Virtual lane line generation method and device, vehicle and storage medium

Abstract

The embodiment of the invention provides a virtual lane line generation method, and relates to the technical field of automatic driving, and the method comprises the steps: obtaining the position information of at least one other vehicle within a preset range of a vehicle at a current moment when the vehicle cannot recognize a lane line of a current driving lane; acquiring a driving track point data set of each other vehicle according to the position information; filtering each driving track point data set to obtain each filtered driving track point data set; generating a lane center line of the current driving lane according to the filtered driving track point data sets; and generating a virtual lane line of the current driving lane according to the lane center line and a preset lane width. In the embodiment of the invention, the virtual lane line of the current driving lane can be determined by acquiring the driving tracks of other vehicles in the preset range, so that the problem that the vehicle cannot detect the lane line is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and particularly to a method for generating virtual lane lines, a device for generating virtual lane lines, a vehicle, and a storage medium. Background Art

[0002] Lane keeping is one of the basic functions of an autonomous driving system. This function uses a perception module to identify the position of lane lines on the road, and the control system dynamically adjusts the steering of the vehicle according to the relative position of the vehicle within the current lane, so that the vehicle can drive smoothly within the current lane.

[0003] In the prior art, an in-vehicle camera is used to collect continuous video data for detecting lane lines, and lane line detection is performed separately on each frame of the video. However, in some special scenarios (such as snowy days, newly built roads, worn lane lines, etc.), the lane lines may not exist or be very blurred, so that the in-vehicle camera cannot detect the lane lines, which easily causes the vehicle to drive out of the lane edge during autonomous driving, thus resulting in danger. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention are proposed to provide a method for generating virtual lane lines, a device for generating virtual lane lines, a vehicle, and a storage medium that overcome the above problems or at least partially solve the above problems.

[0005] To solve the above problems, an embodiment of the present invention discloses a method for generating virtual lane lines, which is applied to a vehicle, and the method includes:

[0006] When the vehicle cannot identify the lane lines of the current driving lane, obtain the position information of at least one other vehicle within a preset range of the vehicle at the current moment;

[0007] Obtain the driving trajectory point data sets of each of the other vehicles according to the position information;

[0008] Filter each of the driving trajectory point data sets to obtain the filtered driving trajectory point data sets;

[0009] Generate the lane center line of the current driving lane according to the filtered driving trajectory point data sets;

[0010] Generate the virtual lane lines of the current driving lane according to the lane center line and a preset lane width.

[0011] Optionally, the filtering each of the driving trajectory point data sets to obtain the filtered driving trajectory point data sets includes:

[0012] Calculate the distances between each pair of trajectory points in each of the driving trajectory point datasets to obtain the average speed between each pair of trajectory points;

[0013] Eliminate the trajectory points with an average speed greater than the first threshold to obtain the filtered driving trajectory point datasets.

[0014] Optionally, the filtering of each of the driving trajectory point datasets to obtain the filtered driving trajectory point datasets further includes:

[0015] Traverse each trajectory point in each of the driving trajectory point datasets to identify the normal trajectory points and abnormal trajectory points in each of the driving trajectory point datasets;

[0016] Calculate the distance between the previous normal trajectory point of the abnormal trajectory point and the last abnormal trajectory point in the abnormal trajectory points;

[0017] If the distance is greater than the second threshold, eliminate the abnormal trajectory points to obtain the filtered driving trajectory point datasets.

[0018] Optionally, the generation of the lane centerline of the current driving lane based on the filtered driving trajectory point datasets includes:

[0019] Use a preset algorithm to calculate each of the filtered driving trajectory point datasets to obtain the vehicle centerline of each of the driving trajectory point datasets;

[0020] Determine the lane centerline of the current driving lane based on each of the vehicle centerlines.

[0021] Optionally, the determination of the lane centerline of the current driving lane based on each of the vehicle centerlines includes:

[0022] Calculate the distance between each of the vehicle centerlines and the centerline of the vehicle;

[0023] Determine the vehicle centerline with a distance less than the third threshold as the lane centerline of the current driving lane.

