An image-based method for testing key parameters of vehicle automatic emergency braking system

Abstract

The present invention provides an image-based vehicle automatic emergency braking system key parameter testing method, comprising: obtaining image data in front of a vehicle in a simulation scene through a pre-built simulation system; generating control instructions based on the image data through a preset automatic emergency braking model, and controlling the vehicle to brake based on the control instructions; setting different preset values ​​for key parameters during braking, simulating the braking effect under different preset values; and determining boundary warning values ​​of different key parameters according to the braking effect. The present invention solves the problem of potential safety hazards caused by unclear settings of key parameters of existing vehicle automatic emergency systems.

Description

Technical Field

[0001] The present invention relates to the field of vehicle intelligent driving technology, and in particular to an image-based key parameter testing method for a vehicle automatic emergency braking system. Background Art

[0002] With the continuous development of autonomous driving technology, the driving mode has gradually changed from being assisted by a driver or a co-driver to driving without a driver. The safety requirements of autonomous driving for vehicles have also increased with the change in driving mode. The automatic emergency braking system (AEBS) is a system that automatically detects target vehicles or obstacles, detects potential forward collision hazards, issues a warning signal to alert the driver, and activates the vehicle's braking system to avoid or mitigate collisions by reducing speed. It is widely used in the fields of commercial vehicle safe driving and autonomous driving.

[0003] Based on the "Performance Requirements and Test Methods for Lane Departure Warning Systems of Intelligent Transport Systems" or "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 safe working boundaries of the vision-based automatic emergency braking system under the influence of key indicators such as latency / packet loss, quantification caused by resolution and bandwidth, perception output accuracy and variance are tested and analyzed, a target perception model based on the "Detection Method" is established, and quantitative analysis results of key indicators are obtained.

[0004] However, the existing vehicle automatic emergency braking process does not fully consider the impact of key indicators such as actual delay / packet loss, quantization caused by resolution and bandwidth, and perception output accuracy and variance on automatic emergency braking. It is difficult to determine the boundary value to effectively adjust the braking system, resulting in poor emergency braking effect and safety hazards. Summary of the invention

[0005] The present invention provides an image-based vehicle automatic emergency braking system key parameter testing method, which is used to solve the problem of possible and existing safety hazards caused by unclear key parameter settings of the existing vehicle automatic emergency braking system.

[0006] The present invention provides an image-based vehicle automatic emergency braking system key parameter testing method, comprising:

[0007] Acquire image data in front of the vehicle in a simulation scene through a pre-built simulation system;

[0008] Generate a control instruction based on the image data through a preset automatic emergency braking model, and control the vehicle to brake based on the control instruction;

[0009] During the braking process, different preset values ​​are set for key parameters to simulate the braking effect under different preset values;

[0010] Boundary warning values ​​of different key parameters are determined according to the braking effect.

[0011] According to an image-based vehicle automatic emergency braking system key parameter testing method provided by the present invention, the image data in front of the vehicle is obtained in a simulation scene by a pre-built simulation system, specifically comprising:

[0012] Collect image data in front of the vehicle through the on-board monocular camera;

[0013] The front vehicle information is detected based on the image data by using a pre-trained vehicle detection model.

[0014] According to a method for testing key parameters of an automatic emergency braking system of a vehicle based on an image provided by the present invention, the method generates a control instruction based on the image data through a preset automatic emergency braking model, and controls the vehicle to brake based on the control instruction, specifically comprising:

[0015] Calculating the collision time between the two vehicles through a preset automatic emergency braking model according to the front vehicle information detected in the image data;

[0016] A control instruction is generated according to the collision time, and the vehicle is controlled by the control instruction to perform full braking, partial braking or issue a warning.

[0017] According to an image-based vehicle automatic emergency braking system key parameter testing method provided by the present invention, different preset values ​​are set for the key parameters during the braking process to simulate the braking effects under different preset values, specifically including:

[0018] The resolution of the key parameters is set to a fixed value, the frame rate is changed and different preset values ​​are set for the time delay and the packet loss rate, and the shortest relative distance between the two vehicles is simulated and calculated;

[0019] Among them, the key parameters include: time delay, packet loss rate, resolution and perception output accuracy.

