Method, device, equipment and product for drawing lane center line

Abstract

This disclosure relates to a method, apparatus, device, and product for drawing lane centerlines. By acquiring lane centerlines in a separation-merging scenario, where multiple lanes connect to a single lane, for each lane, multiple lane centerlines with the same starting point are extracted from the lane centerlines in the area connecting the lane to the single lane as lane centerlines to be smoothed. Each lane centerline to be smoothed is then smoothed to obtain a smoothing result. For multiple smoothing results corresponding to the same lane, the smoothing result with the largest curvature is taken as the target smoothing result for that lane. The target smoothing results corresponding to each lane are then connected to the remaining lane centerlines in the separation-merging scenario to obtain the smoothed target lane centerlines of the separation-merging scenario. This improves the smoothness of lane centerlines in the separation-merging scenario, thereby providing data assurance for the driving safety of autonomous driving.

Description

Technical Field

[0001] This disclosure relates to the field of high-precision mapping technology, and in particular to a method, apparatus, device, and product for drawing lane center lines. Background Technology

[0002] During autonomous driving, autonomous vehicles plan their trajectories and speeds based on lane centerlines on a map. The smoothness of the lane centerlines affects the safety of autonomous driving. In reality, road conditions are complex, with multiple lanes merging into one and one lane splitting into multiple lanes. In such cases, ensuring the smoothness of the lane centerlines and improving driving safety are technical problems that need to be solved. Summary of the Invention

[0003] To address the aforementioned technical problems, this disclosure provides a method, apparatus, device, and product for drawing lane centerlines.

[0004] A first aspect of this disclosure provides a method for drawing lane centerlines. The method includes: obtaining the original lane centerlines of a separation and merging scenario, wherein the separation and merging scenario refers to a lane scenario in which multiple lanes are connected to a single lane; for each of the multiple lanes, extracting multiple lane centerlines with the same starting point from the lane centerlines of the lanes connecting to the single lane as lane centerlines to be smoothed; smoothing each lane centerline to be smoothed to obtain a smoothing result; for multiple smoothing results corresponding to the same lane, selecting the smoothing result with the largest curvature as the target smoothing result corresponding to the lane; and connecting the target smoothing results corresponding to each lane with the remaining lane centerlines of the separation and merging scenario to obtain the target lane centerlines of the separation and merging scenario.

[0005] A second aspect of this disclosure provides a lane centerline drawing apparatus, comprising:

[0006] The acquisition module is used to acquire the original lane centerline of the separation and merging scenario, which refers to a lane scenario in which multiple lanes are connected to a single lane;

[0007] The extraction module is used to extract multiple lane center lines with the same starting point from the lane center line of the connection area between the lane and the single lane for each of the multiple lanes as lane center lines to be smoothed.

[0008] The smoothing module is used to smooth the center line of each lane to be smoothed, and obtain the smoothing result.

[0009] The determination module is used to select the smoothing result with the largest curvature as the target smoothing result corresponding to the lane from multiple smoothing results corresponding to the same lane.

[0010] The connection module is used to connect the target smoothing result corresponding to each lane with the remaining lane centerline of the separation and merging scenario to obtain the target lane centerline of the separation and merging scenario.

[0011] A third aspect of this disclosure provides a computer device including a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, can implement the method of the first aspect described above.

[0012] A fourth aspect of this disclosure provides a computer program product, wherein the computer program product is stored in a storage medium, and when the computer program product is executed by a computer device, the computer device performs the method of the first aspect described above.

[0013] A fifth aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a computer device, causes the computer device to perform the method of the first aspect described above.