[0024] Optionally, the determination of the vehicle centerline with a distance less than the third threshold as the lane centerline of the current driving lane includes:

[0025] If there are multiple vehicle centerlines with a distance less than the third threshold, determine the vehicle centerline with the minimum distance as the lane centerline of the current driving lane;

[0026] If there is one vehicle centerline with a distance less than the third threshold, determine the vehicle centerline as the lane centerline of the current driving lane.

[0027] Optionally, before generating the virtual lane line of the current driving lane according to the lane center line and the preset lane width, the method further includes:

[0028] When the vehicle recognizes the lane line of the current lane, obtain the lane width of the current lane;

[0029] Determine the lane width as the preset lane width.

[0030] Correspondingly, an embodiment of the present invention also discloses a virtual lane line generation device, which is applied to a vehicle. The device includes:

[0031] An information acquisition module, configured to obtain the position information of at least one other vehicle within a preset range of the vehicle at the current moment when the vehicle cannot recognize the lane line of the current driving lane;

[0032] A data set acquisition module, configured to obtain the driving trajectory point data sets of each of the other vehicles according to the position information;

[0033] A data filtering module, configured to filter each of the driving trajectory point data sets to obtain the filtered driving trajectory point data sets;

[0034] A center line generation module, configured to generate the lane center line of the current driving lane according to the filtered driving trajectory point data sets;

[0035] A lane line generation module, configured to generate the virtual lane line of the current driving lane according to the lane center line and the preset lane width.

[0036] Optionally, the data filtering module includes:

[0037] A speed calculation sub-module, configured to calculate the distance between each trajectory point in each of the driving trajectory point data sets to obtain the average speed between each of the trajectory points;

[0038] A trajectory point elimination sub-module, configured to eliminate the trajectory points with an average speed greater than a first threshold to obtain the filtered driving trajectory point data sets.

[0039] Optionally, the data filtering module further includes:

[0040] A trajectory point determination sub-module, configured to traverse each trajectory point in each of the driving trajectory point data sets to determine the normal trajectory points and abnormal trajectory points in each of the driving trajectory point data sets

[0041] A distance calculation sub-module, configured to calculate the distance between the previous normal trajectory point of the abnormal trajectory point and the last abnormal trajectory point in the abnormal trajectory points;

[0042] A trajectory point filtering sub-module, configured to remove the abnormal trajectory points if the distance is greater than a second threshold, so as to obtain each filtered driving trajectory point dataset.

[0043] Optionally, the center line generation module includes:

[0044] An algorithm calculation sub-module, configured to calculate each filtered driving trajectory point dataset by using a preset algorithm to obtain the vehicle center line of each driving trajectory point dataset;

[0045] A center line determination sub-module, configured to determine the lane center line of the current driving lane according to each vehicle center line.

[0046] Optionally, the center line determination sub-module includes:

[0047] A distance calculation unit, configured to calculate the distance between each vehicle center line and the center line of the vehicle;

[0048] A center line determination unit, configured to determine the vehicle center line with a distance less than a third threshold as the lane center line of the current driving lane.

[0049] Optionally, the center line determination unit includes:

[0050] A distance calculation sub-unit, configured to, if there are multiple vehicle center lines with a distance less than a third threshold, determine the vehicle center line with the minimum distance as the lane center line of the current driving lane;

[0051] A center line determination sub-unit, configured to, if there is one vehicle center line with a distance less than a third threshold, determine the vehicle center line as the lane center line of the current driving lane.

[0052] Optionally, the device further includes:

[0053] A width acquisition module, configured to acquire the lane width of the current lane when the vehicle recognizes the lane lines of the current lane;

[0054] A width determination module, configured to determine the lane width as a preset lane width.

[0055] Correspondingly, an embodiment of the present invention discloses a vehicle, including: a processor, a memory, and a computer program stored on the memory and capable of running on the processor, where when the computer program is executed by the processor, each step of the method embodiment for generating the virtual lane line is implemented.

[0056] Correspondingly, an embodiment of the present invention discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, each step of the above-described method embodiment for generating a virtual lane line is implemented.

