A vehicle lane line estimation method and device and a storage medium

Abstract

The application provides a vehicle lane line estimation method, device and storage medium, comprising: a processor of a first vehicle processing position information of each target vehicle trajectory point based on vehicle information and road confidence to obtain trajectory point coordinates; for each target vehicle, processing based on driving speed, trajectory point coordinates and the number of target vehicle trajectory points to obtain corresponding fitting trajectory score and fitting trajectory parameters; determining the corresponding lane line according to the fitting trajectory score, the fitting trajectory parameters, the vehicle information and the road confidence, to determine whether the position information of the next trajectory point of the target vehicle is the same as the driving target of the first vehicle based on the lane line. The application determines the trajectory point coordinates to improve the accuracy of trajectory fitting based on the road curvature of the trajectory of the preceding vehicle, thereby improving the accuracy of the lane target determination.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a method, apparatus and storage medium for predicting vehicle travel routes. Background Technology

[0002] Currently, there are two common methods for determining whether the vehicle in front is a target in this lane.

[0003] The first method relies on lane lines and their parameters calculated by visual sensors to determine whether the vehicle in front is a target in the lane. However, this method is often unsuitable for scenarios without lane lines because it cannot determine whether a vehicle at a greater distance is a target in the lane due to obstruction of lane lines at a distance.

[0004] The second method involves recording the lateral and longitudinal positions of the preceding vehicle relative to the following vehicle over a period of time and the trajectory they form to fit a curve. Based on the parameters of the fitted curve, the approximate position of the current lane line can be determined. Furthermore, the relative position of the preceding vehicle to the estimated current lane line or the parameters of the fitted curve can be used to determine whether the preceding vehicle is a target in the current lane. However, since the lateral speed of the following vehicle and the accuracy of the distance sensor are not considered, the accuracy of the judgment made in the above method is not high. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a method, apparatus and storage medium for estimating vehicle driving lanes to solve the problem of low recognition accuracy in the prior art.

[0006] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0007] A first aspect of this invention discloses a method for estimating vehicle lane lines, applied to a processor of a first vehicle, the method comprising:

[0008] The location information and speed of the target vehicle trajectory point in front of the first vehicle are obtained at preset time intervals, and the vehicle information and road confidence of the first vehicle are collected. The road confidence includes left confidence and right confidence.

[0009] Based on the vehicle information and the road confidence level, the location information of each target vehicle trajectory point is processed to obtain the trajectory point coordinates;

[0010] For each target vehicle, the driving speed, trajectory point coordinates, and the number of trajectory points of the target vehicle are processed to obtain the corresponding fitted trajectory score and fitted trajectory parameters.

[0011] Based on the fitted trajectory score, the fitted trajectory parameters, the vehicle information, and the road confidence score, a corresponding road line is determined, so as to determine whether the position information of the next trajectory point of the target vehicle is the same as the driving target of the first vehicle based on the road line.

[0012] Optionally, the step of processing the location information of each target vehicle trajectory point based on the vehicle information and the road confidence score to obtain trajectory point coordinates includes:

[0013] Calculate the lateral speed of the first vehicle based on the vehicle information;

[0014] Using the vehicle information and lateral velocity of the first vehicle, coordinate transformation is performed on the position information of all collected trajectory points of each target vehicle to obtain the initial coordinates of the trajectory points;

[0015] The initial coordinates of the trajectory points are corrected based on the road confidence level to obtain the trajectory point coordinates.

[0016] Optionally, the step of correcting the initial coordinates of the trajectory points based on the road confidence to obtain the trajectory point coordinates includes:

[0017] The target confidence parameter is obtained by processing based on left and right confidence levels.

[0018] The initial coordinates of the trajectory point are corrected using the target confidence parameter to obtain the trajectory point coordinates.

[0019] Optionally, for each target vehicle, processing is performed based on the driving speed, trajectory point coordinates, and the number of trajectory points of the target vehicle to obtain the corresponding fitted trajectory score and fitted trajectory parameters, including:

[0020] For each target vehicle, a first score is determined based on the target vehicle's speed and the relative distance between the target vehicle and the first vehicle in the vehicle information.

[0021] The second score is determined based on the coordinates of all trajectory points of the target vehicle.

[0022] The third score is determined based on the number of trajectory points of all trajectory points of the target vehicle;

[0023] The fourth score is determined based on the target vehicle's speed and the first parameter;

[0024] The fifth score is determined based on the second parameter of the target vehicle;

[0025] An evaluation score is obtained by calculating based on the first score, the second score, the third score, the fourth score, and the fifth score;

[0026] Multi-trajectory fusion is performed based on the evaluation score of each target vehicle and the vehicle reference parameters to obtain the fitted trajectory score and fitted trajectory parameters. The vehicle reference parameters are determined by fitting the coordinates of the trajectory points.

[0027] Optionally, determining the corresponding lane line based on the fitted trajectory score, the fitted trajectory parameters, the vehicle information, and the road confidence score includes:

[0028] If it is determined that both the left confidence level and the right confidence level are higher than the preset track confidence level threshold, processing is performed based on the left confidence level and the right confidence level to obtain the target confidence parameter;

[0029] The road line is obtained by calculating based on the fitted trajectory score, fitted trajectory parameters, road confidence, vehicle information, and target confidence parameters.

[0030] If the left confidence level and the right confidence level are lower than or equal to the preset track confidence threshold, the track is calculated based on the preset track width and the fitted trajectory parameters to obtain the track.

[0031] Optionally, after processing the location information of each target vehicle trajectory point based on the vehicle information and the road confidence score to obtain the trajectory point coordinates, the method further includes:

[0032] Determine if the coordinates of the previous trajectory point of the target vehicle exist;

[0033] If it exists, calculate the first difference between the trajectory point coordinates of the current trajectory point and the trajectory point coordinates of the previous trajectory point;

[0034] When the first difference is determined to be greater than the preset longitudinal distance difference or less than 0, the following step is performed: for each target vehicle, processing is performed based on the driving speed, trajectory point coordinates, and the number of trajectory points of the target vehicle to obtain the corresponding fitted trajectory score and fitted trajectory parameters.

[0035] Optional, also includes:

[0036] Compare the coordinates of the current trajectory point with the coordinates of the previous trajectory point;

[0037] If the vertical coordinate of the current trajectory point is less than the vertical coordinate of the previous trajectory point, the number and the corresponding trajectory point coordinate of the target vehicle are deleted.

