A method, apparatus, equipment and medium for lane centerline processing

Abstract

This application discloses a lane centerline processing method, apparatus, device, and medium, relating to the field of intelligent driving technology. The method includes: obtaining the lane centerline equation of the vehicle at the previous moment; converting the lane centerline equation of the vehicle at the previous moment into an equation representation in the current coordinate system to obtain a first lane centerline equation; determining filtering coefficients based on the dispersion of lateral distance changes; adjusting various first lane line characteristic coefficients of the first lane centerline equation based on the filtering coefficients to obtain second lane line characteristic coefficients; the lateral distance is the distance between the first lane centerline equation and the lane centerline equation of the vehicle at the current moment; and controlling vehicle movement using the second lane centerline equation obtained based on the second lane line characteristic coefficients. It is evident that this application determines the filtering coefficients by the degree of dispersion, which can dynamically adapt to different lane centerline fluctuations, effectively smoothing the lane centerline and minimizing jump phenomena.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, and in particular to a method, apparatus, device, and medium for processing lane center lines. Background Technology

[0002] Current vision-based intelligent driving solutions often suffer from unstable upper-level perception or rapid changes in road curvature, leading to occasional abrupt changes in the calculated lane centerline. Small abrupt changes may cause the vehicle's trajectory to become erratic, resulting in a poor driving experience; larger abrupt changes may cause the control module to plan a larger steering wheel angle to control the vehicle, which often causes significant panic among drivers and may even lead to traffic accidents. Therefore, these problems urgently need to be addressed. Summary of the Invention

[0003] In view of this, the purpose of this invention is to provide a lane centerline processing method, apparatus, device, and medium that can determine the filtering coefficients by the degree of dispersion, thereby dynamically adapting to different lane centerline fluctuations, effectively smoothing the lane centerline, and reducing abrupt changes. The specific solution is as follows:

[0004] Firstly, this application discloses a method for processing lane centerlines, including:

[0005] Obtain the lane centerline equation of the vehicle at the previous moment, and convert the lane centerline equation of the previous moment into an equation representation in the current coordinate system to obtain the first lane centerline equation.

[0006] The filtering coefficients are determined based on the dispersion of the lateral distance change. The first lane line characteristic coefficients of the first lane centerline equation are adjusted based on the filtering coefficients to obtain the second lane line characteristic coefficients. The lateral distance is the distance between the first lane centerline equation and the lane centerline equation of the vehicle at the current moment.

[0007] The vehicle's movement is controlled by using the equation of the centerline of the second lane, which is obtained based on the characteristic coefficients of the second lane.

[0008] Optionally, determining the filter coefficients based on the dispersion of the lateral distance variation includes:

[0009] Calculate the lateral distance difference between the first lane centerline equation and the lane centerline equation at the current time at each sampling point, and calculate the target variance based on the lateral distance difference;

[0010] The filtering coefficients are determined based on the relationship between the target variance and the change in lane lines at different times.

[0011] Optionally, determining the filtering coefficients based on the relationship between the target variance and the change in lane lines at different times includes:

[0012] When the target variance increases, the filter coefficient increases according to a preset linear function; wherein the target variance is positively correlated with the change in lane lines at different times.

[0013] Optionally, adjusting the first lane line characteristic coefficients of the first lane centerline equation according to the filtering coefficients to obtain the second lane line characteristic coefficients includes:

[0014] Determine the characteristic coefficients of each third lane line in the lane centerline equation at the current moment;

[0015] Calculate the difference between the first lane line feature coefficient of each term and the corresponding third lane line feature coefficient of each term, and calculate the product of the filter coefficient and the difference of each term;

[0016] The sum of the product values ​​of each term and the first lane line characteristic coefficient of each term is determined as the second lane line characteristic coefficient.

[0017] Optionally, converting the lane centerline equation from the previous moment into an equation in the current coordinate system to obtain the first lane centerline equation includes:

[0018] Multiple first position points are obtained from the lane centerline equation of the previous moment; wherein, the multiple first position points are sampling points on the lane centerline equation of the previous moment.

[0019] The plurality of first position points are converted into coordinate representations in the vehicle coordinate system at the current time to obtain a plurality of second position points;

[0020] The first lane line characteristic coefficients are determined based on the plurality of second location points, and the equation constructed based on the first lane line characteristic coefficients is determined as the first lane centerline equation.

