual distance from the estimated motion trajectory point of the test vehicle to the lane line;

[0190] Based on the simulated lane departure warning system and the simulation scenario, the sampling frame rate is set to a fixed value, and lane departure warning simulation is performed at different resolution preset values, and the detection distance and actual distance at each resolution are obtained as key parameter related data; wherein the detection distance is the lateral distance output by the simulated lane departure warning system.

[0191] According to a lane departure warning system safety operation key parameter testing device provided by the present invention, the analysis of the key parameter related data to obtain the safety threshold boundary of the key parameter specifically includes:

[0192] Using the vehicle warning starting point as a measurement standard, drawing a three-dimensional analysis diagram of the key parameters to be measured and the vehicle warning starting point;

[0193] The safety threshold boundary is obtained according to the three-dimensional analysis graph.

[0194] According to a lane departure warning system safety operation key parameter testing device provided by the present invention, the lane departure warning system includes a road video pre-processing module, a lane line detection module, a lane line tracking module, a departure warning module and a warning information post-processing module;

[0195] The road video pre-processing module is used to perform grayscale processing and threshold processing on the road image acquired by the camera to obtain a grayscale image and a binary image;

[0196] The lane line detection module is used to extract geometric features of the road boundary of the test road according to the grayscale image and the binarization image to obtain the current lane line;

[0197] The lane line tracking module is used to input the current lane line into a filter to obtain a lane estimation value, and replace the current lane line with the lane estimation value;

[0198] The deviation warning module is used to estimate the estimated motion trajectory point according to the dynamic parameters of the test vehicle in the current driving state, calculate the lateral distance from the estimated motion trajectory point to the boundary of the current lane line, compare the lateral distance with a preset safety threshold, obtain deviation information, and perform a deviation warning according to the deviation information;

[0199] The warning information post-processing module is used to visualize the current lane line and the deviation information, and output them to an oscilloscope or a video port for real-time observation.

[0200] According to a lane departure warning system safety operation key parameter testing device provided by the present invention, the lane departure warning system is simulated by using a preset simulation algorithm and a simulation scene is built, specifically including:

[0201] Use Matlab or Simulink to simulate the lane departure warning system and use Prescan to build the simulation scenario;

[0202] The test road includes a straight road and a curved road, and the visible lane markings on the road surface of the test road comply with the provisions of GB5768.

[0203] The lane departure warning system safety operation key parameter test device provided by the present invention simulates the lane departure warning system and builds a simulation scene by using a preset simulation algorithm; wherein the simulation scene at least includes a camera, a test vehicle and a test road; based on the simulated lane departure warning system and the simulation scene, the corresponding key parameter to be tested is selected for testing according to the pre-selected test category through the test category-key parameter mapping relationship, different preset values ​​are set for the key parameter to be tested, and lane departure warning simulation is performed according to the preset value to obtain the key parameter related data of the test vehicle in the current driving state; wherein the key parameter to be tested includes at least one of resolution, delay, sampling frame rate, and time packet loss rate, and the test category includes perception output accuracy test and quantization test; the key parameter related data is analyzed to obtain the safety threshold boundary of the key parameter. The present invention tests the key parameters for the safe operation of the lane departure warning system through a simulation algorithm, and calculates the safety threshold boundary of the key parameters through scene simulation, thereby contributing to a lane departure warning system with higher explanatory power.

[0204] Fig. 20 An example of a physical structure diagram of an electronic device is shown in FIG. Fig. 20As shown, the electronic device may include: a processor (processor) 310, a communication interface (Communications Interface) 320, a memory (memory) 330 and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call the logic instructions in the memory 330 to execute a method for testing key parameters for safe operation of a lane departure warning system, the method comprising: simulating a lane departure warning system using a preset simulation algorithm and building a simulation scene; wherein the simulation scene at least includes a camera, a test vehicle, and a test road; based on the simulated lane departure warning system and the simulation scene, selecting corresponding key parameters to be tested for testing according to a pre-selected test category through a test category-key parameter mapping relationship, setting different preset values ​​for the key parameters to be tested, performing lane departure warning simulation according to the preset values, and obtaining key parameter related data of the test vehicle in the current driving state; wherein the key parameters to be tested include at least one of resolution, delay, sampling frame rate, and time packet loss rate, and the test category includes a perception output accuracy test and a quantization test; analyzing the key parameter related data to obtain the safety threshold boundary of the key parameter.