[0038] Optionally, determining whether the position information of the next trajectory point of the target vehicle is the same as the driving target of the first vehicle based on the road line includes:

[0039] Collect the location information of the next trajectory point of the target vehicle;

[0040] Based on the lateral position of the new trajectory point, determine whether the target vehicle will be located within the lane.

[0041] If it is determined that the target vehicle will be located within the lane, the position information of the next trajectory point of the target vehicle is determined to be the same as the driving target of the first vehicle.

[0042] A second aspect of the present invention discloses a vehicle lane prediction device, applied to a processor of a first vehicle, the device comprising:

[0043] The acquisition unit is used to acquire the position information and driving speed of the target vehicle trajectory point in front of the first vehicle at preset time intervals, and to collect the vehicle information and road confidence of the first vehicle, wherein the road confidence includes left confidence and right confidence.

[0044] The processing unit is configured to process the position information of each target vehicle trajectory point based on the vehicle information and the road confidence score to obtain trajectory point coordinates; for each target vehicle, the processing unit is configured to process the driving speed, trajectory point coordinates, and the number of target vehicle trajectory points to obtain a corresponding fitted trajectory score and fitted trajectory parameters; and determine the corresponding road line based on the fitted trajectory score, the fitted trajectory parameters, the vehicle information, and the road confidence score, so as to determine whether the position information of the next trajectory point of the target vehicle is the same as the driving target of the first vehicle based on the road line.

[0045] A third aspect of the present invention discloses a storage medium comprising a stored program, wherein, when the program is executed, the device on which the storage medium is located executes a vehicle lane prediction method as shown in the first aspect of the present invention.

[0046] Based on the above embodiments of the present invention, a method, apparatus, and storage medium for estimating vehicle driving lanes are provided and applied to a processor of a first vehicle. The method includes: acquiring the position information and driving speed of a target vehicle trajectory point ahead of the first vehicle at preset time intervals, and collecting vehicle information and road confidence of the first vehicle; processing the position information of each target vehicle trajectory point based on the vehicle information and the road confidence to obtain trajectory point coordinates; for each target vehicle, processing based on the driving speed, trajectory point coordinates, and the number of target vehicle trajectory points to obtain a corresponding fitted trajectory score and fitted trajectory parameters; determining the corresponding lane based on the fitted trajectory score, the fitted trajectory parameters, the vehicle information, and the road confidence, and judging whether the position information of the next trajectory point of the target vehicle is the same as the driving target of the first vehicle based on the lane. In the embodiments of the present invention, the coordinate system transformation of the target vehicle's position information through vehicle information is performed to improve the accuracy of trajectory fitting based on the road curvature of the preceding vehicle's trajectory, thereby improving the accuracy of target judgment in the current lane. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0048] Figure 1 This is a schematic diagram of the vehicle architecture shown in an embodiment of the present invention;

[0049] Figure 2 This is a flowchart illustrating a method for estimating vehicle lane lines according to an embodiment of the present invention.

[0050] Figure 3 This is a schematic diagram illustrating the location information of the target vehicle's trajectory points in an embodiment of the present invention.

[0051] Figure 4 This is a schematic diagram illustrating the lateral distance of the lane lines of the first vehicle according to an embodiment of the present invention;

[0052] Figure 5 This is a flowchart illustrating another method for estimating vehicle lane lines according to an embodiment of the present invention.

[0053] Figure 6 This is a schematic diagram illustrating the process of trajectory point coordinate changes according to an embodiment of the present invention;

[0054] Figure 7This is a schematic diagram of the structure of a vehicle lane prediction device according to an embodiment of the present invention. Detailed Implementation

[0055] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0057] It should be noted that the descriptions involving "first," "second," etc., in this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0058] In this application, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0059] See Figure 1 This is a schematic diagram of the vehicle architecture shown in an embodiment of the present invention;

[0060] The vehicle includes a processor 10 and sensors 20, with the processor 10 connected to various sensors 20.

[0061] The sensor 20 may include at least a vision sensor, a distance sensor, and a speed detection sensor.

[0062] Based on the vehicle architecture shown in the above embodiments of the present invention, the specific method for predicting the vehicle's driving lane includes:

[0063] The processor 10 acquires the position information and speed of the target vehicle trajectory points collected by the sensor 20 in the first vehicle at preset time intervals, as well as the vehicle information and road confidence level of the first vehicle. The number of target vehicles is at least one, and the target vehicle is the vehicle in front of the first vehicle and is marked with a number. Based on the vehicle information and the road confidence level, the position information of each target vehicle trajectory point is processed to obtain the trajectory point coordinates. For each target vehicle, based on the speed, trajectory point coordinates, and the number of target vehicle trajectory points, the corresponding fitted trajectory score and fitted trajectory parameters are obtained. The corresponding road line is determined according to the fitted trajectory score, the fitted trajectory parameters, the vehicle information, and the road confidence level.

[0064] In this embodiment of the invention, the position information of each target vehicle trajectory point is processed based on vehicle information and the road confidence score to obtain trajectory point coordinates; then, the fitted trajectory score and fitted trajectory parameters corresponding to each target vehicle are determined; and the corresponding lane line is determined based on the fitted trajectory score, fitted trajectory parameters, vehicle information, and road confidence score. This invention performs coordinate system transformation on the target vehicle's position information using vehicle information and introduces the vehicle's lateral velocity during the coordinate system transformation process to improve the accuracy of trajectory fitting based on the road curvature of the preceding vehicle's trajectory, thereby improving the accuracy of target judgment within the current lane.

[0065] See Figure 2 This is a flowchart illustrating a method for predicting vehicle lane lines according to an embodiment of the present invention. The method includes:

[0066] Step S201: Obtain the location information and driving speed of the target vehicle in front of the first vehicle at a preset time interval, and collect the vehicle information and road confidence of the first vehicle.

[0067] In step S201, the number of target vehicles is at least one, and the target vehicle is the vehicle marked with a number in front of the first vehicle.

[0068] It should be noted that there are multiple implementation methods for the specific implementation step S201.

[0069] In the first implementation, the processor sets all vehicles in front of the first vehicle's location, as target vehicles, as detected by the vision sensors installed on the first vehicle, and assigns a number to each target vehicle. The processor acquires the position information of the current trajectory point of the target vehicle collected by the vision sensors at preset time intervals, and acquires the driving speed of the target vehicle collected by the speed sensor. Then, the processor acquires vehicle information of the first vehicle itself through its various other sensors, and controls the vision sensors to identify the left confidence level of the left lane line in front of the first vehicle, and the right confidence level of the right lane line in front of the first vehicle.