[0014] The technical solution provided in this disclosure has the following advantages compared with the prior art:

[0015] In this embodiment, the lane centerlines of a separation and merging scenario are obtained. In the separation and merging scenario, multiple lanes are connected to a single lane. For each lane, multiple lane centerlines with the same starting point are extracted from the lane centerlines of the area where the lane is connected to the single lane as lane centerlines to be smoothed. Smoothing is performed on each lane centerline to be smoothed to obtain a smoothing result. For multiple smoothing results corresponding to the same lane, the smoothing result with the largest curvature is taken as the target smoothing result for that lane. The target smoothing results corresponding to each lane are then connected with the remaining lane centerlines in the separation and merging scenario to obtain the smoothed target lane centerlines of the separation and merging scenario. In the separation and merging scenario, the unsmooth lane centerlines are mainly concentrated in the connection area between multiple lanes and a single lane. Therefore, for each lane among the multiple lanes connected to a single lane, multiple lane centerlines with the same starting point are extracted from the lane centerlines of the connection area between that lane and the single lane, and smoothed. The result with the largest curvature among the smoothed results is taken as the target smoothing result. This can improve the smoothness of the lane centerlines in the connection area between each lane and the single lane. Then, the target smoothing results corresponding to each lane are connected with the remaining lane centerlines in the separation and merging scenario. This can improve the smoothness of the lane centerlines in the connection area between multiple lanes and the single lane in the separation and merging scenario, thereby providing data assurance for the driving safety of autonomous driving. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0017] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of a separation and merging scenario provided by related technologies;

[0019] Figure 2 This is a schematic diagram of a lane centerline drawing scenario provided by an embodiment of this disclosure;

[0020] Figure 3 This is a flowchart of a method for drawing lane centerlines provided in an embodiment of this disclosure;

[0021] Figure 4 This is a schematic diagram of a method for extracting lane centerlines provided in an embodiment of this disclosure;

[0022] Figure 5 This is a schematic diagram of a method for obtaining the lane centerline from a reference point, provided in an embodiment of this disclosure;

[0023] Figure 6 This is a schematic diagram of a set of candidate lane centerlines provided in an embodiment of this disclosure;

[0024] Figure 7 yes Figure 1 A schematic diagram showing the effect of smoothing the lane centerline;

[0025] Figure 8 This is a schematic diagram of the structure of a lane centerline drawing device provided in an embodiment of this disclosure;

[0026] Figure 9 This is a schematic diagram of the structure of a computer device according to an embodiment of this disclosure. Detailed Implementation

[0027] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0028] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0029] In related technologies, the separation and merging scenario refers to a lane scenario where multiple lanes connect to a single lane. For example, Figure 1 This is a schematic diagram illustrating a separation and merging scenario provided by related technologies. In Figure 1 Lane lines L1 and L3 are lane lines for the left-hand lane, and lane lines L2 and L4 are lane lines for the right-hand lane. The two lanes merge into one lane at the position of straight line z1, thus forming a separation and merging scenario.

[0030] See Figure 1 In related technologies, lane centerlines are generally generated by connecting the midpoints between the lane lines on both sides of the lane. This method typically divides the lane data into multiple segments, and then connects the lane centerlines of the segments belonging to the same lane to obtain the lane centerline. However, for split-and-merge scenarios, the road conditions are more complex, especially in areas where multiple lanes connect to a single lane (e.g., in...). Figure 1In the section from the dashed line z2 to z1, the area where z2 and z1 intersect with the lane center line is often not smooth enough if the lane center line is simply generated by connecting the midpoints between the lane lines, thus failing to meet the requirements of autonomous driving.

[0031] To meet the requirements of autonomous driving, this disclosure provides a method for drawing lane center lines. For example, Figure 2 This is a schematic diagram illustrating a scenario for drawing a lane centerline according to an embodiment of this disclosure. Figure 2 In this context, data source 11 can be understood as a device that stores lane line data for the separated and merged scenario and original lane centerline data, such as a storage server or hard drive, but is not limited to storage servers and hard drives. The lane line data stored in data source 11 may include the coordinates of points on the lane lines and the direction of the lane lines at those points. The original lane centerline data may include the coordinates of points on the original lane centerline and the direction of the original lane centerline at those points.

[0032] In the embodiments of this disclosure, the data source 11 may be a separate device independent of the computer device 12, or it may be a device installed or integrated on the computer device 12.

[0033] Computer equipment 12 can be understood as devices with computing and processing capabilities, such as computers, servers, and in-vehicle systems, but is not limited to computers, servers, and in-vehicle systems.