[0020] According to an image-based vehicle automatic emergency braking system key parameter testing method provided by the present invention, different preset values ​​are set for the key parameters during the braking process to simulate the braking effects under different preset values, and further includes:

[0021] The time delay and packet loss rate in the key parameters are set to fixed values, the frame rate is changed and different preset values ​​are set for the resolution in the key parameters, and the shortest relative distance between the two vehicles is calculated by simulation.

[0022] According to an image-based vehicle automatic emergency braking system key parameter testing method provided by the present invention, different preset values ​​are set for the key parameters during the braking process to simulate the braking effects under different preset values, and further includes:

[0023] Set a fixed frame rate, change the resolution and set the perception output accuracy to different preset values, and simulate and calculate the shortest relative distance between the two vehicles.

[0024] According to an image-based vehicle automatic emergency braking system key parameter testing method provided by the present invention, the boundary warning values ​​of different key parameters are determined according to the braking effect, specifically including:

[0025] When the shortest relative distance between the two vehicles is greater than zero, the corresponding key parameter is the boundary warning value.

[0026] The present invention also provides an image-based vehicle automatic emergency braking system key parameter testing system, the system comprising:

[0027] A data acquisition module, used to acquire image data in front of the vehicle in a simulation scene through a pre-built simulation system;

[0028] A control module, configured to generate a control instruction based on the image data through a preset automatic emergency braking model, and control the vehicle to brake based on the control instruction;

[0029] The braking effect simulation module is used to set different preset values ​​for key parameters during the braking process and simulate the braking effect under different preset values;

[0030] The boundary warning value determination module is used to determine the boundary warning values ​​of different key parameters according to the braking effect.

[0031] 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, an image-based vehicle automatic emergency braking system key parameter testing method as described in any one of the above-mentioned methods is implemented.

[0032] 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 image-based methods for testing key parameters of a vehicle automatic emergency braking system.

[0033] The present invention provides an image-based method for testing key parameters of a vehicle automatic emergency braking system. The method obtains a real-time image of a car driving on a road through a camera, and then determines the degree of danger of the vehicle's surrounding environment based on a control algorithm. When the perception system detects a collision risk, the automatic emergency braking system issues a warning to the driver, reminding the driver to take measures to avoid the collision risk. When the driver does not take timely measures to avoid the collision risk (braking or turning to change lanes), the system automatically brakes; or when the braking force applied by the driver is insufficient, the system actively increases the braking force according to the strategy, thereby avoiding a collision or reducing the vehicle speed at the time of the collision, so as to avoid the occurrence of dangerous accidents or reduce the severity of traffic accidents. By simulating the braking effects of multiple key parameters under different preset values, the boundary warning values ​​of different key parameters are determined, so that the automatic emergency braking model can be adjusted to achieve more accurate emergency braking and eliminate safety hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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.

[0035] Figure 1 It is a flow chart of a method for testing key parameters of an automatic emergency braking system of a vehicle based on an image provided by the present invention;

[0036] Figure 2 It is a schematic diagram of the ranging angle provided by the present invention;

[0037] Figure 3 It is a schematic diagram of the change of the relative distance between two vehicles provided by the present invention;

[0038] Figure 4 It is the shortest relative distance analysis diagram under different time delays provided by the present invention;

[0039] Figure 5 It is a schematic diagram of a Markov chain packet loss model with two states provided by the present invention;

[0040] Figure 6 It is the shortest relative distance analysis diagram under different packet loss rates provided by the present invention;

[0041] Figure 7 It is the shortest relative distance analysis diagram under different resolutions provided by the present invention;

[0042] Figure 8It is a module connection diagram of a key parameter test system of an automatic emergency braking system of a vehicle based on an image provided by the present invention;

[0043] Fig. 9 It is a structural schematic diagram of the electronic device provided by the present invention.

[0044] Reference numerals:

[0045] 110: data acquisition module; 120: control module; 130: braking effect simulation module; 140: boundary warning value determination module;

[0046] 910: processor; 920: communication interface; 930: memory; 940: communication bus. DETAILED DESCRIPTION

[0047] 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.