[0070] It should be noted that the road confidence level includes left confidence level and right confidence level.

[0071] In the second implementation, the processor uses a vision sensor installed on the first vehicle to collect information on vehicles within a preset distance in front of the first vehicle, designates them all as target vehicles, and assigns a number to each target vehicle. The processor acquires the position information of the current trajectory point of the target vehicle collected by the vision sensor at preset time intervals, and acquires the driving speed of the target vehicle collected by the speed sensor. Then, the processor collects vehicle information of the first vehicle itself through its various other sensors, and controls the vision sensor to identify the left confidence level of the lane line on the left side in front of the first vehicle, and the right confidence level of the lane line on the right side in front of the first vehicle.

[0072] For example: Figure 3 As shown, this coordinate axis passes through a preset time interval t thres The target vehicle collected is the vehicle whose horizontal and vertical coordinates are recorded during the current sampling period. , ); where n is the vehicle number, t is the sampling time, and sampling time t=0 is the data entered at the current recording time, i.e. ( , The sampling time t=1 is the data recorded at the previous recording time, that is ( , ), and so on.

[0073] It should be noted that the other sensors include at least a speed sensor.

[0074] The vehicle information includes the rear wheel lateral stiffness kr, the distance from the vehicle's center of gravity to the front axle lf, the distance from the vehicle's center of gravity to the rear axle lr, the vehicle's wheelbase l, the vehicle's speed vx, the vehicle's yaw rate, the vehicle's mass m, the vehicle's lateral acceleration ay, and the vehicle speed vx of the first vehicle.

[0075] The preset time interval is set by technicians based on multiple experiments or experience, such as collecting data once per second.

[0076] In embodiments of the present invention, such as Figure 4 As shown, the coordinate axes are expanded with the vehicle's sensor as the origin, the direction the sensor faces (i.e., the direction the vehicle is facing) as the positive X-axis, and the direction to the right of the sensor as the positive Y-axis. The lateral distances of the lane lines to the left and right, represented by solid curves, provided by the vision sensor are recorded, specifically the lateral distance C0 of the left lane line. Left The lateral distance C0 between the lane and the right lane. Right And the left angle C1 formed by the lane line and the longitudinal axis due to the vehicle's yaw angle. Left and the right angle C1 Right The value, such as Figure 4 As shown by the vertical and slanted dashed lines, this means that the vehicle information includes the lateral distance C0 of the left lane. Left The lateral distance C0 of the right lane Right The left angle C1 formed by the lane line and the longitudinal axis due to the vehicle's yaw angle Left , and the right angle C1 Right The value.

[0077] Step S202: Process the location information of each target vehicle trajectory point based on the vehicle information and the road confidence level to obtain the trajectory point coordinates.

[0078] It should be noted that the specific implementation process of step S203 includes the following steps:

[0079] Step S11: Calculate the lateral speed of the first vehicle based on the vehicle information.

[0080] It should be noted that the specific implementation of step S11 includes the following steps:

[0081] Step S21: Calculate the vehicle sideslip angle of the first vehicle using the vehicle rear wheel sideslip stiffness, distance from the vehicle center of gravity to the front axle, distance from the vehicle center of gravity to the rear axle, vehicle wheelbase, vehicle speed, vehicle yaw rate, vehicle mass, and vehicle lateral acceleration from the vehicle information.

[0082] In the specific implementation step S21, the following information is used to substitute the vehicle rear wheel lateral stiffness, the distance from the vehicle center of gravity to the front axle lf, the distance from the vehicle center of gravity to the rear axle lr, the vehicle wheelbase l, the vehicle speed vx, the vehicle yaw rate, the vehicle mass m, and the vehicle lateral acceleration ay into formula (1) to obtain the vehicle lateral angle.

[0083] Formula (1):

[0084] (1)

[0085] in, For vehicle sideslip angle, The distance from the vehicle's center of gravity to the rear axle. For the rear wheel lateral stiffness of the vehicle, The distance from the vehicle's center of gravity to the front axle. for , For vehicle speed for , For vehicle quality, .

[0086] Step S22: Calculate the lateral speed vy of the first vehicle based on the vehicle sideslip angle and the vehicle speed in the vehicle information.

[0087] In the specific implementation step S22, the vehicle side slip angle calculated by the above formula (1) and the vehicle speed in the vehicle information are substituted into formula (2) to calculate the lateral speed vy of the first vehicle.

[0088] Formula (2):

[0089] (2)

[0090] in, for , For vehicle sideslip angle, For vehicle speed.

[0091] Step S12: Using the vehicle information and lateral velocity of the first vehicle, perform coordinate transformation on the position information of all collected trajectory points of each target vehicle to obtain the initial coordinates of the trajectory points;

[0092] In this embodiment of the invention, considering that the vehicle, i.e. the first vehicle, is moving, the position of the same trajectory point in the vehicle's coordinate system is different at different times, and considering that the lateral speed of the vehicle will affect the accuracy of trajectory fitting, it is necessary to perform coordinate system transformation on all recorded trajectory points of the preceding vehicle at each sampling time using the following formula.

[0093] For each target vehicle, the vehicle information of the first vehicle, namely the distance from the vehicle's center of gravity to the rear axle, the rear wheel lateral stiffness, and the distance from the vehicle's center of gravity to the front axle, is collected. Vehicle speed Vehicle quality , The acquisition time of the location information corresponding to each trajectory point of the target vehicle and the current acquisition number are substituted into formulas (3) and (4) to perform coordinate system transformation through formulas (3) and (4) to obtain the initial coordinates of the trajectory points.

[0094] It should be noted that the initial coordinates of the trajectory point include the initial vertical coordinates and the initial horizontal coordinates of the transformed trajectory point.

[0095] Formula (3):

[0096] (3)

[0097] Formula (4):

[0098] (4)

[0099] in, These are the initial longitudinal coordinates of the transformed trajectory points. These are the initial horizontal coordinates of the transformed trajectory points. The distance from the vehicle's center of gravity to the rear axle. For the rear wheel lateral stiffness of the vehicle, The distance from the vehicle's center of gravity to the front axle. for , For vehicle speed, for , For vehicle quality, , for Δt is the sampling time difference, t is the number of samplings, and n is the target vehicle number.

[0100] Optionally, if the line confidence is low or there is no line, the road confidence C1 is 0, and the initial coordinates of the point are not corrected, i.e., step S13 is not executed.

[0101] Step S13: Correct the initial coordinates of the trajectory points based on the road confidence level to obtain the coordinates of the trajectory points.