[0034] In one example, computer device 12 can directly obtain the original lane centerline data of the separation and merging scenario from data source 11, then smooth the lane centerlines corresponding to the multi-lane and single-lane connection areas in the original lane centerlines, and connect the smoothed lane centerlines with the remaining lane centerlines in the separation and merging scenario to obtain the target lane centerline of the separation and merging scenario.

[0035] In practice, the unevenness of lane centerlines in separation and merging scenarios is mainly concentrated in the connection areas between multiple lanes and single lanes. Therefore, by smoothing the lane centerlines corresponding to the connection areas between multiple lanes and single lanes in separation and merging scenarios, and then connecting the smoothed lane centerlines with the remaining lane centerlines in the separation and merging scenarios, the smoothness of lane centerlines in separation and merging scenarios can be improved, thereby providing data assurance for the driving safety of autonomous driving.

[0036] To better understand the solutions of the embodiments of this disclosure, the solutions of the embodiments of this disclosure will be described below with reference to exemplary embodiments.

[0037] Figure 3This is a flowchart of a method for drawing lane centerlines provided in this disclosure embodiment. This method can be exemplarily described by... Figure 2 The computer device in the scenario shown is executing. For example... Figure 3 As shown, the method includes:

[0038] Step 301: Obtain the original lane centerline of the separation and merging scenario. The separation and merging scenario refers to a lane scenario in which multiple lanes are connected to a single lane.

[0039] In this disclosure, the original lane centerline can be understood as a lane centerline generated by a method using related technologies. For example, in one method, the left and right lane lines can be interpolated at 1-meter intervals. Then, starting from the same side of the left and right lane lines, the interpolated points on the left and right lane lines are sorted. Points with the same sorting on the left and right lane lines are connected, and the center points of each connecting line are then connected to obtain the lane centerline.

[0040] In this embodiment of the disclosure, the original lane centerline data for the separation and merging scenario can be obtained in advance and stored in a preset data source. The original lane centerline data for different separation and merging scenarios can be marked with different identifiers in the data source. When performing the operation of obtaining the original lane centerline of the separation and merging scenario, the corresponding original lane centerline can be obtained from the data source based on the identifier of the original lane centerline of the target separation and merging scenario.

[0041] Alternatively, in other implementations, the computer device may request the original lane centerline of the separation and merging scenario from the data source via a request message. The request message may not carry an identifier of the original lane centerline of the separation and merging scenario; instead, the data source decides which original lane centerline of the separation and merging scenario to send to the computer device.

[0042] It should be noted that the two methods for obtaining the original lane centerline described above are only two exemplary methods and not the only methods. In fact, in other embodiments, other custom methods can be used as needed to obtain the original lane centerline of the separation and merging scenario.

[0043] Step 302: For each of the multiple lanes, extract multiple lane center lines with the same starting point from the lane center line of the area connecting the lane and the single lane as lane center lines to be smoothed.

[0044] In one exemplary implementation, the original lane centerline obtained from the data source may include marking information for the connection areas of multiple lanes and single lanes. Based on this marking information, the connection areas of each lane in the multiple lanes and single lanes can be accurately determined from the original lane centerline. For example, in Figure 1In the diagram, dashed lines z1 and z2 can be understood as markers for the connecting areas of multiple lanes and single lanes. Data about dashed lines z1 and z2, such as their position and length, can be carried within the original lane centerline data. Figure 1 In the example shown, the portion of each lane's centerline falling between z1 and z2 represents the connection area between each lane and a single lane. After obtaining the connection areas between each lane and a single lane, for each lane, multiple lane centerlines with the same starting point can be extracted as the lane centerlines to be smoothed, starting from one end of the lane's centerline falling within the connection area (i.e., the portion marked by the labeling information). The lengths of these extracted lane centerlines to be smoothed can be different.