[0057] The embodiment of the present invention has the following advantages: when a vehicle cannot recognize the lane lines of the current driving lane, the position information of at least one other vehicle within a preset range of the vehicle at the current moment is obtained; according to the position information, a driving trajectory point data set of each other vehicle is obtained; each driving trajectory point data set is filtered to obtain each filtered driving trajectory point data set; according to each filtered driving trajectory point data set, a lane center line of the current driving lane is generated; according to the lane center line and a preset lane width, a virtual lane line of the current driving lane is generated. In the embodiment of the present invention, the virtual lane line of the current driving lane can be determined by obtaining the driving trajectories of other vehicles within the preset range, so as to solve the problem that the vehicle cannot detect the lane lines. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 is a flowchart of the steps of a method for generating a virtual lane line provided by an embodiment of the present invention;

[0059] Figure 2 is a prediction range diagram provided by an embodiment of the present invention;

[0060] Figure 3 is a trajectory point acquisition diagram provided by an embodiment of the present invention;

[0061] Figure 4 is an abnormal trajectory point distribution diagram (1) provided by an embodiment of the present invention;

[0062] Figure 5 is an abnormal trajectory point distribution diagram (2) provided by an embodiment of the present invention;

[0063] Figure 6 is a vehicle center line distance diagram provided by an embodiment of the present invention;

[0064] Figure 7 is a virtual lane line generation diagram provided by an embodiment of the present invention;

[0065] Figure 8 is a structural block diagram of a device for generating a virtual lane line provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0066] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0067] Refer to Figure 1, which shows the step flowchart of a method for generating a virtual lane line provided by an embodiment of the present invention. The method is applied to a vehicle, and the method may specifically include the following steps:

[0068] Step 101, when the vehicle cannot recognize the lane lines of the current driving lane, obtain the position information of at least one other vehicle within a preset range of the vehicle at the current moment.

[0069] When the vehicle is in autonomous driving, if the lane lines of the current driving lane cannot be obtained, it will cause the autonomous driving to be unable to drive according to the lane lines, and the vehicle may drive out of the edge line of the road, resulting in a traffic accident.

[0070] In the embodiment of the present invention, when the vehicle is in autonomous driving, if the lane lines of the current driving lane cannot be recognized, the position information of at least one other vehicle within a preset range of the vehicle at the current moment can be obtained, where the preset range can be determined according to the lane center line of the previous frame of the lane. Refer to Figure 2 , the dotted line is the preset range of the vehicle, the solid line is the lane center line of the previous frame of the lane, vehicle a is the vehicle itself, and vehicle b and vehicle c are other vehicles within the preset range. The specific preset range can be set according to the actual situation, and the embodiment of the present invention does not limit this.

[0071] Step 102, obtain the driving trajectory point datasets of each of the other vehicles according to the position information.

[0072] After obtaining the position information of at least one other vehicle within a preset range of the vehicle at the current moment, obtain the position information where the other vehicle travels to at another moment, obtain the continuous frames during the driving between the two moments through the on-vehicle camera of the vehicle, obtain the driving trajectory points of each other vehicle, and supplement the driving trajectory data of the other vehicle to obtain the driving trajectory point datasets of the other vehicles. Refer to Figure 3 , the position information of vehicle c determined by vehicle a at time t1 is m. After vehicle a has traveled for a period of time, the position information of vehicle c determined at time t2 is n. The continuous frames between time t1 and time t2 can be obtained through the on-vehicle camera, and the driving trajectory points of vehicle c from m to n can be determined. For example, the vehicle has traveled for 20 seconds, and the on-vehicle camera has obtained 20 frames of images. The trajectory points of the vehicle traveling from m to n can be determined through these 20 frames. S1 is the driving trajectory point dataset of vehicle c, and S2 is the driving trajectory point dataset of vehicle b.

[0073] Step 103, filter each of the driving trajectory point datasets to obtain the filtered driving trajectory point datasets.

[0074] When obtaining the driving trajectory point datasets of other vehicles, there may be abnormal driving trajectory points. After obtaining the driving trajectory point datasets, it is necessary to filter the driving trajectory point datasets to obtain the filtered driving trajectory point datasets for each one.