[0048] Combine the following Figure 1 The present invention describes an image-based vehicle automatic emergency braking system key parameter testing method, comprising:

[0049] S100, acquiring image data in front of the vehicle in a simulation scene through a pre-built simulation system;

[0050] In the present invention, the simulation experiment adopts Matlab / Simulink and Prescan joint simulation, the automatic emergency braking algorithm design is realized by Matlab / Simulink, and the scene and sensor design is realized by Prescan. The automatic emergency braking system (AEBS) uses sensors such as cameras to monitor the vehicle in front at all times, judge the distance, direction and relative speed between the vehicle and the vehicle in front, and warn the driver and perform emergency braking when there is a potential collision risk.

[0051] The video image input by the on-board monocular camera is an M×N×3 color image array, also known as an RGB image. Since the target detection algorithm used this time is an end-to-end one-stage target detection algorithm, it does not require image preprocessing, so it is only necessary to pass the real-time image of the vehicle during driving to the target detection module.

[0052] The vehicle detection model is pre-trained using the Aggregate Channel Algorithm (ACF). Aggregate channel features are a variant of integral channel features. They were first used in pedestrian detection algorithms. Pixels in aggregate channels are used as features. Feature channels usually include color channels (RGB color channels, LUV color channels, grayscale channels), gradient channels (including gradient amplitude channels and gradient direction channels), and edge channels (Sobel edge channels and Canny edge channels). Several different features are superimposed together to form a unified feature. The advantage of the aggregate channel algorithm is that the vehicle detection performance is good and the detection speed is extremely fast.

[0053] S200, generating a control instruction based on the image data through a preset automatic emergency braking model, and controlling the vehicle to brake based on the control instruction;

[0054] In the present invention, based on the image data, the distance between the front vehicle and the vehicle is calculated by a monocular camera ranging algorithm. Based on the pinhole imaging principle, the object to be measured is incident on the camera imaging element through the camera pinhole. The camera imaging element converts the received light signal into a digital signal through a digital signal switching function module and transmits it to a computer chip, and the computer chip restores the scene where the object to be measured is located. The converted digital signal is composed of a pixel matrix consisting of a horizontal x and a vertical y, so the distance measurement based on monocular vision ranging is based on the coordinate transformation of the pixel points. Matrix multiplication is used to realize the conversion between the pixel coordinate system, the camera optical center coordinate system and the world coordinate system and to realize the distance measurement. The required calculation steps and parameters are relatively large. The calibration of parameters and the conversion between coordinate systems seriously affect the speed and accuracy of visual measurement. Therefore, in order to improve the accuracy, real-time and convenience of measurement in practical applications, it is necessary to obtain the downward deflection angle of the camera in real time through a posture sensor according to the actual application scenario. The ranging model used in the experiment is as follows: Figure 2 ,exist Figure 2 The angle between the optical axis and the horizontal line is α, that is, the camera has a depression angle of α. When the optical axis is offset downward, α>0, and when the optical axis is offset upward, α<0. M is the intersection of P′P′x and the horizontal plane, and N is the intersection of P′P′y and the horizontal plane, that is, OMN constitutes a horizontal plane perpendicular to OO′, and OO′ is recorded as the focal length f. Since the horizontal plane is parallel to the ground, ∠OPO′=∠P′OM=∠P′OP′x+∠P′xOM. In ΔNO′′O, NO″⊥OO″, therefore:

[0055] O′′N=f·tanα (1) In ΔO″P′xO, OP′x=x, OO″⊥OO″P′x, so:

[0056]

[0057] P′xM=O″N, in ΔP′xOM, OP′x⊥P′xM, so:

[0058]

[0059] In ΔP′OP′x, OP′x⊥PP′x, so:

[0060]

[0061] In ΔOPO′, PO′⊥OO′, so we have

[0062]

[0063] According to the monocular ranging model, the camera height H, downward deflection angle α and camera focal length f can be obtained from Prescan, and the target's xmin, xmax, ymin and ymax in the image can be obtained according to the target detection algorithm. According to the above formula, the distance d from the object to the camera can be calculated. The visual ranging formula used is as follows:

[0064]

[0065] We can get d:

[0066]

[0067] The TTC model based on time distance refers to the distance between the two vehicles and the collision time under the current motion state. The formula is as follows:

[0068]

[0069] Where TTC is the collision time, D rel is the relative distance, V rel is the relative speed. For the TTC model, you only need to input the relative speed and distance of the two vehicles to calculate the collision time. First, the sensor collects information about the front vehicle, and the signal processing module transmits the real-time relative distance and speed information of the two vehicles to the calculation module to calculate TTC. Then it is compared with the time threshold. When the TTC value is less than the time threshold, there is a risk of collision. This model is simple to calculate and requires few parameters.