[0102] In this embodiment of the invention, since the existing trajectory point closure does not take into account the angle between the road line and the longitudinal axis caused by the vehicle yaw angle, and this angle will bring errors to the road curvature obtained by trajectory fitting, it is necessary to first rotate the trajectory points using the following formula to eliminate the influence of this angle.

[0103] The specific implementation process of step S13 includes the following steps:

[0104] Step S31: Process based on left confidence and right confidence to obtain target confidence parameters.

[0105] In step S31, the left confidence level and the right confidence level belong to the road confidence level.

[0106] In the specific implementation step S31, the processor controls the vision sensor to identify the left confidence level of the left lane line in front of the first vehicle and the right confidence level of the right lane line in front of the first vehicle; and substitutes the left confidence level and the right confidence level into formula (5) to obtain the target confidence parameter.

[0107] Formula (5):

[0108] (5)

[0109] in, For left confidence level, For right confidence level, s is a pre-set track confidence threshold, used to represent high track confidence; C1 Left C1 is the left angle formed by the lane line and the longitudinal axis due to the vehicle's yaw angle. Right C1 is the right angle formed by the lane line and the longitudinal axis due to the vehicle's yaw angle, and C1 is the target confidence parameter.

[0110] Step S32: Correct the initial coordinates of the trajectory point using the target confidence parameter to obtain the trajectory point coordinates.

[0111] It should be noted that the trajectory point coordinates include the horizontal coordinates and vertical coordinates of the trajectory point target.

[0112] In the specific implementation of step S32, the road confidence C1 and the initial coordinates of the trajectory points calculated by formulas (3) and (4) are substituted into formulas (6) and (7) to obtain the coordinates of the trajectory points.

[0113] Formula (6):

[0114] (6)

[0115] Formula (7):

[0116] (7)

[0117] in, The vertical coordinate of the target The horizontal coordinate of the target This refers to the initial longitudinal coordinates of the transformed trajectory points calculated by formula (3). It refers to the initial horizontal coordinates of the transformed trajectory points obtained by formula (4).

[0118] Step S203: For each target vehicle, process the data based on the driving speed, trajectory point coordinates, and the number of trajectory points of the target vehicle to obtain the corresponding fitted trajectory score and fitted trajectory parameters.

[0119] In step S203, the vehicle reference parameters are determined by trajectory fitting of the coordinates of the trajectory points.

[0120] It should be noted that the vehicle baseline parameters include the first parameter. Second parameter .

[0121] In this embodiment of the invention, the process of determining the vehicle reference parameters by trajectory fitting of the trajectory point coordinates is as follows: for each target vehicle, the trajectory point coordinates of multiple trajectory points collected within a preset time interval of the target vehicle are fitted using the least squares formula, that is, the target horizontal coordinate and target vertical coordinate of each trajectory point are substituted into formulas (8) and (9) for calculation to obtain the vehicle reference parameters.

[0122] Formula (8):

[0123] (8)

[0124] Formula (9):

[0125] (9)

[0126] in, , As the first parameter, This is the second parameter.

[0127] It should be noted that the specific implementation of step S203 includes the following steps:

[0128] Step S41: For each target vehicle, determine a first score S1 based on the target vehicle's speed and the relative distance between the target vehicle and the first vehicle in the vehicle information. n .

[0129] In the specific implementation step S41, for each target vehicle, the processor sequentially obtains the driving speed of the target vehicle according to its number, and uses the relative distance between the target vehicle and the first vehicle mentioned in the vehicle information as the basis for querying the first dimension table to obtain the first score S1. n .

[0130] It should be noted that the first dimension table is used to store the target vehicle's speed, the relative distance between the target vehicle and the first vehicle, and the first score S1. n The correspondence between them.

[0131] The target vehicle's speed, the relative distance between the target vehicle and the first vehicle, and the first score S1 are pre-constructed in the first dimension table based on multiple experiments. n The correspondence between them.

[0132] It should be further noted that the faster the target vehicle travels, the higher the first score S1. n The higher the value, the closer the relative distance, and its first score S1 n And the higher;

[0133] For example, a vehicle traveling at 20 kph and 30 m in front of it scores 80 points, while a vehicle traveling at 10 kph and 80 m in front of it scores 30 points.

[0134] Step S42: Determine the second fraction S2 based on the trajectory point coordinates of all trajectory points of the target vehicle. n ;

[0135] In the specific implementation step S42, for each target vehicle, the processor obtains the trajectory point coordinates of all trajectory points stored for the corresponding number of the current target vehicle; calculates the longitudinal coordinates in the trajectory point coordinates to calculate the longitudinal distance, obtains the length of the trajectory segment, and uses the length to query the second dimension table to obtain the second score S2. n ;

[0136] It should be noted that the second dimension table is used to store the length of the trajectory and the second score S2. n The correspondence between them.

[0137] The length of the trajectory and the second score S2 in the second-dimensional table are constructed in advance based on multiple experiments. n The correspondence between them.

[0138] It should be further noted that the longer the trajectory, the higher its corresponding second fraction S2. n The higher the temperature, the better.

[0139] For example, a trajectory segment with a maximum longitudinal distance of 30m is worth 60 minutes, and a trajectory segment with a maximum length of 80m is worth 80 minutes.

[0140] Step S43: Determine the third fraction S3 based on the number of trajectory points of all trajectory points of the target vehicle. n ;

[0141] In the specific implementation step S43, for each target vehicle, the processor obtains the number of trajectory points of all trajectory points stored for the corresponding number of the current target vehicle; and queries the third dimension table by the number of trajectory points to obtain the third score S3. n ;

[0142] It should be noted that the third dimension table is used to store the number of trajectory points and the third score S3. n The correspondence between them.

[0143] The length of the trajectory and the third fraction S3 in the third-dimensional table are constructed in advance based on multiple experiments. n The correspondence between them.

[0144] It should be further noted that the more trajectory points there are, the higher the corresponding third score S3. n The higher the temperature, the better.

[0145] For example, the third fraction S3 corresponding to 10 trajectory points. n It scores 60 points.

[0146] Step S44: Based on the target vehicle's speed and the first parameter C2 n Determine the fourth fraction S4 n ;

[0147] In the specific implementation step S44, for each target vehicle, the processor obtains the vehicle's speed and the first parameter C2 calculated above. n To pass through the driving speed and the first parameter C2 n Querying the fourth dimension table yields the fourth score, S4. n ;

[0148] It should be noted that the fourth dimension table is used to store the driving speed and the first parameter C2. n , and the fourth score S4 n The correspondence between them.