[0075] In the embodiment of the present invention, the filtering of each of the driving trajectory point datasets to obtain the filtered driving trajectory point datasets for each one includes:

[0076] Calculate the distances between each pair of trajectory points in each of the driving trajectory point datasets to obtain the average speed between each pair of the trajectory points;

[0077] Eliminate the trajectory points with an average speed greater than the first threshold to obtain the filtered driving trajectory point datasets for each one.

[0078] When a vehicle is driving, it may change lanes, which may result in abnormal trajectory points in the obtained driving trajectory point datasets. To ensure the accuracy of the driving trajectory point datasets, it is necessary to identify the abnormal trajectory points and eliminate them. For example, referring to Figure 4 , p1, p2, p3, p4 are normal driving trajectory points. When it comes to p5, the trajectory point deviates. When it comes to p6, p7, p8, the trajectory point returns to normal. It is possible to calculate the distances between each pair of trajectory points in each of the driving trajectory point datasets to obtain the average speed between each pair of the trajectory points, and eliminate the trajectory points with an average speed greater than the first threshold. For example, by calculating the distances between p1 and p2, p2 and p3, p3 and p4, p4 and p5, p5 and p6, p6 and p7, p7 and p8, the average speed between the corresponding trajectory points is obtained. If the average speed between p4 and p5, p5 and p6 is greater than the first threshold, then p5 is determined as an abnormal trajectory point, and the trajectory point p5 is eliminated, thus performing the operation of filtering the driving trajectory point datasets. The specific first threshold can be set according to the actual situation, and the embodiment of the present invention does not limit this.

[0079] In the embodiment of the present invention, the filtering of each of the driving trajectory point datasets to obtain the filtered driving trajectory point datasets for each one further includes:

[0080] Traverse each trajectory point in each of the driving trajectory point datasets to identify the normal trajectory points and abnormal trajectory points in each of the driving trajectory point datasets;

[0081] Calculate the distance between the previous normal trajectory point of the abnormal trajectory point and the last abnormal trajectory point in the abnormal trajectory point;

[0082] If the distance is greater than the second threshold, then eliminate the abnormal trajectory point to obtain the filtered driving trajectory point datasets for each one.

[0083] After obtaining the driving trajectory point dataset, in order to obtain the normal trajectory points and abnormal trajectory points in the driving trajectory point dataset, each trajectory point in the driving trajectory point dataset can be traversed to obtain the normal trajectory points and abnormal trajectory points in each driving trajectory point dataset. In the embodiment of the present invention, the traversal method in "Mining User Similarity Based on Location History" can be selected to obtain the normal trajectory points and abnormal trajectory points in each driving trajectory point dataset. Refer to Figure 5 , p1, p2, and p3 are normal driving trajectory points. When it comes to p4, p5, and p6, the trajectory points are abnormal, and when it comes to p7 and p8, the trajectory points return to normal. When the vehicle is queuing in a congested lane, the trajectory points may be published in a small area, for example, the trajectory points p4, p5, and p6. Therefore, by traversing all of p1 to p8, it can be determined that p1, p2, p3, p7, and p8 are normal trajectory points, and p4, p5, and p6 are abnormal trajectory points. The normal trajectory point before the abnormal trajectory point is p3, and the last abnormal trajectory point among the abnormal trajectory points is p6. At this time, calculate the distance between p3 and p6. If the calculated distance between p3 and p6 is greater than the second threshold, then the abnormal trajectory points p4, p5, and p6 are removed, thereby filtering the driving trajectory point dataset. The specific second threshold can be set according to the actual situation, and the embodiment of the present invention does not limit this.

[0084] Step 104: Generate the lane centerline of the current driving lane according to each filtered driving trajectory point dataset.

[0085] After obtaining each filtered driving trajectory point dataset, the corresponding centerline can be generated according to each driving trajectory point dataset, and the lane centerline of the current driving lane is determined from the centerlines corresponding to each driving trajectory point dataset.