[0070] In the TTC algorithm, the warning danger TTC is set to 2.6s, the partial braking TTC is set to 1.6s, and the full braking TTC is set to 0.6s. When the system calculates that the actual TTC reaches 2.6s, 1.6s, and 0.6s, it will respectively raise a warning, partial braking (40% brake pressure), and full braking (100% brake pressure). When the two vehicles have the same speed and are close to each other, the TTC value cannot be calculated, and the safety distance model determines whether to intervene with full braking. When d <H stopWhen the vehicle's AEBS intervenes and performs full braking, the vehicle's AEBS will be activated.

[0071] After obtaining the information such as the position of the vehicle in front and the distance between the vehicle and the vehicle in front, it is necessary to process this information so that it can be output to an oscilloscope or video port for real-time observation. The target object is selected by the target detection algorithm and the distance between the vehicle and the vehicle in front is marked. This paper implements the vision-based automatic emergency braking algorithm research based on Matlab / Simulink and Prescan joint simulation. Combining literature data and empirical analysis, the shortest relative distance between the two vehicles is selected to measure the performance of the automatic emergency braking system, such as Figure 3 When the shortest relative distance is greater than zero, it means that the vehicle has not collided with the vehicle in front; when the shortest relative distance is less than zero, it means that the vehicle has collided with the vehicle in front.

[0072] S300, setting different preset values ​​for key parameters during braking, and simulating braking effects under different preset values;

[0073] In the present invention, a delay test analysis is first performed. In an unreliable communication scenario, the distance between the vehicle and the vehicle in front is detected by a camera during driving. There is a delay in the position, which will reduce the performance of the system. For the delay under unreliable communication, this test uses the delay module of the Simulink library, sets the camera resolution to 1280×960, and sets different frame rates and time delays for testing. The data is shown in Table 1:

[0074] Table 1 Data records of the shortest relative distance under different frame rates and delays

[0075]

[0076] From Table 1, we can see that the influence of delay on AEBS is significant. As the delay increases, its influence increases accordingly. The three-dimensional analysis diagram of delay, frame rate and shortest relative distance is shown in Figure 4 shown.

[0077] Figure 7 The red boundary line in the figure is the failure boundary of the automatic emergency braking system under time delay. As can be seen from the figure, with the increase of time delay, the shortest relative distance drops sharply. When the time delay is greater than 650ms, the ego vehicle collides with the vehicle in front. Because when the time delay is a constant value, the ego vehicle tracks the historical state of the vehicle in front before the time delay, and the distance between vehicles increases to the distance traveled by the vehicle in front under the time delay. Due to the time delay, the vehicle distance received by the automatic emergency braking system is larger than the actual vehicle distance. Therefore, the actual alarm and braking time lags behind the theoretical alarm and braking time, causing the minimum relative distance to continue to decrease, so the ego vehicle collides with the vehicle in front. The test results show that time delay is one of the key factors affecting the performance of AEBS.

[0078] Perform packet loss rate test analysis and build a packet loss model in Simulink for packet loss test. 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 Figure 5 The Markov chain with two states is shown in the figure. 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:

[0079] P = [p ij ],

[0080] p ij =P{σ(k+1)=j|σ(k)=i},

[0081]

[0082] Different packet loss probabilities were set to 5%, 25%, 35%, 55%, 65%, and 80% for detection tests. The individual camera resolution was set to 1280×960, and the warning signal responses under different frame rates and packet loss rates are shown in Table 2 below:

[0083] Table 2 Data records of the shortest relative distance under different frame rates and packet loss rates

[0084]

[0085] Table 2 shows that packet loss rate has little impact on AEBS. The three-dimensional analysis diagram of packet loss rate, frame rate and shortest relative distance is shown in Figure 6 shown.

[0086] Depend on Figure 6 Packet loss data analysis shows that as the packet loss rate increases, the shortest relative distance generally shows a downward trend, but the minimum value of the shortest relative distance is 2.13m, which can still effectively stop the vehicle. Since the control system has the properties of a low-pass filter, the controller has a certain robustness to changes in the input signal sampling period, which is manifested in a certain resistance to occasional packet loss, and the control performance deteriorates slightly. The test results show that packet loss has little effect on AEBS performance.