[0021] Optionally, obtaining multiple first location points from the lane centerline equation of the previous moment includes:

[0022] The validity of the lane centerline equation at the previous moment is determined based on preset judgment rules.

[0023] If the lane centerline equation of the previous moment is valid, then the plurality of first position points are obtained from the lane centerline equation of the previous moment.

[0024] Optionally, converting the plurality of first position points into coordinate representations in the vehicle coordinate system at the current time includes:

[0025] Based on the vehicle's travel path from the previous moment to the current moment, determine the translation distance and rotation angle between the vehicle coordinate system at the previous moment and the vehicle coordinate system at the current moment.

[0026] The plurality of first position points are converted into coordinate representations in the vehicle coordinate system at the current moment by means of the translation distance and the rotation angle.

[0027] Secondly, this application discloses a lane centerline processing device, comprising:

[0028] The equation conversion module is used to obtain the lane centerline equation of the vehicle at the previous moment and convert the lane centerline equation at the previous moment into an equation representation in the current coordinate system to obtain the first lane centerline equation.

[0029] The lane line filtering module is used to determine the filtering coefficients based on the dispersion of the lateral distance change, and adjust the first lane line characteristic coefficients of the first lane centerline equation according to the filtering coefficients to obtain the second lane line characteristic coefficients; wherein, the lateral distance is the distance between the first lane centerline equation and the lane centerline equation of the vehicle at the current moment;

[0030] The vehicle control module is used to control the vehicle's movement using the second lane centerline equation obtained based on the second lane line characteristic coefficients.

[0031] Thirdly, this application discloses an electronic device, including:

[0032] Memory, used to store computer programs;

[0033] A processor is used to execute the computer program to implement the aforementioned lane centerline processing method.

[0034] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned lane centerline processing method.

[0035] As can be seen, this application proposes a lane centerline processing method, including: obtaining the lane centerline equation of the vehicle at the previous moment, and converting the lane centerline equation of the previous moment into an equation representation in the current moment's coordinate system to obtain a first lane centerline equation; determining filtering coefficients based on the dispersion of lateral distance changes, adjusting various first lane line characteristic coefficients of the first lane centerline equation based on the filtering coefficients to obtain second lane line characteristic coefficients; the lateral distance is the distance between the first lane centerline equation and the lane centerline equation of the vehicle at the current moment; and controlling vehicle driving using the second lane centerline equation obtained based on the second lane line characteristic coefficients. This application first obtains the lane centerline equation of the previous moment and converts it to the vehicle coordinate system at the current moment to obtain a first lane centerline equation, then determines filtering coefficients based on the dispersion of lateral distance changes between the first and current moment lane centerline equations, and adjusts the first lane line characteristic coefficients using these coefficients to obtain the second lane line characteristic coefficients, thereby deriving the second lane centerline equation, and finally controlling vehicle driving based on this equation. Since the dispersion of lateral distance changes reflects the fluctuation of the lane centerline, a greater dispersion indicates a more pronounced lane centerline jump. Therefore, this method of determining the filtering coefficient based on the dispersion can dynamically adapt to different lane centerline fluctuations, effectively smoothing the lane centerline and minimizing jumps. Furthermore, the smoothed lane centerline provides more stable and reliable reference information for the traffic control module, significantly improving the safety and comfort of intelligent driving. Attached Figure Description

[0036] 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.

[0037] Figure 1 This is a flowchart of a lane centerline processing method disclosed in this application;

[0038] Figure 2 This is a schematic diagram of a coordinate transformation disclosed in this application;

[0039] Figure 3 This is a schematic diagram of the lane centerline equation for the previous and current times disclosed in this application;

[0040] Figure 4 This is a schematic diagram of a lane centerline point selection disclosed in this application;

[0041] Figure 5This is a schematic diagram of the final lane centerline output disclosed in this application;

[0042] Figure 6 This is a schematic diagram of the structure of a lane centerline processing device disclosed in this application;

[0043] Figure 7 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0044] 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.

[0045] Current vision-based intelligent driving solutions often suffer from unstable upper-level perception or rapid changes in road curvature, leading to occasional abrupt changes in the calculated lane centerline. Small abrupt changes may cause the vehicle's trajectory to become erratic, resulting in a poor driving experience; larger abrupt changes may cause the control module to plan a larger steering wheel angle to control the vehicle, which often causes significant panic among drivers and may even lead to traffic accidents. Therefore, these problems urgently need to be addressed.