[0205] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0206] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the lane departure warning system safe operation key parameter testing method provided by the above methods, the method including: using a preset simulation algorithm to simulate the lane departure warning system and build a simulation scene; wherein the simulation scene at least includes a camera, a test vehicle and a test road; based on the simulated lane departure warning system and the simulation scene, according to the pre-selected test category, the corresponding key parameters to be tested are selected for testing through the test category-key parameter mapping relationship, different preset values ​​are set for the key parameters to be tested, and lane departure warning simulation is performed according to the preset values ​​to obtain key parameter related data of the test vehicle in the current driving state; wherein the key parameters to be tested include at least one of resolution, delay, sampling frame rate, and time packet loss rate, and the test category includes perception output accuracy test and quantization test; the key parameter related data is analyzed to obtain the safety threshold boundary of the key parameter.

[0207] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the key parameter testing method for safe operation of a lane departure warning system provided by the above-mentioned methods, the method comprising: simulating a lane departure warning system using a preset simulation algorithm and building a simulation scene; wherein the simulation scene at least includes a camera, a test vehicle and a test road; based on the simulated lane departure warning system and the simulation scene, selecting corresponding key parameters to be tested for testing according to a pre-selected test category through a test category-key parameter mapping relationship, setting different preset values ​​for the key parameters to be tested, performing lane departure warning simulation according to the preset values, and obtaining key parameter related data of the test vehicle in the current driving state; wherein the key parameters to be tested include at least one of resolution, delay, sampling frame rate, and time packet loss rate, and the test category includes perception output accuracy test and quantization test; analyzing the key parameter related data to obtain the safety threshold boundary of the key parameter.

[0208] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0209] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0210] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for testing key parameters of safe operation of a lane departure warning system, characterized in that: include: Using a preset simulation algorithm to simulate a lane departure warning system and build a simulation scene; wherein the simulation scene at least includes a camera, a test vehicle, and a test road; Based on the simulated lane departure warning system and the simulation scenario, the corresponding key parameters to be tested are selected for testing according to the pre-selected test category through the test category-key parameter mapping relationship, different preset values ​​are set for the key parameters to be tested, and lane departure warning simulation is performed according to the preset values ​​to obtain key parameter-related data of the test vehicle in the current driving state; wherein the key parameters to be tested include at least one of resolution, delay, sampling frame rate, and time packet loss rate, and the test category includes perception output accuracy test and quantization test; Analyze the key parameter related data to obtain the safety threshold boundary of the key parameter; In the case where the test category is a quantitative test and the key parameter to be tested is one of latency, temporal packet loss rate and resolution, based on the simulated lane departure warning system and the simulation scenario, a non-key parameter to be tested is set to a fixed value, and a lane departure warning simulation is performed under different preset values ​​of the key parameter to be tested, and a vehicle warning starting point under each preset value is obtained as the key parameter related data; wherein the vehicle warning starting point is the distance between the estimated trajectory point of the test vehicle and the lane line when the warning is issued; When the test category is a perception accuracy test and the key parameter to be tested is resolution, a preset sensor is added to the simulation scene; wherein the preset sensor is used to detect the actual distance from the estimated motion trajectory point of the test vehicle to the lane line; based on the simulated lane departure warning system and the simulation scene, the sampling frame rate is set to a fixed value, and a lane departure warning simulation is performed under different preset resolution values, and the detection distance and actual distance under each resolution are obtained as key parameter related data; wherein the detection distance is the lateral distance output by the simulated lane departure warning system; The analyzing the key parameter related data to obtain the safety threshold boundary of the key parameter specifically includes: The vehicle warning starting point is used as a measurement standard to draw a three-dimensional analysis diagram of the key parameters to be measured and the vehicle warning starting point; and the safety threshold boundary is obtained according to the three-dimensional analysis diagram.