[0045] In another exemplary implementation, for each of the multiple lanes, the intersection of the lane centerline of that lane and the centerline of the single lane can be used as a reference point. Then, starting from the reference point, multiple lane centerlines of different lengths (i.e., portions of the lane centerlines) are obtained in a direction away from the single lane. These multiple lane centerlines of different lengths are then determined as the lane centerlines to be smoothed. For example, Figure 4 This is a schematic diagram of a method for extracting lane centerlines provided in an embodiment of this disclosure, as shown below. Figure 4 As shown, the intersection point G of the center lines of lanes H1 and H2 with the center line of lane H3 is used. Starting from point G, we can extend the center lines of lanes H1 and H2 respectively to obtain the lane center line l1 of a predetermined length on lane H1 (i.e., ...). Figure 4 The center line of lane H1 is located between z1 and z2) and the center line l2 of lane H2 is of a preset length (i.e. Figure 4 If the centerline of lane H2 is located between z1 and z2, then l1 and l2 can be understood as the centerlines of the lanes connecting lanes H1, H2, and a single lane H3. For lane H1, after obtaining the centerline of the area connecting lane H1 and a single lane H3, we can extend the centerline of the connecting area by different lengths, starting from the intersection point G. Multiple centerlines of different lengths starting from the intersection point G can be extracted from these centerlines as the lane centerlines to be smoothed. Similar to lane H1, a similar method can be used to obtain multiple lane centerlines to be smoothed for lane H2.

[0046] For example, Figure 5 This is a schematic diagram illustrating a method for obtaining a lane centerline using a reference point as a starting point, provided in an embodiment of this disclosure. See also... Figure 5In one implementation, for each of the multiple lanes, starting from a reference point, lane center lines of lengths of 50 meters, 40 meters, 30 meters, 20 meters, 10 meters, and 5 meters can be sequentially obtained in the direction of that lane as the lane center line to be smoothed. Here, 50 meters, 40 meters, 30 meters, 20 meters, 10 meters, and 5 meters can be understood as preset lane center line lengths, or they can be randomly selected lane center line lengths, which will not be elaborated further here.

[0047] certainly, Figure 5 This is just an example and not the only limitation. In reality, the number of lane center lines of different lengths and the specific length of each lane center line can be set as needed, and it is not necessary to be limited to the 50 meters, 40 meters, 30 meters, 20 meters, 10 meters and 5 meters listed above.

[0048] By taking a reference point as the starting point and obtaining multiple lane centerlines of different lengths from the connection area between each lane and a single lane as the lane centerlines to be smoothed, the length of the lane centerlines to be smoothed can be flexibly controlled, thereby achieving fine control of lane centerline smoothing.

[0049] Step 303: Smooth the center line of each lane to be smoothed to obtain the smoothing result.

[0050] After obtaining the lane centerline to be smoothed (hereinafter referred to as the lane centerline to be smoothed), a preset smoothing method can be used to smooth it. Preset smoothing methods include the five-term curve method and the Hermite curve method, but are not limited to these two methods. Taking the Hermite curve method as an example, when smoothing the lane centerline to be smoothed, the average directional change of the lane centerline per unit length can be determined based on its length and direction at its two endpoints. Then, based on the coordinates of any endpoint of the lane centerline, its direction at that endpoint, and the average directional change of the lane centerline per unit length, multiple coordinate points are determined for moving from one endpoint to the other. Connecting these coordinate points with the two endpoints of the lane centerline yields the smoothed lane centerline. Detailed implementation methods for the Hermite curve method can be found in related technical documents and will not be elaborated here.

[0051] It should be noted that the above smoothing method is only an exemplary method and not the only method. For example, in other embodiments, after obtaining multiple coordinate points based on the Emil da Ehrlich curve method, the multiple coordinate points can be grouped to obtain multiple coordinate point groups. Then, for each coordinate point group, the points in the coordinate point group are connected sequentially to the two endpoints of the lane centerline to be smoothed, and the lane centerline corresponding to each coordinate group is drawn. Then, the distance between each drawn lane centerline and the lane lines on both sides of the lane is determined. If the distance to at least one lane line is less than a preset safety distance, the lane centerline is deleted, resulting in a set of candidate lane centerlines (e.g., ...). Figure 6 The set of lane centerlines shown is used to select the lane centerline with the largest curvature from the candidate set of lane centerlines, which is then used as the final smoothed lane centerline, i.e., the target smoothed result. Alternatively, after obtaining multiple smoothed results for a lane, the smoothed result with the largest curvature can be determined from the smoothed results whose steering direction is the same as the steering direction of the lane, and used as the target smoothed result for that lane.