[0046] Therefore, this application proposes a lane centerline processing scheme that can dynamically adapt to different lane centerline fluctuations, effectively smooth the lane centerline, and minimize jump phenomena.

[0047] This application discloses a method for processing lane centerlines. See also... Figure 1 As shown, it includes:

[0048] Step S11: Obtain the lane centerline equation of the vehicle at the previous moment, and convert the lane centerline equation of the previous moment into an equation representation in the current coordinate system to obtain the first lane centerline equation.

[0049] In this embodiment, the lane lines output by the camera are typically expressed as a cubic polynomial. To express, This indicates the lateral distance from the vehicle's centerline to the lane line. Indicates the heading angle of the vehicle relative to the lane line. Indicates the curvature of the lane lines. This represents the rate of change of curvature of the lane lines. to All of these represent lane line characteristic coefficients. For ease of distinction, in the expression of the lane centerline equation from the previous moment in the vehicle coordinate system at the current moment, the subscripts of each lane line characteristic coefficient are added with `k1`, while the lane line characteristic coefficients of the current moment's lane centerline equation remain unchanged. Therefore, the lane centerline equation from the previous moment in the vehicle coordinate system at the current moment can be expressed as: ,in, to All of these are unknown and need to be calculated.

[0050] It should be noted that this embodiment needs to determine the validity of the lane centerline equation from the previous moment based on preset judgment rules. These preset judgment rules include, but are not limited to, evaluating the image clarity, completeness, and point cloud density of the lane centerline equation from the previous moment. Specifically, image clarity exceeding a set threshold is considered to meet the clarity requirement; the ratio of detected lane centerline pixels to the theoretical number of pixels is calculated, and a ratio exceeding a threshold is considered to meet the completeness requirement; point cloud density exceeding a threshold is considered to meet the density requirement. Further, if the lane centerline equation from the previous moment is valid, the plurality of first position points are obtained from the lane centerline equation from the previous moment. Specifically, the effective length of the lane centerline from the previous moment is ViewEnd; multiple first position points are obtained at equal intervals from the lane centerline equation from the previous moment, resulting in... , , , ,in, , , , Substitute it into In the middle, you will get:

[0051] ;

[0052] ;

[0053] ;

[0054] .

[0055] Furthermore, the first lane line characteristic coefficients are determined by mapping the lane centerline equation from the previous moment to the vehicle coordinate system at the current moment, and the first lane centerline equation is obtained based on these first lane line characteristic coefficients. Specifically, based on the vehicle's travel path from the previous moment to the current moment, the translation distance and rotation angle between the vehicle coordinate system at the previous moment and the vehicle coordinate system at the current moment are determined. The multiple first position points are then converted into coordinate representations in the vehicle coordinate system at the current moment using the translation distance and rotation angle to obtain multiple second position points. Finally, the first lane line characteristic coefficients are determined based on these multiple second position points.

[0056] See Figure 2 As shown, xoy is the vehicle coordinate system at the previous time step. The vehicle coordinate system at the current moment. To translate the vehicle coordinate system from the previous moment to the current moment, let F be a position point in the vehicle coordinate system at the previous moment, relative to the vehicle, with coordinates (x, y). At the current moment, when the vehicle moves from point O to... At point A, it can be assumed that the vehicle has traveled a circular arc with radius R = , (Corresponding to rotation angle), v is the vehicle speed, yaw rate is the yaw rate, t is the travel time, and the displacement deviation of the vehicle is: , (Corresponding translation distance). Establish an auxiliary coordinate system. The position of F in the vehicle coordinate system at the current moment is , . , , , , Therefore, the position of F in the vehicle coordinate system at the current moment is: , It is understandable that F is one of the first position points, and F's position in the vehicle coordinate system at the current moment. In this way, based on the above method, this embodiment obtains the coordinate representation of all first position points in the vehicle coordinate system at the current time, that is, it obtains all second position points, and determines the coordinates of all second position points as follows: , , , .

[0057] Substitute the coordinates of all second position points We can obtain:

[0058] ;

[0059] ;

[0060] ;

[0061] .

[0062] Written in matrix form:

[0063] ;

[0064] Therefore, the characteristic coefficients of the first lane lines are:

[0065] ;

[0066] At this point, the calculation of the characteristic coefficients of the first lane line is completed, and the equation obtained based on the characteristic coefficients of the first lane line is determined as the equation of the center line of the first lane.