[0087] Quantitative test analysis caused by resolution is performed. AEBS uses a camera to detect the position of the vehicle in front and calculate the distance between vehicles, so the camera resolution will affect the warning performance of the system. Considering the resolution of the camera in actual applications, 5 groups of different resolutions are taken, and the collision avoidance performance of AEBS is tested at each resolution. Table 3 records the shortest relative distance between the two vehicles under different experiments.

[0088] Table 3 Data records of the shortest relative distance at different resolutions and frame rates

[0089]

[0090]

[0091] From Table 3, we can see that the shortest relative distance generally increases with the increase of resolution. The three-dimensional analysis diagram of resolution, frame rate and shortest relative distance is shown in Figure 7 shown.

[0092] The perception output accuracy test analysis is carried out. The accuracy of the camera detecting the distance between the vehicle and the front vehicle will directly affect the output accuracy of the system. The present invention uses the AIR sensor in Prescan (an integrated simulation test platform for intelligent driving of automobiles) to calculate the actual relative distance between the front vehicle and the vehicle. This sensor is an ideal sensor. However, the relative distance measured by the vision-based distance measurement method in this paper has a certain deviation from the actual relative distance, which will directly affect the braking effect of the automatic emergency braking system. The frame rate of the camera is set to 30fps, and the absolute error mean, variance and minimum relative distance data of the actual relative distance and the measured relative distance under different perception output accuracies are given.

[0093] Table 4 Mean, variance and minimum relative distance of absolute error at different resolutions

[0094] Mean absolute error (m) <![CDATA[Mean squared error (m 2 )]]> Minimum relative distance (m) 0.7707 0.3039 3.97 0.8172 0.5059 3.48 0.9701 0.4368 3.31 1.1281 1.3565 3.18 1.1598 1.3270 2.72 1.8391 1.3426 2.45 2.6361 1.7936 1.40 3.1633 3.4491 0.53 3.8064 3.2142 -0.03 4.2884 3.5206 -0.54

[0095] As shown in Table 4, at different resolutions, the larger the absolute error mean and variance, the shorter the minimum relative distance, and the more likely a collision will occur. When the absolute error mean and variance of the perception ranging module are greater than 3.8064m and 3.2142m respectively 2 When the vehicle collided

[0096] S400: Determine boundary warning values ​​of different key parameters according to the braking effect.

[0097] When the shortest relative distance between the two vehicles is greater than zero, the corresponding key parameter is the boundary warning value.

[0098] The present invention uses a camera to obtain real-time images of cars driving on the road, uses a target detection algorithm to detect vehicle targets on the road and calculate the distance between the two vehicles, and calculates the current collision time (TTC) between the two vehicles based on the relative speed of the two vehicles. When the collision time between the vehicle and the front vehicle is less than the preset threshold value Tb3=2.6s, the system should immediately issue a collision warning message, and the driver of the vehicle should take emergency braking measures to avoid collision with the front vehicle; when the collision time is less than the threshold value Tb2=1.6s, if the driver of the vehicle does not take emergency braking measures, the vehicle AEBS intervenes and performs partial braking; when the collision time is less than the threshold value Tb1=0.6s, if the driver of the vehicle still does not take emergency braking measures, the vehicle AEBS intervenes and performs full braking; when the two vehicles have the same speed and are close in distance, the TTC value cannot be calculated, and the safety distance model determines whether full braking is involved. When d <H stop (limit safety distance), the vehicle's AEBS intervenes and performs full braking to actively avoid collision accidents; when the collision danger is eliminated, the AEBS braking is also lifted, which does not affect the normal driving of the vehicle and surrounding vehicles. When the warning and braking conditions are not met, the system should not have false alarms and emergency braking.

[0099] refer to Figure 8 The present invention also discloses an image-based vehicle automatic emergency braking system key parameter testing system, the system comprising:

[0100] A data acquisition module 110, for acquiring image data in front of the vehicle in a simulation scene through a pre-built simulation system;

[0101] A control module 120, configured to generate a control instruction based on the image data through a preset automatic emergency braking model, and control the vehicle to brake based on the control instruction;

[0102] The braking effect simulation module 130 is used to set different preset values ​​for key parameters during the braking process and simulate the braking effects under different preset values;

[0103] The boundary warning value determination module 140 is used to determine the boundary warning values ​​of different key parameters according to the braking effect.