[0086] In the embodiment of the present invention, the generating the lane centerline of the current driving lane according to each filtered driving trajectory point dataset includes:

[0087] Use a preset algorithm to calculate each filtered driving trajectory point dataset to obtain the vehicle centerline of each driving trajectory point dataset;

[0088] Determine the lane centerline of the current driving lane according to each vehicle centerline.

[0089] The filtered datasets of each driving trajectory point can be calculated according to a preset algorithm to obtain the vehicle centerline of each driving trajectory point dataset, and then the lane centerline of the current driving lane can be determined based on each vehicle centerline, where the preset algorithm can be the "RANSAC" algorithm. Refer to Figure 6 , curve ① is the vehicle centerline of vehicle c, and curve ② is the vehicle centerline of vehicle b. The lane centerline of the current driving lane is determined based on curve ① and curve ②. The specific preset algorithm can be set according to the actual situation, and the embodiments of the present invention do not limit this.

[0090] In the embodiments of the present invention, the determining the lane centerline of the current driving lane based on each vehicle centerline includes:

[0091] Calculating the distance between each vehicle centerline and the centerline of the vehicle;

[0092] Determining the vehicle centerline with the distance less than a third threshold as the lane centerline of the current driving lane.

[0093] After determining each vehicle centerline, calculate the distance between each vehicle centerline and the centerline of the vehicle, and determine the vehicle centerline with the distance less than the third threshold as the lane centerline of the current driving lane. Refer to Figure 6 , distance a is the distance between curve ② and vehicle a itself, and distance b is the distance between curve ① and vehicle a itself. If distance a is less than the third threshold and distance b is greater than the third threshold, then determine curve ② as the lane centerline of the current driving lane. The specific third threshold can be set according to the actual situation, and the embodiments of the present invention do not limit this.

[0094] In the embodiments of the present invention, the determining the vehicle centerline with the distance less than the third threshold as the lane centerline of the current driving lane includes:

[0095] If there are multiple vehicle centerlines with the distance less than the third threshold, then determine the vehicle centerline with the minimum distance as the lane centerline of the current driving lane;

[0096] If there is one vehicle centerline with the distance less than the third threshold, then determine the vehicle centerline as the lane centerline of the current driving lane.

[0097] Refer to Figure 6 , if both distance a and distance b are less than the third threshold, then determine the vehicle centerline corresponding to the minimum distance a as the lane centerline of the current driving lane. If only distance a is less than the third threshold, then determine the vehicle centerline corresponding to distance a as the lane centerline of the current driving lane.

[0098] Step 105: Generate the virtual lane lines of the current driving lane according to the lane center line and the preset lane width.

[0099] Generate the virtual lane lines of the current driving lane according to the lane center line and the predicted set lane width. Refer to Figure 7 , the dotted line is the lane center line of the determined current driving lane, and the solid lines above and below vehicle a are the virtual lane lines of the current driving lane.

[0100] In the embodiment of the present invention, before generating the virtual lane lines of the current driving lane according to the lane center line and the preset lane width, the following steps are further included:

[0101] When the vehicle recognizes the lane lines of the current lane, obtain the lane width of the current lane;

[0102] Determine the lane width as the preset lane width.

[0103] In order to obtain more accurate virtual lane lines, when the vehicle recognizes the lane lines of the current lane, the lane width can be updated in real time, obtain the last saved lane width of the current lane, and determine this lane width as the preset lane width. Refer to Figure 7 , the width in the figure is the finally determined lane width when the vehicle is driving on a road with lane lines.

[0104] The embodiment of the present invention has the following advantages: When the vehicle cannot recognize the lane lines of the current driving lane, obtain the position information of at least one other vehicle within the preset range of the vehicle at the current moment; obtain the driving trajectory point data sets of each other vehicle according to the position information; filter each driving trajectory point data set to obtain the filtered driving trajectory point data sets; generate the lane center line of the current driving lane according to the filtered driving trajectory point data sets; generate the virtual lane lines of the current driving lane according to the lane center line and the preset lane width. In the embodiment of the present invention, the virtual lane lines of the current driving lane can be determined by obtaining the driving trajectories of other vehicles within the preset range to solve the problem that the vehicle cannot detect the lane lines.