[0067] Step S12: Determine the filtering coefficients based on the dispersion of the lateral distance change, and adjust the first lane line characteristic coefficients of the first lane centerline equation according to the filtering coefficients to obtain the second lane line characteristic coefficients; the lateral distance is the distance between the first lane centerline equation and the lane centerline equation at the current moment.

[0068] See Figure 3 As shown, This is the equation representing the lane centerline equation from the previous moment in the vehicle coordinate system at the current moment. y is the equation of the lane centerline at the current moment. .

[0069] In this embodiment, the lateral distance difference between the first lane centerline equation and the current lane centerline equation at each sampling point is calculated, and the target variance is calculated based on the lateral distance difference. Then, the filtering coefficient is determined based on the target variance and the change in lane lines between consecutive time points. Specifically, the target variance is positively correlated with the change in lane lines between consecutive time points, and the target variance is also positively correlated with the filtering coefficient. That is, when the target variance increases, the filtering coefficient increases according to a preset linear function; the target variance is positively correlated with the change in lane lines between consecutive time points. The preset linear function can be... In the form of.

[0070] The longest effective distance between the lane centerlines at two different time points is taken as the longest pre-aiming distance (LongPreDist) for lane line processing. Assuming this embodiment samples 10 points at equal intervals, the spacing between adjacent points is step. Substitute the distance at each sampling point into the lane centerline equation for the two time points before and after, and calculate the lateral distance from the vehicle to each sampling point on the lane centerline for the two time points before and after.

[0071] ;

[0072] ;

[0073] in, ,like Figure 4 As shown.

[0074] The lateral distance from the vehicle to the centerline at the previous time step is represented by LatDistToLastCenterLine, and the lateral distance to the centerline at the current time step is represented by LatDistToCurrentLine. Therefore, the lateral distance difference LatDistError between the lane line at the previous time step and the lane line at the current time step for each sampling point is:

[0075] ;

[0076] The average value of the lateral distance difference between the lane centerline at the previous time step and the lane centerline at the current time step at all sampling points, LatDistErrorAverage, is:

[0077] ;

[0078] The target variance of the lateral distance LatDistError from the lane centerline at the previous time step to the lane centerline at the current time step at all sampling points is:

[0079] ;

[0080] The smaller the variance, the less obvious the change in the current lane centerline. Conversely, a larger variance indicates a greater change in the lane centerline between two consecutive moments. Therefore, this embodiment designs a filtering coefficient for the current lane centerline based on the variance of the lateral distance between the centerlines between two consecutive moments, as shown in Table 1 below. The first row in Table 1 represents the target variance of the lateral distance between the centerlines between the two consecutive moments, and the second row in Table 1 represents the filtering coefficients used. In Table 1, a=1 and b=0.

[0081] Table 1

[0082]

[0083] After obtaining the filtering coefficients, the third lane line characteristic coefficients of each term in the lane centerline equation at the current time are determined. The difference between each term's second lane line characteristic coefficient and the corresponding term's third lane line characteristic coefficient is calculated. The product of the filtering coefficients and each term's difference is then calculated. The sum of this product and each term's first lane line characteristic coefficient is then determined as the second lane line characteristic coefficient. The final output is the second lane line characteristic coefficient. , , , for:

[0084] ;

[0085] ;

[0086] ;

[0087] ;

[0088] in, to This represents the characteristic coefficients of the third lane lines. to This represents the characteristic coefficient of the first lane line for each item.

[0089] Step S13: Control the vehicle's movement using the second lane centerline equation obtained based on the second lane line characteristic coefficient.

[0090] See Figure 5 yend represents the equation of the center line of the second lane obtained based on the characteristic coefficient of the second lane line. After obtaining the equation of the center line of the second lane, the vehicle driving is controlled based on the equation of the center line of the second lane.