[0052] By smoothing the lane centerline multiple times and taking the one with the largest curvature that meets the preset safety distance requirement after multiple smoothings as the final smoothing result, the smoothing effect can be improved.

[0053] Step 304: For multiple smoothing results corresponding to the same lane, the smoothing result with the largest curvature is taken as the target smoothing result corresponding to the lane.

[0054] Since there are multiple lane centerlines to be smoothed extracted from the connection area of ​​each lane, multiple smoothing results can be obtained after smoothing multiple lane centerlines to be smoothed. The smoothing result with the largest curvature among the multiple smoothing results can be used as the target smoothing result for that lane, which can improve the smoothness of that lane in the connection area.

[0055] Step 305: Connect the target smoothing results corresponding to each lane with the remaining lane centerlines of the separation and merging scenario to obtain the target lane centerlines of the separation and merging scenario.

[0056] For example, in Figure 1 In the process, after smoothing the lane centerline between z1 and z2, connecting the smoothed lane centerline with the remaining lane centerlines yields the desired result. Figure 7 The center line of the target lane is shown.

[0057] For example, after obtaining the center line of the target lane, the center line of the target lane can be cut according to the length of each part of the lane in the separation and merging scenario to obtain the center line of the lane corresponding to each part of the lane in the separation and merging scenario.

[0058] In this embodiment, the lane centerlines of a separation and merging scenario are obtained. In the separation and merging scenario, multiple lanes are connected to a single lane. For each lane, multiple lane centerlines with the same starting point are extracted from the lane centerlines of the area where the lane is connected to the single lane as lane centerlines to be smoothed. Smoothing is performed on each lane centerline to be smoothed to obtain a smoothing result. For multiple smoothing results corresponding to the same lane, the smoothing result with the largest curvature is taken as the target smoothing result for that lane. The target smoothing results corresponding to each lane are then connected with the remaining lane centerlines in the separation and merging scenario to obtain the smoothed target lane centerlines of the separation and merging scenario. In the separation and merging scenario, the unsmooth lane centerlines are mainly concentrated in the connection area between multiple lanes and a single lane. Therefore, for each lane among the multiple lanes connected to a single lane, multiple lane centerlines with the same starting point are extracted from the lane centerlines of the connection area between that lane and the single lane, and smoothed. The result with the largest curvature among the smoothed results is taken as the target smoothing result. This can improve the smoothness of the lane centerlines in the connection area between each lane and the single lane. Then, the target smoothing results corresponding to each lane are connected with the remaining lane centerlines in the separation and merging scenario. This can improve the smoothness of the lane centerlines in the connection area between multiple lanes and the single lane in the separation and merging scenario, thereby providing data assurance for the driving safety of autonomous driving.

[0059] Figure 8 This is a schematic diagram of a lane centerline drawing device provided in an embodiment of this disclosure. This device can be understood as the aforementioned computer equipment or some functional modules of the aforementioned computer equipment. Figure 8 As shown, the drawing device 80 includes:

[0060] The acquisition module 81 is used to acquire the original lane centerline of the separation and merging scenario, which refers to a lane scenario in which multiple lanes are connected to a single lane.

[0061] Extraction module 82 is used to extract multiple lane center lines with the same starting point from the lane center line of the connection area between the lane and the single lane for each of the multiple lanes as lane center lines to be smoothed.

[0062] Smoothing module 83 is used to smooth the center line of each lane to be smoothed to obtain the smoothing result;

[0063] The determining module 84 is used to select the smoothing result with the largest curvature as the target smoothing result corresponding to the lane from multiple smoothing results corresponding to the same lane.