[0104] Among them, the data acquisition module collects image data in front of the vehicle through the on-board monocular camera;

[0105] The front vehicle information is detected based on the image data by using a pre-trained vehicle detection model.

[0106] A control module, which calculates the collision time between the two vehicles through a preset automatic emergency braking model according to the information of the front vehicle detected in the image data;

[0107] A control instruction is generated according to the collision time, and the vehicle is controlled by the control instruction to perform full braking, partial braking or issue a warning.

[0108] A braking effect simulation module, wherein the resolution among the key parameters is set to a fixed value, the frame rate is changed and different preset values ​​are set for the time delay and the packet loss rate, and the shortest relative distance between the two vehicles is simulated and calculated;

[0109] Among them, the key parameters include: time delay, packet loss rate, resolution and perception output accuracy.

[0110] The time delay and packet loss rate in the key parameters are set to fixed values, the frame rate is changed and different preset values ​​are set for the resolution in the key parameters, and the shortest relative distance between the two vehicles is calculated by simulation.

[0111] Set a fixed frame rate, change the resolution and set the perception output accuracy to different preset values, and simulate and calculate the shortest relative distance between the two vehicles.

[0112] The boundary warning value determination module, when the shortest relative distance between the two vehicles is greater than zero, the corresponding key parameter is the boundary warning value.

[0113] Through the image-based key parameter testing system of the vehicle automatic emergency braking system provided by the present invention, the camera obtains the real-time image of the car driving on the road, and then judges the danger level of the surrounding environment of the vehicle according to the control algorithm. When the perception system detects that there is a risk of collision, the automatic emergency braking system warns the driver to remind the driver to take measures to avoid the risk of collision. When the driver does not take measures to avoid the risk of collision in time (braking or turning to change lanes), the system automatically brakes; or when the braking force applied by the driver is insufficient, the system actively increases the braking force according to the strategy, thereby avoiding collision or reducing the speed of the vehicle at the time of collision, so as to avoid the occurrence of dangerous accidents or reduce the severity of traffic accidents. By simulating the braking effects of multiple key parameters under different preset values, the boundary warning values ​​of different key parameters are determined, so that the automatic emergency braking model can be adjusted to achieve more accurate emergency braking and eliminate safety hazards.

[0114] Fig. 9 An example of a physical structure diagram of an electronic device is shown in FIG. Fig. 9As shown, the electronic device may include: a processor 910, a communications interface 920, a memory 930 and a communication bus 940, wherein the processor 910, the communications interface 920 and the memory 930 communicate with each other through the communication bus 940. The processor 910 may call the logic instructions in the memory 930 to execute a vehicle automatic emergency braking system key parameter test system based on an image, the method comprising: a data acquisition module, for acquiring image data in front of the vehicle in a simulation scene through a pre-built simulation system;

[0115] A control module, configured to generate a control instruction based on the image data through a preset automatic emergency braking model, and control the vehicle to brake based on the control instruction;

[0116] The braking effect simulation module is used to set different preset values ​​for key parameters during the braking process and simulate the braking effect under different preset values;

[0117] The boundary warning value determination module is used to determine the boundary warning values ​​of different key parameters according to the braking effect.

[0118] In addition, the logic instructions in the above-mentioned memory 930 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 can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several 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, etc. Various media that can store program codes.

[0119] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute an image-based vehicle automatic emergency braking system key parameter test system provided by the above methods, the method includes: a data acquisition module, used to acquire image data in front of the vehicle in a simulation scene through a pre-built simulation system;

[0120] A control module, configured to generate a control instruction based on the image data through a preset automatic emergency braking model, and control the vehicle to brake based on the control instruction;

[0121] The braking effect simulation module is used to set different preset values ​​for key parameters during the braking process and simulate the braking effect under different preset values;

[0122] The boundary warning value determination module is used to determine the boundary warning values ​​of different key parameters according to the braking effect.