[0091] The following is a detailed explanation using a specific embodiment:

[0092] In an intelligent driving system, the system records the lane centerline equation from the previous moment, which describes the position and shape characteristics of the lane centerline at that moment. Since the vehicle's position and attitude constantly change during driving, it's necessary to transform the lane centerline equation from the previous moment into the vehicle's coordinate system at the current moment. Specifically, the system selects multiple points at equal intervals from the lane centerline equation from the previous moment, for example, four points, located at a certain proportion (e.g., 0.25, 0.5, 0.75, and 1 times the effective length of the lane centerline ViewEnd from the previous moment). Next, based on the vehicle's travel path from the previous moment to the current moment, the translation distance and rotation angle between the two vehicle coordinate systems are calculated. For example, translation and rotation parameters are obtained using specific calculation methods based on information such as the vehicle's speed, yaw rate, and travel time. Using these parameters, the selected points from the previous moment are transformed into the vehicle's coordinate system at the current moment, resulting in multiple new points (i.e., second position points). Finally, based on the coordinate information of these new points, the characteristic coefficients of the first lane line are determined, thus obtaining the first lane centerline equation. This equation can more accurately reflect the positional relationship between the lane centerline and the vehicle at the current moment.

[0093] Furthermore, the filtering coefficients are determined and the lane line feature coefficients are adjusted. Specifically, the lateral distance difference between the first lane centerline equation and the lane centerline equation actually detected at the current moment is calculated at multiple sampling points. For example, a relatively long lane line is selected as the processing range, and 10 points are sampled at equal intervals within this range. The lateral distance from the vehicle to each sampling point of the lane centerline at the two consecutive moments is calculated, and then the lateral distance difference between the lane line at the previous moment and the lane line at the current moment is calculated for each sampling point. The lateral distance differences of all sampling points are averaged, and then the target variance is calculated based on the average value. The larger the target variance, the greater the difference between the first lane centerline equation and the lane centerline equation at the current moment, that is, the more obvious the fluctuation of the lane centerline; conversely, the smaller the variance, the less obvious the fluctuation.

[0094] Furthermore, the filtering coefficient is determined based on the target variance and the change in lane lines at different times. A larger target variance results in a larger filtering coefficient, and a smaller target variance results in a smaller filtering coefficient. For example, a suitable filtering coefficient can be selected using a pre-defined correspondence table (e.g., a filtering coefficient of 0.1 when the target variance is 0.1, and a filtering coefficient of 0.2 when the target variance is 0.2). The characteristic coefficients of the third lane lines in the current lane centerline equation are determined, and the differences between the characteristic coefficients of the first lane lines and the corresponding characteristic coefficients of the third lane lines are calculated. Each difference is multiplied by the filtering coefficient to obtain a series of product values. Finally, these product values ​​are added to the corresponding first lane line characteristic coefficients to obtain the second lane line characteristic coefficients.

[0095] Finally, vehicle control is implemented. Specifically, the obtained second lane line characteristic coefficients are used to construct the second lane centerline equation. This equation, after filtering, provides a more accurate and smoother description of the current lane centerline. The vehicle's control system plans the vehicle's path based on this second lane centerline equation. If the vehicle deviates from the second lane centerline, the system calculates the necessary adjustments in direction and speed to bring the vehicle back to its ideal trajectory, ensuring stable and safe driving within the lane, improving driving comfort and safety, and reducing vehicle instability caused by lane centerline jumps.

[0096] This application uses the variance of the lateral deviation between the lane centerline at the previous moment and the current moment at different longitudinal distances to indicate the changing trend of the lane centerline at the previous moment and the current moment. If the changing trend is small, a small filtering coefficient is used; if the changing trend is large, a larger filtering coefficient is used to achieve a smooth transition of the lane centerline. In this way, it will not cause the control end to generate a large steering wheel angle that pulls the vehicle off course, and it will also give the driver enough reaction time. If the coefficient plans an incorrect angle, the driver can take over the vehicle in time.

[0097] As can be seen, this application proposes a lane centerline processing method, including: obtaining the lane centerline equation of the vehicle at the previous moment, and converting the lane centerline equation of the previous moment into an equation representation in the current moment's coordinate system to obtain a first lane centerline equation; determining filtering coefficients based on the dispersion of lateral distance changes, adjusting various first lane line characteristic coefficients of the first lane centerline equation based on the filtering coefficients to obtain second lane line characteristic coefficients; the lateral distance is the distance between the first lane centerline equation and the lane centerline equation of the vehicle at the current moment; and controlling vehicle driving using the second lane centerline equation obtained based on the second lane line characteristic coefficients. This application first obtains the lane centerline equation of the previous moment and converts it to the vehicle coordinate system at the current moment to obtain a first lane centerline equation, then determines filtering coefficients based on the dispersion of lateral distance changes between the first and current moment lane centerline equations, and adjusts the first lane line characteristic coefficients using these coefficients to obtain the second lane line characteristic coefficients, thereby deriving the second lane centerline equation, and finally controlling vehicle driving based on this equation. Since the dispersion of lateral distance changes reflects the fluctuation of the lane centerline, a greater dispersion indicates a more pronounced lane centerline jump. Therefore, this method of determining the filtering coefficient based on the dispersion can dynamically adapt to different lane centerline fluctuations, effectively smoothing the lane centerline and minimizing jumps. Furthermore, the smoothed lane centerline provides more stable and reliable reference information for the traffic control module, significantly improving the safety and comfort of intelligent driving.