[0064] The connection module 85 is used to connect the target smoothing result corresponding to each lane with the remaining lane centerline of the separation and merging scenario to obtain the target lane centerline of the separation and merging scenario.

[0065] In one implementation, the extraction module 82 is used for:

[0066] The intersection of the center line of the lane and the center line of the single lane is determined as the reference point;

[0067] Starting from the reference point, obtain multiple lane centerlines of different lengths in the direction of the lane;

[0068] The obtained lane centerlines of different lengths are selected as the lane centerlines to be smoothed.

[0069] In one implementation, the extraction module 82 is used for:

[0070] For each of the multiple lanes, based on the marking information on the lane centerline, starting from one end marked by the marking information, multiple lane centerlines of the same starting point but different lengths are extracted as lane centerlines to be smoothed.

[0071] The marking information is used to mark the lane centerline of the lane and the single lane connection area.

[0072] In one implementation, the smoothing module 83 is used for:

[0073] Based on the length of the lane centerline to be smoothed and the direction of the lane centerline at its two endpoints, determine the average directional change of the lane centerline to be smoothed per unit length.

[0074] Based on the coordinates of any endpoint of the center line of the lane to be smoothed, the direction of the center line of the lane to be smoothed at any endpoint, and the average directional change of the center line of the lane to be smoothed per unit length, determine multiple coordinate points that the lane to be smoothed passes through when moving from one endpoint to another.

[0075] Based on the two endpoints of the lane centerline to be smoothed and the plurality of coordinate points, the lane centerline is drawn, and the drawn lane centerline is used as the smoothing result.

[0076] In one embodiment, the drawing device 80 further includes:

[0077] The first processing module is used for:

[0078] The multiple coordinate points are divided to obtain multiple groups of coordinate points;

[0079] The process of drawing a lane centerline based on the two endpoints of the lane centerline to be smoothed and the plurality of coordinate points, and using the drawn lane centerline as the smoothing result, includes:

[0080] For each set of coordinate points, draw the lane centerline based on the coordinate points contained in the set and the two endpoints.

[0081] The lane centerline with the largest curvature among the multiple lane centerlines drawn based on the multiple coordinate point groups is taken as the smoothing result.

[0082] In one embodiment, the drawing device 80 further includes:

[0083] The second processing module is used for:

[0084] From the multiple lane centerlines drawn, determine the lane centerlines whose distance from the lane lines is less than the preset safety distance;

[0085] Delete the lane center lines that are less than the preset safety distance from the multiple lane center lines that have been drawn.

[0086] In one embodiment, the determining module 84 is configured to: for multiple smoothing results corresponding to the same lane, determine the smoothing result with the largest curvature from the smoothing results whose steering direction is consistent with the steering direction of the lane as the target smoothing result corresponding to the lane.

[0087] The apparatus provided in this disclosure is capable of performing... Figures 3-7 The methods in any of the embodiments are similar in execution and beneficial effects, and will not be described again here.

[0088] This disclosure also provides a computer device including a processor and a memory, wherein the memory stores a computer program that, when executed by the processor, can implement the method of any of the above method embodiments.

[0089] Example, Figure 9 This is a schematic diagram of the structure of a computer device according to an embodiment of this disclosure. See below for details. Figure 9 The diagram illustrates a structural schematic suitable for implementing the computer device 1400 in the embodiments of this disclosure. The computer device 1400 in the embodiments of this disclosure may include, but is not limited to, devices with computing and data processing capabilities such as laptops, tablets, desktop computers, servers, and in-vehicle systems. Figure 9 The computer device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0090] like Figure 9 As shown, computer device 1400 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 1401, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1402 or a program loaded from storage device 1408 into random access memory (RAM) 1403. The RAM 1403 also stores various programs and data required for the operation of computer device 1400. The processing unit 1401, ROM 1402, and RAM 1403 are interconnected via bus 1404. Input / output (I / O) interface 1405 is also connected to bus 1404.