[0123] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform an image-based vehicle automatic emergency braking system key parameter test system provided by the above methods, the method comprising: a data acquisition module, for acquiring image data in front of the vehicle in a simulation scene through a pre-built simulation system;

[0124] A control module, configured to generate a control instruction based on the image data through a preset automatic emergency braking model, and control the vehicle to brake based on the control instruction;

[0125] The braking effect simulation module is used to set different preset values ​​for key parameters during the braking process and simulate the braking effect under different preset values;

[0126] The boundary warning value determination module is used to determine the boundary warning values ​​of different key parameters according to the braking effect.

[0127] 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.

[0128] 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.

[0129] 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 a vehicle automatic emergency braking system based on an image, characterized in that: include: Acquire image data in front of the vehicle in a simulation scene through a pre-built simulation system; Generate a control instruction based on the image data through a preset automatic emergency braking model, and control the vehicle to brake based on the control instruction; During the braking process, different preset values ​​are set for key parameters to simulate the braking effect under different preset values; Determining boundary warning values ​​of different key parameters according to the braking effect; The step of setting different preset values ​​for key parameters during the braking process and simulating the braking effects under different preset values ​​specifically includes: The resolution of the key parameters is set to a fixed value, the frame rate is changed and different preset values ​​are set for the time delay and the packet loss rate, and the shortest relative distance between the two vehicles is simulated and calculated; The key parameters include: time delay, packet loss rate, resolution and perception output accuracy; The time delay and packet loss rate in the key parameters are set to fixed values, the frame rate is changed and different preset values ​​are set for the resolution in the key parameters, and the shortest relative distance between the two vehicles is simulated and calculated; Set a fixed frame rate, change the resolution and set the perception output accuracy to different preset values, and simulate and calculate the shortest relative distance between the two vehicles.

2. The image-based vehicle automatic emergency braking system key parameter testing method according to claim 1 is characterized in that: The method of obtaining image data in front of the vehicle in a simulation scene by using a pre-built simulation system specifically includes: Collect image data in front of the vehicle through the on-board monocular camera; The front vehicle information is detected based on the image data by using a pre-trained vehicle detection model.

3. The image-based vehicle automatic emergency braking system key parameter testing method according to claim 1 is characterized in that: The generating a control instruction based on the image data through a preset automatic emergency braking model, and controlling the vehicle to brake based on the control instruction specifically includes: Calculating the collision time between the two vehicles through a preset automatic emergency braking model according to the front vehicle information detected in the image data; A control instruction is generated according to the collision time, and the vehicle is controlled by the control instruction to perform full braking, partial braking or issue a warning.

4. The image-based vehicle automatic emergency braking system key parameter testing method according to claim 1, characterized in that: Determining the boundary warning values ​​of different key parameters according to the braking effect specifically includes: When the shortest relative distance between the two vehicles is greater than zero, the corresponding key parameter is the boundary warning value.

5. An image-based vehicle automatic emergency braking system key parameter testing system, characterized in that: The system comprises: A data acquisition module, used to acquire image data in front of the vehicle in a simulation scene through a pre-built simulation system; A control module, configured to generate a control instruction based on the image data through a preset automatic emergency braking model, and control the vehicle to brake based on the control instruction; The braking effect simulation module is used to set different preset values ​​for key parameters during the braking process and simulate the braking effect under different preset values; A boundary warning value determination module, used to determine boundary warning values ​​of different key parameters according to the braking effect; The step of setting different preset values ​​for key parameters during the braking process and simulating the braking effects under different preset values ​​specifically includes: The resolution of the key parameters is set to a fixed value, the frame rate is changed and different preset values ​​are set for the time delay and the packet loss rate, and the shortest relative distance between the two vehicles is simulated and calculated; The key parameters include: time delay, packet loss rate, resolution and perception output accuracy; The time delay and packet loss rate in the key parameters are set to fixed values, the frame rate is changed and different preset values ​​are set for the resolution in the key parameters, and the shortest relative distance between the two vehicles is simulated and calculated; Set a fixed frame rate, change the resolution and set the perception output accuracy to different preset values, and simulate and calculate the shortest relative distance between the two vehicles.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the image-based vehicle automatic emergency braking system key parameter testing method as described in any one of claims 1 to 4 is implemented.

7. 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 image-based vehicle automatic emergency braking system key parameter testing method as described in any one of claims 1 to 4 is implemented.

Images