[0098] Accordingly, this application also discloses a lane centerline processing device, see [link to relevant documentation]. Figure 6 As shown, the device includes:

[0099] Equation conversion module 11 is used to obtain the lane centerline equation of the vehicle at the previous moment and convert the lane centerline equation at the previous moment into an equation representation in the coordinate system at the current moment to obtain the first lane centerline equation.

[0100] The lane line filtering module 12 is used to determine the filtering coefficients based on the dispersion of the lateral distance change, and adjust the first lane line characteristic coefficients of the first lane centerline equation according to the filtering coefficients to obtain the second lane line characteristic coefficients; wherein, the lateral distance is the distance between the first lane centerline equation and the lane centerline equation of the vehicle at the current moment.

[0101] The vehicle control module 13 is used to control the vehicle's movement using the second lane centerline equation obtained based on the second lane line characteristic coefficient.

[0102] For more detailed information on the working process of each of the above modules, please refer to the relevant content disclosed in the foregoing embodiments, which will not be repeated here.

[0103] As can be seen, this application proposes a lane centerline processing method, including: obtaining the lane centerline equation of the vehicle at the previous moment, and converting the lane centerline equation of the previous moment into an equation representation in the current moment's coordinate system to obtain a first lane centerline equation; determining filtering coefficients based on the dispersion of lateral distance changes, adjusting various first lane line characteristic coefficients of the first lane centerline equation based on the filtering coefficients to obtain second lane line characteristic coefficients; the lateral distance is the distance between the first lane centerline equation and the lane centerline equation of the vehicle at the current moment; and controlling vehicle driving using the second lane centerline equation obtained based on the second lane line characteristic coefficients. This application first obtains the lane centerline equation of the previous moment and converts it to the vehicle coordinate system at the current moment to obtain a first lane centerline equation, then determines filtering coefficients based on the dispersion of lateral distance changes between the first and current moment lane centerline equations, and adjusts the first lane line characteristic coefficients using these coefficients to obtain the second lane line characteristic coefficients, thereby deriving the second lane centerline equation, and finally controlling vehicle driving based on this equation. Since the dispersion of lateral distance changes reflects the fluctuation of the lane centerline, a greater dispersion indicates a more pronounced lane centerline jump. Therefore, this method of determining the filtering coefficient based on the dispersion can dynamically adapt to different lane centerline fluctuations, effectively smoothing the lane centerline and minimizing jumps. Furthermore, the smoothed lane centerline provides more stable and reliable reference information for the traffic control module, significantly improving the safety and comfort of intelligent driving.

[0104] Furthermore, embodiments of this application also provide an electronic device. Figure 7 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.

[0105] Figure 7 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. Specifically, the electronic device 20 may include: at least one processor 21, at least one memory 22, a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the lane centerline processing method disclosed in any of the foregoing embodiments. Furthermore, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0106] In this embodiment, the power supply 26 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 25 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 24 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0107] Furthermore, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk, or optical disk, etc. The resources stored thereon may include computer programs 221, and the storage method may be temporary storage or permanent storage. The computer programs 221 may include, in addition to computer programs capable of performing the lane centerline processing method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, computer programs capable of performing other specific tasks.

[0108] Furthermore, embodiments of this application also disclose a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned lane centerline processing method.

[0109] For the specific steps of this method, please refer to the relevant content disclosed in the foregoing embodiments, which will not be repeated here.

[0110] The various embodiments in this application are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. For the same or similar parts between the various embodiments, refer to each other. As for the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and relevant parts can be referred to in the method section.

[0111] 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 implementation should not be considered beyond the scope of this application.