[0105] It should be noted that for the method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of the present invention are not limited by the described action sequences, because according to the embodiments of the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential for the embodiments of the present invention.

[0106] Refer to Figure 8, showing a structural block diagram of a virtual lane line generation device provided by an embodiment of the present invention. The device is applied to a vehicle and specifically may include the following modules:

[0107] An information acquisition module 201, configured to acquire position information of at least one other vehicle within a preset range of the vehicle at the current moment when the vehicle cannot recognize the lane lines of the current driving lane;

[0108] A data set acquisition module 202, configured to acquire a driving trajectory point data set of each of the other vehicles according to the position information;

[0109] A data filtering module 203, configured to filter each of the driving trajectory point data sets to obtain filtered driving trajectory point data sets;

[0110] A center line generation module 204, configured to generate a lane center line of the current driving lane according to the filtered driving trajectory point data sets;

[0111] A lane line generation module 205, configured to generate a virtual lane line of the current driving lane according to the lane center line and a preset lane width.

[0112] Optionally, the data filtering module includes:

[0113] A speed calculation sub-module, configured to calculate the distance between each trajectory point in each of the driving trajectory point data sets to obtain the average speed between each of the trajectory points;

[0114] A trajectory point elimination sub-module, configured to eliminate the trajectory points with an average speed greater than a first threshold to obtain filtered driving trajectory point data sets.

[0115] Optionally, the data filtering module further includes:

[0116] A trajectory point determination sub-module, configured to traverse each trajectory point in each of the driving trajectory point data sets to determine normal trajectory points and abnormal trajectory points in each of the driving trajectory point data sets

[0117] A distance calculation sub-module, configured to calculate the distance between the previous normal trajectory point of the abnormal trajectory point and the last abnormal trajectory point in the abnormal trajectory points;

[0118] A trajectory point filtering sub-module, configured to eliminate the abnormal trajectory points if the distance is greater than a second threshold to obtain filtered driving trajectory point data sets.

[0119] Optionally, the center line generation module includes:

[0120] An algorithm calculation sub-module, configured to calculate each filtered driving trajectory point data set by using a preset algorithm to obtain the vehicle center line of each driving trajectory point data set;

[0121] A center line determination sub-module, configured to determine the lane center line of the current driving lane according to each vehicle center line.

[0122] Optionally, the center line determination sub-module includes:

[0123] A distance calculation unit, configured to calculate the distance between each vehicle center line and the center line of the vehicle;

[0124] A center line determination unit, configured to determine the vehicle center line with a distance less than a third threshold as the lane center line of the current driving lane.

[0125] Optionally, the center line determination unit includes:

[0126] A distance calculation sub-unit, configured to, if there are multiple vehicle center lines with a distance less than a third threshold, determine the vehicle center line with the minimum distance as the lane center line of the current driving lane;

[0127] A center line determination sub-unit, configured to, if there is one vehicle center line with a distance less than a third threshold, determine the vehicle center line as the lane center line of the current driving lane.

[0128] Optionally, the device further includes:

[0129] A width acquisition module, configured to acquire the lane width of the current lane when the vehicle recognizes the lane lines of the current lane;

[0130] A width determination module, configured to determine the lane width as a preset lane width.

[0131] For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For related parts, refer to the partial description of the method embodiment.

[0132] An embodiment of the present invention further provides a vehicle, including:

[0133] Including a processor, a memory, and a computer program stored on the memory and capable of running on the processor. When the computer program is executed by the processor, it implements each process of the above method embodiment for generating a virtual lane line and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0134] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements each process of the above-described embodiment of the method for generating virtual lane lines and can achieve the same technical effects. To avoid repetition, details are not described herein again.

[0135] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The same or similar parts among the embodiments can be referred to each other.

[0136] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a device, or a computer program product. Therefore, the embodiments of the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0137] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the method, terminal device (system), and computer program product according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing terminal devices generate a device for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0138] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0139] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, such that a series of operation steps are executed on the computer or other programmable terminal device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable terminal device provide for implementing the functions in the process Figure 1one or more processes and / or blocks Figure 1 Steps of functions specified in one or more blocks.