[0149] The fourth dimension table, constructed in advance based on multiple experiments, contains the driving speed and the first parameter C2. n , and the fourth score S4 n The correspondence between them.

[0150] It should be further explained that the first parameter C2 n The larger the value, the higher its corresponding fourth score S4. n The lower the value, the better.

[0151] Step S45: Based on the second parameter C0 of the target vehicle n Determine the fifth fraction S5 n ;

[0152] In the specific implementation of step S45, for each target vehicle, the processor obtains the second parameter C0 of the target vehicle. n , so as to pass the second parameter C0 n Querying the fifth dimension table yields the fifth score, S5. n ;

[0153] It should be noted that the fifth dimension table is used to store the second parameter C0. n , with the fifth score S5 n The correspondence between them.

[0154] The second parameter C0 in the fifth dimension table is constructed in advance based on multiple experiments. n , with the fifth score S5 n The correspondence between them.

[0155] It should be further noted that the second parameter C0 n The greater the deviation from the current lane width by an integer multiple, the higher the fifth score S5. n The lower.

[0156] Step S46: Calculate the evaluation score based on the first score, the second score, the third score, the fourth score, and the fifth score.

[0157] In the specific implementation step S46, the first score, second score, third score, fourth score and fifth score are substituted into formula (10) for calculation to obtain the evaluation score. .

[0158] Formula (10):

[0159] (10)

[0160] Here, min refers to taking the smaller value among the values ​​within the parentheses. It is a score of the quality of the trajectory points of the generated trajectory. The faster the target vehicle, i.e. the vehicle in front, is moving, the farther the expected distribution of the future trajectory points will be. The closer the relative distance, the higher the probability of accurate sensor recognition. The longer the trajectory and the more points there are, the higher the expected quality of the trajectory generated from the current trajectory points.

[0161] This is a score for the generated fitted trajectory. Based on the proportion of curves in the overall road conditions, when the first parameter C2_n is maximized, the resulting fitted trajectory is likely to be inaccurate. Similarly, the second parameter C0... n This represents the lateral position of the fitted trajectory. The further this value deviates from the center of each lane, the lower the probability of accuracy of the fitted trajectory. Taking the smaller value of each part and multiplying them together can weigh various indicators, thus providing a comprehensive evaluation of the quality of each trajectory.

[0162] Step S47: Perform multi-trajectory fusion based on the evaluation score and vehicle baseline parameters of each target vehicle to obtain the fitted trajectory score and fitted trajectory parameters.

[0163] In this embodiment of the invention, the quality of each trajectory can be weighed by the following formulas (11) and (12), and the road curvature information provided by all trajectories can be integrated to provide a score that can be used as confidence, namely the fitted trajectory score.

[0164] In the specific implementation step S47, firstly, the evaluation score of each target vehicle is... Substitute into formula (11) to calculate and obtain the fitted trajectory score.

[0165] Formula (11):

[0166] (11)

[0167] Next, the evaluation score for each target vehicle will be calculated. And the first parameter in the vehicle reference parameters Substituting into formula (12) for calculation, the fitted trajectory parameter C2 is obtained. traj .

[0168] Formula (12):

[0169] (12)

[0170] Optionally, it also includes: determining whether the fitted trajectory score is less than a preset threshold; if it is less, it indicates that the reliability of the final trajectory is low, and the fitted trajectory parameter C2 is not output. traj This indicates that line generation failed and execution should be stopped.

[0171] It should be noted that the preset threshold was set by technicians based on multiple tests or experience.

[0172] C2 traj Including C2 for each vehicle n n That is, C21, C22, C33.

[0173] Step S206: Determine the corresponding road line based on the fitted trajectory score, the fitted trajectory parameters, the vehicle information, and the road confidence score, so as to determine whether the position information of the next trajectory point of the target vehicle is the same as the driving target of the first vehicle based on the road line.

[0174] In this embodiment of the invention, when the fitted trajectory parameter C2 traj When there is output, the road line formula is derived from the road curvature estimation based on the trajectory of the preceding vehicle. This is based on the confidence level of the left and right road line parameters obtained from the visual sensor. and The confidence level of the track is higher than the preset track confidence threshold. If the confidence level is high (e.g., 80 points), it indicates that the visually predicted track line has a high confidence level; in this case, it is weighted and fused with C2 calculated from the above formula based on the confidence levels of both. Conversely, if the confidence level is low, it indicates that there is no track line or the track line quality is poor; in this case, the visual sensor's predicted track line is not used, and the track width is assumed to be a constant value. lane For example, 3.5m, and the vehicle is located in the center of the lane and is traveling along the road ahead.

[0175] It should be noted that the specific implementation of step S206 includes the following steps:

[0176] Step S51: Determine whether the left confidence level and the right confidence level are higher than the preset track confidence threshold, respectively. If the left confidence level is higher than the preset track confidence threshold, The right confidence level is higher than the preset track confidence threshold. Then proceed with steps S52 and S53. If the left confidence level is lower than or equal to the preset track confidence threshold... The right confidence level is lower than or equal to the preset track confidence threshold. Then proceed to step S54.

[0177] In step S51, the left confidence level and the right confidence level belong to the road confidence level.

[0178] Step S52: Process based on the left confidence and right confidence to obtain the target confidence parameter.

[0179] It should be noted that the implementation process of step S52 is the same as that of step S31 above, and they can be referred to each other.

[0180] Step S53: Based on the fitted trajectory score Fitted trajectory parameters C2 traj Road confidence and Vehicle information and target confidence parameters and Calculations are performed to obtain the track line.

[0181] Step S54: Based on the preset lane width lane and the fitted trajectory parameter C2 traj Calculations are performed to obtain the track line.

[0182] In the specific implementation of steps S53 and S54, the fitted trajectory score is... Fitted trajectory parameters C2 traj Road confidence and Lane information , , and Input formula (13) and / or formula (14) to calculate and obtain the track line; set the preset track width. lane and the fitted trajectory parameter C2 traj Enter formula (13) and / or formula (14) to calculate and obtain the track line.

[0183] It should be noted that the lane markings include the left lane markings. and right lane line .

[0184] Formula (13):

[0185] (13)

[0186] Formula (14):

[0187] (14)

[0188] Among them, C2 n These are the C2 parameters of the trajectory of car number n. The C2 parameter is the left path line obtained by fitting the left and right confidence levels collected by the vision sensor according to its own internal first preset path line fitting formula. C2 is the parameter of the right side path obtained by the vision sensor fitting the left and right confidence scores it has collected according to its own first preset path fitting formula. x is the vertical distance, and C3 is the parameter obtained by the vision sensor fitting the left and right confidence scores it has collected according to its own second preset path fitting formula.