[0112] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0113] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover 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 limitations, 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.

[0114] The above provides a detailed description of a lane centerline processing method, apparatus, device, and storage medium provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for processing lane centerlines, characterized in that, include: Obtain the lane centerline equation of the vehicle at the previous moment, and convert the lane centerline equation of the previous moment into an equation representation in the current coordinate system to obtain the first lane centerline equation. The filtering coefficients are determined based on the dispersion of the lateral distance change. The first lane line characteristic coefficients of the first lane centerline equation are adjusted based on the filtering coefficients to obtain the second lane line characteristic coefficients. The lateral distance is the distance between the first lane centerline equation and the lane centerline equation of the vehicle at the current moment. The vehicle's movement is controlled by using the equation of the centerline of the second lane, which is obtained based on the characteristic coefficients of the second lane.

2. The lane centerline processing method according to claim 1, characterized in that, The determination of filter coefficients based on the dispersion of lateral distance variation includes: Calculate the lateral distance difference between the first lane centerline equation and the lane centerline equation at the current time at each sampling point, and calculate the target variance based on the lateral distance difference; The filtering coefficients are determined based on the relationship between the target variance and the change in lane lines at different times.

3. The lane centerline processing method according to claim 2, characterized in that, The step of determining the filtering coefficients based on the relationship between the target variance and the change in lane lines at different times includes: When the target variance increases, the filter coefficient increases according to a preset linear function; wherein the target variance is positively correlated with the change in lane lines at different times.

4. The lane centerline processing method according to claim 1, characterized in that, The step of adjusting the first lane line characteristic coefficients of the first lane centerline equation according to the filtering coefficients to obtain the second lane line characteristic coefficients includes: Determine the characteristic coefficients of each third lane line in the lane centerline equation at the current moment; Calculate the difference between the first lane line feature coefficient of each term and the corresponding third lane line feature coefficient of each term, and calculate the product of the filter coefficient and the difference of each term; The sum of the product values ​​of each term and the first lane line characteristic coefficient of each term is determined as the second lane line characteristic coefficient.

5. The lane centerline processing method according to any one of claims 1 to 4, characterized in that, The step of converting the lane centerline equation from the previous moment to an equation in the current coordinate system to obtain the first lane centerline equation includes: Multiple first position points are obtained from the lane centerline equation of the previous moment; wherein, the multiple first position points are sampling points on the lane centerline equation of the previous moment. The plurality of first position points are converted into coordinate representations in the vehicle coordinate system at the current time to obtain a plurality of second position points; The first lane line characteristic coefficients are determined based on the plurality of second location points, and the equation constructed based on the first lane line characteristic coefficients is determined as the first lane centerline equation.

6. The lane centerline processing method according to claim 5, characterized in that, The process of obtaining multiple first position points from the lane centerline equation of the previous moment includes: The validity of the lane centerline equation at the previous moment is determined based on preset judgment rules. If the lane centerline equation of the previous moment is valid, then the plurality of first position points are obtained from the lane centerline equation of the previous moment.

7. The lane centerline processing method according to claim 5, characterized in that, The step of converting the plurality of first position points into coordinate representations in the vehicle coordinate system at the current time includes: Based on the vehicle's travel path from the previous moment to the current moment, determine the translation distance and rotation angle between the vehicle coordinate system at the previous moment and the vehicle coordinate system at the current moment. The plurality of first position points are converted into coordinate representations in the vehicle coordinate system at the current moment by means of the translation distance and the rotation angle.

8. A lane centerline processing device, characterized in that, include: The equation conversion module is used to obtain the lane centerline equation of the vehicle at the previous moment and convert the lane centerline equation at the previous moment into an equation representation in the current coordinate system to obtain the first lane centerline equation. The lane line filtering module is used to determine the filtering coefficients based on the dispersion of the lateral distance change, and adjust the first lane line characteristic coefficients of the first lane centerline equation according to the filtering coefficients to obtain the second lane line characteristic coefficients; wherein, the lateral distance is the distance between the first lane centerline equation and the lane centerline equation of the vehicle at the current moment; The vehicle control module is used to control the vehicle's movement using the equation of the centerline of the second lane obtained based on the characteristic coefficients of the second lane.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the lane centerline processing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store a computer program; wherein, when the computer program is executed by a processor, it implements the lane centerline processing method as described in any one of claims 1 to 7.

Images