[0140] Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

[0141] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising the element.

[0142] The above has introduced in detail a method for generating a virtual lane line, a device for generating a virtual lane line, a vehicle, and a storage medium provided by the present invention. Specific examples are used in this text to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for generating virtual lane lines, characterized in that, The method is applied to a vehicle, and the method includes: When the vehicle cannot identify the lane lines of the current driving lane, obtain the position information of at least one other vehicle within a preset range of the vehicle at the current moment; Obtain the driving trajectory point data sets of each of the other vehicles according to the position information; Filter each of the driving trajectory point data sets to obtain the filtered driving trajectory point data sets; Generate the lane center line of the current driving lane according to the filtered driving trajectory point data sets; Generate the virtual lane lines of the current driving lane according to the lane center line and a preset lane width.

2. The method according to claim 1, characterized in that, The filtering of each of the driving trajectory point data sets to obtain the filtered driving trajectory point data sets includes: Calculate the distances between the trajectory points in each of the driving trajectory point data sets to obtain the average speed between the trajectory points; Eliminate the trajectory points with an average speed greater than a first threshold to obtain the filtered driving trajectory point data sets.

3. The method according to claim 1, characterized in that, The filtering of each of the driving trajectory point data sets to obtain the filtered driving trajectory point data sets further includes: Traverse each of the trajectory points in each of the driving trajectory point data sets to determine the normal trajectory points and abnormal trajectory points in each of the driving trajectory point data sets; Calculate the distance between the previous normal trajectory point of the abnormal trajectory point and the last abnormal trajectory point in the abnormal trajectory points; If the distance is greater than a second threshold, eliminate the abnormal trajectory points to obtain the filtered driving trajectory point data sets.

4. The method according to claim 1, characterized in that, The generating of the lane center line of the current driving lane according to the filtered driving trajectory point data sets includes: Use a preset algorithm to calculate each of the filtered driving trajectory point data sets to obtain the vehicle center line of each of the driving trajectory point data sets; Determine the lane center line of the current driving lane according to each of the vehicle center lines.

5. The method according to claim 4, characterized in that, The determining of the lane center line of the current driving lane according to each of the vehicle center lines includes: Calculate the distance between each of the vehicle center lines and the center line of the vehicle; Determine the vehicle center line with a distance less than a third threshold as the lane center line of the current driving lane.

6. The method according to claim 5, characterized in that, The determining of the vehicle center line with a distance less than a third threshold as the lane center line of the current driving lane includes: If there are multiple vehicle center lines with a distance less than the third threshold, determine the vehicle center line with the minimum distance as the lane center line of the current driving lane; If there is one vehicle center line with a distance less than the third threshold, determine the vehicle center line as the lane center line of the current driving lane.

7. The method according to claim 1, characterized in that, Before generating the virtual lane lines of the current driving lane according to the lane center line and a preset lane width, it further includes: When the vehicle identifies the lane lines of the current lane, obtain the lane width of the current lane; Determine the lane width as the preset lane width.

8. A device for generating virtual lane lines, characterized in that, The device is applied to a vehicle, and the device includes: An information acquisition module, configured to acquire position information of at least one other vehicle within a preset range of the vehicle at the current moment when the vehicle fails to recognize the lane lines of the current driving lane; A data set acquisition module, configured to acquire a driving trajectory point data set of each of the other vehicles according to the position information; A data filtering module, configured to filter each of the driving trajectory point data sets to obtain the filtered driving trajectory point data sets; A center line generation module, configured to generate a lane center line of the current driving lane according to the filtered driving trajectory point data sets; A lane line generation module, configured to generate virtual lane lines of the current driving lane according to the lane center line and a preset lane width.

9. A vehicle, characterized in that, Comprising:A processor, a memory, and a computer program stored on the memory and capable of running on the processor, where when the computer program is executed by the processor, the steps of the method for generating virtual lane lines as described in any one of claims 1-7 are implemented.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, the steps of the method for generating virtual lane lines as described in any one of claims 1-7 are implemented.

Images