[0189] Furthermore, both the first preset track fitting formula and the second preset track fitting formula are preset by technicians based on experience or actual conditions, such as the least squares formula or other formulas, and this embodiment of the invention does not limit them.

[0190] The first preset track fitting formula and the second preset track fitting formula can be the same or different.

[0191] It should be noted that the preset lane width is... lane It is set by technicians based on experience or experiments, for example, it can be set to 3.5m.

[0192] Optionally, the process of determining whether the position information of the next trajectory point of the target vehicle is the same as the driving target of the first vehicle based on the lane line includes: collecting the position information of the next trajectory point of the target vehicle; determining whether the target vehicle will be located within the lane line based on the lateral position in the position information of the new trajectory point; if it is determined that the target vehicle will be located within the lane line, determining that the position information of the next trajectory point of the target vehicle is the same as the driving target of the first vehicle, that is, determining that the target vehicle is the lane target of the first vehicle.

[0193] Specifically, the location information of the target vehicle's new trajectory point, i.e., the next trajectory point, is collected; and the lateral position in the location information is used as a reference. Substituting into formula (15), it is determined whether the target vehicle is within the lane line calculated in step S206 above. That is, based on the lateral position of the latest trajectory point... Lateral position relative to the generated track line at the longitudinal distance from the target ,and The positional relationship determines whether the vehicle in front is in the same lane.

[0194] Formula (15):

[0195] (15)

[0196] It should be noted that, if for This indicates that the target vehicle and the first vehicle have the same driving target. for This indicates that the target vehicle and the first vehicle have different driving goals.

[0197] In this embodiment of the invention, the position information of each target vehicle trajectory point is processed based on vehicle information and road confidence level to obtain trajectory point coordinates; then, the fitted trajectory score and fitted trajectory parameters corresponding to each target vehicle are determined; and the corresponding lane line is determined based on the fitted trajectory score, fitted trajectory parameters, vehicle information, and road confidence level. This invention performs coordinate system transformation on the target vehicle's position information using vehicle information and introduces the vehicle's lateral velocity during the coordinate system transformation process to improve the accuracy of trajectory fitting based on the road curvature of the preceding vehicle's trajectory, thereby improving the accuracy of target judgment within the current lane.

[0198] Based on the flowchart of another vehicle lane prediction method shown in the above embodiments of the present invention, as follows: Figure 5 As shown, the method includes:

[0199] Step S501: Obtain the position information and driving speed of the target vehicle in front of the first vehicle at a preset time interval, and collect the vehicle information and road confidence of the first vehicle.

[0200] In step S501, the number of target vehicles is at least one, and the target vehicle is the vehicle marked with a number in front of the first vehicle.

[0201] Step S502: Process the location information of each target vehicle trajectory point based on the vehicle information and the road confidence level to obtain the trajectory point coordinates.

[0202] Optionally, the trajectory coordinates of the trajectory points can be stored using the target vehicle's identification number.

[0203] It should be noted that the specific implementation process of steps S501 to S502 is the same as that of steps S201 to S202 above, and they can be referred to each other.

[0204] Step S503: Determine if there are trajectory point coordinates of the previous trajectory point of the target vehicle. If there are, proceed to step S504. If not, store the trajectory point coordinates of the vehicle using the number corresponding to the target vehicle.

[0205] In the specific implementation of step S503, firstly, query the database to see if there is a trajectory point with the same number as the target vehicle. If it exists, proceed to step S504. If it does not exist, use the code corresponding to the target vehicle to store the trajectory point information of the vehicle.

[0206] Step S504: Calculate the first difference between the coordinates of the current trajectory point and the coordinates of the previous trajectory point.

[0207] Step S505: Determine whether the first difference is greater than the preset longitudinal distance difference and whether it is less than 0.

[0208] In the specific implementation of steps S504 and S505, the vertical coordinate of the trajectory point coordinates of the current trajectory point is... The vertical coordinate of the trajectory point and the previous trajectory point Substituting into formula (16) for judgment, if the vertical coordinate of the current trajectory point is determined... The vertical coordinate of the trajectory point and the previous trajectory point If the first difference is less than the preset longitudinal distance difference and greater than 0, then step S506 is executed. If it is determined that the first difference is greater than the preset longitudinal distance difference or less than 0, it is determined that a large longitudinal distance jump has occurred, and a new vehicle number is generated. The trajectory point coordinates of the current trajectory point are stored with the new vehicle number.

[0209] Formula (16):

[0210] (16)

[0211] It should be noted that the preset longitudinal distance difference is the preset maximum vehicle speed v thres The permissible longitudinal distance difference per unit sampling time interval, that is, the sampling time interval between the current trajectory point and the previous trajectory point. Inside, the preset maximum vehicle speed v thres The maximum allowable longitudinal distance difference.

[0212] Wherein, the preset maximum vehicle speed v thresIt has been tested multiple times or is based on the markings made when the vehicle leaves the factory.

[0213] For example: Figure 6 As shown, the location of target vehicle number 1 at sampling time t=1, i.e., the location detected at the previous detection time ( , Compared to the position detected at sampling time t=0, i.e., the current detection time ( , ), and the vertical coordinate of the trajectory point coordinates of the current trajectory point The vertical coordinate of the trajectory point and the previous trajectory point Substituting into formula (16) for judgment, if it is determined that the first difference is greater than the preset longitudinal distance difference, it is determined that a large longitudinal distance jump has occurred. Therefore, at time t=0, the new vehicle number 2 is used for subsequent updates and fitting.

[0214] Optionally, it also includes: comparing the coordinates of the current trajectory point with the coordinates of the previous trajectory point; specifically, determining the vertical coordinate of the current trajectory point. Is the vertical coordinate of the trajectory point less than that of the previous trajectory point? If the value is less than 1, it indicates that the target vehicle's identification position is moving backward or in the opposite direction compared to the previous moment. In this case, the target vehicle's number and the corresponding trajectory point coordinates are deleted.

[0215] It should be noted that if the detected target vehicle is moving backward or in the opposite direction compared to the previous moment, it may affect the accuracy of the fitted trajectory. Therefore, the coordinates of this trajectory point are not considered.

[0216] Optionally, it also includes storing the trajectory coordinates of the current trajectory point and the acquisition time using the target vehicle's number.

[0217] Step S506: For each target vehicle, process the data based on the driving speed, trajectory point coordinates, and the number of trajectory points of the target vehicle to obtain the corresponding fitted trajectory score and fitted trajectory parameters.