2. The method for testing key parameters of safe operation of lane departure warning system according to claim 1, characterized in that: The lane departure warning system includes a road video pre-processing module, a lane line detection module, a lane line tracking module, a departure warning module and a warning information post-processing module; The road video pre-processing module is used to perform grayscale processing and threshold processing on the road image acquired by the camera to obtain a grayscale image and a binary image; The lane line detection module is used to extract geometric features of the road boundary of the test road according to the grayscale image and the binarization image to obtain the current lane line; The lane line tracking module is used to input the current lane line into a filter to obtain a lane estimation value, and replace the current lane line with the lane estimation value; The deviation warning module is used to estimate the estimated motion trajectory point according to the dynamic parameters of the test vehicle in the current driving state, calculate the lateral distance from the estimated motion trajectory point to the boundary of the current lane line, compare the lateral distance with a preset safety threshold, obtain deviation information, and perform a deviation warning according to the deviation information; The warning information post-processing module is used to visualize the current lane line and the deviation information, and output them to an oscilloscope or a video port for real-time observation.

3. The method for testing key parameters of safe operation of lane departure warning system according to claim 1, characterized in that: The method of simulating the lane departure warning system using a preset simulation algorithm and building a simulation scenario specifically includes: Use Matlab or Simulink to simulate the lane departure warning system and use Prescan to build the simulation scenario; The test road includes a straight road and a curved road, and the visible lane markings on the road surface of the test road comply with the provisions of GB5768.

4. A lane departure warning system safe operation key parameter test device, characterized in that: include: An algorithm building unit, used to simulate the lane departure warning system using a preset simulation algorithm and build a simulation scene; wherein the simulation scene at least includes a camera, a test vehicle, and a test road; A simulation test unit, for selecting corresponding key parameters to be tested for testing based on the simulated lane departure warning system and the simulation scenario according to a pre-selected test category through a test category-key parameter mapping relationship, setting different preset values ​​for the key parameters to be tested, performing lane departure warning simulation according to the preset values, and obtaining key parameter-related data of the test vehicle in the current driving state; wherein the key parameters to be tested include at least one of resolution, latency, sampling frame rate, and time packet loss rate, and the test category includes perception output accuracy test and quantization test; An analysis result unit, used to analyze the key parameter related data to obtain the safety threshold boundary of the key parameter; The simulation test unit is specifically used for: when the test category is a quantitative test and the key parameter to be tested is one of latency, time packet loss rate and resolution, based on the simulated lane departure warning system and the simulation scenario, setting the non-key parameter to be tested to a fixed value, and performing lane departure warning simulation under different preset values ​​of the key parameter to be tested, and obtaining the vehicle warning starting point under each preset value as the key parameter related data; wherein the vehicle warning starting point is the distance between the estimated trajectory point of the test vehicle and the lane line when the warning is issued; The simulation test unit is specifically used to: when the test category is a perception accuracy test and the key parameter to be tested is resolution, add a preset sensor to the simulation scene; wherein the preset sensor is used to detect the actual distance from the estimated motion trajectory point of the test vehicle to the lane line; based on the simulated lane departure warning system and the simulation scene, set the sampling frame rate to a fixed value, and perform lane departure warning simulation under different resolution preset values, and obtain the detection distance and actual distance under each resolution as key parameter related data; wherein the detection distance is the lateral distance output by the simulated lane departure warning system; The analysis result unit is specifically used to: use the vehicle warning starting point as a measurement standard to draw a three-dimensional analysis diagram of the key parameters to be measured and the vehicle warning starting point; and obtain the safety threshold boundary according to the three-dimensional analysis diagram.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for testing key parameters for safe operation of the lane departure warning system as described in any one of claims 1 to 3 is implemented.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for testing key parameters for safe operation of a lane departure warning system as claimed in any one of claims 1 to 3 is implemented.

7. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for testing key parameters for safe operation of a lane departure warning system as claimed in any one of claims 1 to 3 is implemented.

Images