[0218] Step S507: Determine the corresponding road line based on the fitted trajectory score, the fitted trajectory parameters, the vehicle information, and the road confidence score, so as to determine whether the position information of the next trajectory point of the target vehicle is the same as the driving target of the first vehicle based on the road line.

[0219] It should be noted that the specific implementation process of steps S506 to S507 is the same as that of steps S204 to S205 above, and they can be referred to each other.

[0220] In this embodiment of the invention, the position information of each target vehicle trajectory point is processed based on the vehicle information and the road confidence score to obtain the trajectory point coordinates; then, the fitted trajectory score and fitted trajectory parameters corresponding to each target vehicle are determined; and the corresponding lane line is determined based on the fitted trajectory score, fitted trajectory parameters, vehicle information, and road confidence score. This invention performs coordinate system transformation on the target vehicle's position information using vehicle information and introduces the vehicle's lateral velocity during the coordinate system transformation process, thereby improving the accuracy of trajectory fitting based on the road curvature of the preceding vehicle's trajectory, and thus improving the accuracy of target judgment within the current lane.

[0221] Based on the vehicle lane prediction method shown in the above embodiments of the present invention, correspondingly, the present invention provides a schematic diagram of the structure of a vehicle lane prediction device, as follows: Figure 7 As shown, the device includes:

[0222] The acquisition unit 701 is used to acquire the position information and driving speed of the target vehicle trajectory point in front of the first vehicle at a preset time interval, and to collect the vehicle information and road confidence of the first vehicle, wherein the road confidence includes left confidence and right confidence.

[0223] The processing unit 702 is configured to process the position information of each target vehicle trajectory point based on the vehicle information and the road confidence score to obtain trajectory point coordinates; for each target vehicle, it processes the driving speed, trajectory point coordinates, and the number of target vehicle trajectory points to obtain a corresponding fitted trajectory score and fitted trajectory parameters; and determines the corresponding road line based on the fitted trajectory score, the fitted trajectory parameters, the vehicle information, and the road confidence score, so as to determine whether the position information of the next trajectory point of the target vehicle is the same as the driving target of the first vehicle based on the road line.

[0224] It should be noted that the specific principles and execution processes of each unit in the vehicle lane estimation device disclosed in the above embodiments of this application are the same as the vehicle lane estimation method shown in the above embodiments of this application. Please refer to the corresponding parts in the vehicle lane estimation method disclosed in the above embodiments of this application, and they will not be repeated here.

[0225] In this embodiment of the invention, the position information of each target vehicle trajectory point is processed based on the vehicle information and the road confidence score to obtain the trajectory point coordinates; then, the fitted trajectory score and fitted trajectory parameters corresponding to each target vehicle are determined; and the corresponding lane line is determined based on the fitted trajectory score, fitted trajectory parameters, vehicle information, and road confidence score. This invention performs coordinate system transformation on the target vehicle's position information using vehicle information and introduces the vehicle's lateral velocity during the coordinate system transformation process, thereby improving the accuracy of trajectory fitting based on the road curvature of the preceding vehicle's trajectory, and thus improving the accuracy of target judgment within the current lane.

[0226] Optionally, based on the vehicle lane prediction device shown in the above embodiments of the present invention, the processing unit 702, which processes the position information of each target vehicle trajectory point based on the vehicle information and the road confidence level to obtain the trajectory point coordinates, is specifically used for:

[0227] Calculate the lateral speed of the first vehicle based on the vehicle information;

[0228] Using the vehicle information and lateral velocity of the first vehicle, coordinate transformation is performed on the position information of all collected trajectory points of each target vehicle to obtain the initial coordinates of the trajectory points;

[0229] The initial coordinates of the trajectory points are corrected based on the road confidence level to obtain the trajectory point coordinates.

[0230] Optionally, the step of correcting the initial coordinates of the trajectory points based on road confidence to obtain the trajectory point coordinates includes:

[0231] Based on the left and right confidence levels, the target confidence parameters are obtained.

[0232] The initial coordinates of the trajectory point are corrected using the target confidence parameter to obtain the trajectory point coordinates.

[0233] Optionally, based on the vehicle lane prediction device shown in the above embodiments of the present invention, a processing unit 702, for each target vehicle, processes the driving speed, trajectory point coordinates, number of target vehicle trajectory points, and vehicle reference parameters to obtain the corresponding fitted trajectory score and fitted trajectory parameters, specifically used for:

[0234] For each target vehicle, a first score is determined based on the target vehicle's speed and the relative distance between the target vehicle and the first vehicle in the vehicle information.

[0235] The second score is determined based on the coordinates of all trajectory points of the target vehicle.

[0236] The third score is determined based on the number of trajectory points of all trajectory points of the target vehicle;

[0237] The fourth score is determined based on the target vehicle's speed and the first parameter;

[0238] The fifth score is determined based on the second parameter of the target vehicle;

[0239] An evaluation score is obtained by calculating based on the first score, the second score, the third score, the fourth score, and the fifth score;

[0240] Multi-trajectory fusion is performed based on the evaluation score of each target vehicle and the vehicle baseline parameters to obtain the fitted trajectory score and fitted trajectory parameters.

[0241] Optionally, in the vehicle lane prediction device shown in the above embodiments of the present invention, the processing unit 702 for determining the corresponding lane based on the fitted trajectory score, the fitted trajectory parameters, the vehicle information, and the road confidence score is specifically used for:

[0242] If the left confidence level and the right confidence level are higher than the preset track confidence threshold, the target confidence parameter is obtained by processing based on the left confidence level and the right confidence level.

[0243] Based on the fitted trajectory score, fitted trajectory parameters, road confidence, vehicle information, and target confidence parameters, the road line is obtained through processing.

[0244] If the left confidence level and the right confidence level are lower than or equal to the preset track confidence threshold, the track is processed based on the preset track width and the fitted trajectory parameters to obtain the track.

[0245] Optionally, based on the vehicle lane prediction device shown in the above embodiments of the present invention, the processing unit 702 is further configured to:

[0246] After processing the location information of each target vehicle trajectory point based on the vehicle information and the road confidence level to obtain the trajectory point coordinates, it is determined whether there are trajectory point coordinates of the previous trajectory point of the target vehicle.

[0247] If it exists, calculate the first difference between the trajectory point coordinates of the current trajectory point and the trajectory point coordinates of the previous trajectory point;

[0248] When the first difference is determined to be greater than the preset longitudinal distance difference or less than 0, processing is performed for each target vehicle based on the driving speed, trajectory point coordinates, and the number of trajectory points of the target vehicle to obtain the corresponding fitted trajectory score and fitted trajectory parameters.

[0249] Optionally, based on the vehicle lane prediction device shown in the above embodiments of the present invention, the processing unit 702 is further configured to:

[0250] Compare the coordinates of the current trajectory point with the coordinates of the previous trajectory point;

[0251] If the vertical coordinate of the current trajectory point is less than the vertical coordinate of the previous trajectory point, the number and the corresponding trajectory point coordinate of the target vehicle are deleted.

[0252] Optionally, in the vehicle lane prediction device shown in the above embodiments of the present invention, the processing unit 702, which determines whether the position information of the next trajectory point of the target vehicle is the same as the driving target of the first vehicle based on the lane, is specifically used for:

[0253] Collect the location information of the next trajectory point of the target vehicle;

[0254] Based on the lateral position of the new trajectory point, determine whether the target vehicle will be located within the lane.

[0255] If it is determined that the target vehicle will be located within the lane, the position information of the next trajectory point of the target vehicle is determined to be the same as the driving target of the first vehicle.

[0256] This invention also discloses an electronic device for running database stored procedures, wherein running the database stored procedures involves executing the above-described... Figures 2 to 5 Publicly available methods for estimating vehicle lane lines.

[0257] This invention also discloses a storage medium, which includes a stored database procedure, wherein, during the execution of the stored database procedure, the device where the storage medium is located is controlled to execute the above-mentioned... Figures 2 to 5 Publicly available methods for estimating vehicle lane lines.

[0258] In the context of this disclosure, a storage medium may be a tangible medium that may contain or store programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0259] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the descriptions in the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0260] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0261] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting vehicle lane lines, characterized in that, The method, applied to a processor in a first vehicle, includes: The location information and speed of the target vehicle trajectory point in front of the first vehicle are obtained at preset time intervals, and the vehicle information and road confidence of the first vehicle are collected. The road confidence includes left confidence and right confidence. Based on the vehicle information and the road confidence level, the location information of each target vehicle trajectory point is processed to obtain the trajectory point coordinates; For each target vehicle, the driving speed, trajectory point coordinates, and the number of trajectory points of the target vehicle are processed to obtain the corresponding fitted trajectory score and fitted trajectory parameters. Based on the fitted trajectory score, the fitted trajectory parameters, the vehicle information, and the road confidence score, a corresponding road line is determined, so as to determine whether the position information of the next trajectory point of the target vehicle is the same as the driving target of the first vehicle based on the road line. The step of processing the location information of each target vehicle trajectory point based on the vehicle information and the road confidence score to obtain the trajectory point coordinates includes: Calculate the lateral speed of the first vehicle based on the vehicle information; Using the vehicle information and lateral velocity of the first vehicle, coordinate transformation is performed on the position information of all collected trajectory points of each target vehicle to obtain the initial coordinates of the trajectory points; The initial coordinates of the trajectory points are corrected based on the road confidence level to obtain the trajectory point coordinates; The step of determining the corresponding lane line based on the fitted trajectory score, the fitted trajectory parameters, the vehicle information, and the road confidence score includes: If it is determined that both the left confidence level and the right confidence level are higher than the preset track confidence level threshold, processing is performed based on the left confidence level and the right confidence level to obtain the target confidence parameter; The road line is obtained by calculating based on the fitted trajectory score, fitted trajectory parameters, road confidence, vehicle information, and target confidence parameters. If the left confidence level and the right confidence level are lower than or equal to the preset track confidence threshold, the track is calculated based on the preset track width and the fitted trajectory parameters to obtain the track.

2. The method according to claim 1, characterized in that, The process of correcting the initial coordinates of the trajectory points based on the road confidence level to obtain the trajectory point coordinates includes: The target confidence parameter is obtained by processing based on left and right confidence levels. The initial coordinates of the trajectory point are corrected using the target confidence parameter to obtain the trajectory point coordinates.

3. The method according to claim 1, characterized in that, After processing the location information of each target vehicle trajectory point based on the vehicle information and the road confidence level to obtain the trajectory point coordinates, the process further includes: Determine if the coordinates of the previous trajectory point of the target vehicle exist; If it exists, calculate the first difference between the coordinates of the current trajectory point and the coordinates of the previous trajectory point; When the first difference is determined to be greater than the preset longitudinal distance difference or less than 0, the following step is performed: for each target vehicle, processing is performed based on the driving speed, trajectory point coordinates, and the number of trajectory points of the target vehicle to obtain the corresponding fitted trajectory score and fitted trajectory parameters.

4. The method according to claim 3, characterized in that, Also includes: Compare the coordinates of the current trajectory point with the coordinates of the previous trajectory point; If the vertical coordinate of the current trajectory point is less than the vertical coordinate of the previous trajectory point, the number and the corresponding trajectory point coordinate of the target vehicle are deleted.

5. The method according to claim 1, characterized in that, The step of determining whether the position information of the next trajectory point of the target vehicle is the same as the driving target of the first vehicle based on the road line includes: Collect the location information of the next trajectory point of the target vehicle; Based on the lateral position in the position information of the next trajectory point, determine whether the target vehicle will be located within the lane line; If it is determined that the target vehicle will be located within the lane, the position information of the next trajectory point of the target vehicle is determined to be the same as the driving target of the first vehicle.

6. A vehicle lane prediction device, characterized in that, A processor applied to a first vehicle, implementing the vehicle lane prediction method of claim 1, the apparatus comprising: The acquisition unit is used to acquire the position information and driving speed of the target vehicle trajectory point in front of the first vehicle at preset time intervals, and to collect the vehicle information and road confidence of the first vehicle, wherein the road confidence includes left confidence and right confidence. The processing unit is configured to process the position information of each target vehicle trajectory point based on the vehicle information and the road confidence score to obtain trajectory point coordinates; for each target vehicle, the processing unit is configured to process the driving speed, trajectory point coordinates, and the number of target vehicle trajectory points to obtain a corresponding fitted trajectory score and fitted trajectory parameters; and determine the corresponding road line based on the fitted trajectory score, the fitted trajectory parameters, the vehicle information, and the road confidence score, so as to determine whether the position information of the next trajectory point of the target vehicle is the same as the driving target of the first vehicle based on the road line.

7. A storage medium, characterized in that, The storage medium includes a stored program, wherein, when the program is executed, it controls the device where the storage medium is located to perform the vehicle lane prediction method as described in any one of claims 1-5.

Images