[0091] Typically, the following devices can be connected to I / O interface 1405: input devices 1406 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 1407 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1408 including, for example, magnetic tape, hard disk, etc.; and communication devices 1409. Communication device 1409 allows computer device 1400 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 9 A computer device 1400 with various devices is shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0092] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 1409, or installed from storage device 1408, or installed from ROM 1402. When the computer program is executed by processing device 1401, it performs the functions defined in the methods of embodiments of this disclosure.

[0093] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0094] The aforementioned computer-readable medium may be included in the aforementioned computer device; or it may exist independently and not assembled into the computer device.

[0095] The aforementioned computer-readable medium carries one or more programs that, when executed by the computer device, cause the computer device to: acquire the original lane centerlines of a separation-merging scenario, wherein the separation-merging scenario refers to a lane scenario where multiple lanes are connected to a single lane; for each of the multiple lanes, extract multiple lane centerlines with the same starting point from the lane centerlines of the area where the lane is connected to the single lane as lane centerlines to be smoothed; smooth each lane centerline to be smoothed to obtain a smoothing result; for multiple smoothing results corresponding to the same lane, select the smoothing result with the largest curvature as the target smoothing result corresponding to the lane; and connect the target smoothing results corresponding to each lane with the remaining lane centerlines of the separation-merging scenario to obtain the target lane centerlines of the separation-merging scenario.

[0096] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0097] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0098] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0099] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0100] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0101] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can perform the above-described functions. Figures 3-7 The methods in any of the embodiments are similar in execution and beneficial effects, and will not be described again here.

[0102] This disclosure also provides a computer program product stored in a storage medium, which, when executed by a processor of a computer device, causes the processor to perform... Figures 3-7 The methods in any of the embodiments are similar in execution and beneficial effects, and will not be described again here.

[0103] It should be noted that, in this document, relational terms such as "first" and "second" are used merely 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.

[0104] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. 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 this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for drawing lane centerlines, wherein, include: Obtain the original lane centerline of the separation and merging scenario, which refers to a lane scenario where multiple lanes are connected to a single lane; For each of the multiple lanes, multiple lane center lines with the same starting point are extracted from the lane center line of the area connecting the lane and the single lane as lane center lines to be smoothed. Smooth the center line of each lane to be smoothed to obtain the smoothing result; For multiple smoothing results corresponding to the same lane, the smoothing result with the largest curvature is taken as the target smoothing result corresponding to the lane; Connect the target smoothing result corresponding to each lane with the remaining lane centerline of the separation and merging scenario to obtain the target lane centerline of the separation and merging scenario.

2. The method according to claim 1, wherein, For each of the multiple lanes, extracting multiple lane centerlines with the same starting point from the lane centerline of the area connecting the lane to the single lane as lane centerlines to be smoothed includes: The intersection of the center line of the lane and the center line of the single lane is determined as the reference point; Starting from the reference point, obtain multiple lane centerlines of different lengths in the direction of the lane; The obtained lane centerlines of different lengths are selected as the lane centerlines to be smoothed.

3. The method according to claim 1, wherein, For each of the multiple lanes, extracting multiple lane centerlines with the same starting point from the lane centerline of the area connecting the lane to the single lane as lane centerlines to be smoothed includes: For each of the multiple lanes, based on the marking information on the lane centerline, starting from one end marked by the marking information, multiple lane centerlines of the same starting point but different lengths are extracted as lane centerlines to be smoothed. The marking information is used to mark the lane centerline of the lane and the single lane connection area.

4. The method according to claim 1, wherein, The process of smoothing each lane centerline to be smoothed to obtain a smoothing result includes: Based on the length of the lane centerline to be smoothed and the direction of the lane centerline at its two endpoints, determine the average directional change of the lane centerline to be smoothed per unit length. Based on the coordinates of any endpoint of the center line of the lane to be smoothed, the direction of the center line of the lane to be smoothed at any endpoint, and the average directional change of the center line of the lane to be smoothed per unit length, determine multiple coordinate points that the lane to be smoothed passes through when moving from one endpoint to another. Based on the two endpoints of the lane centerline to be smoothed and the plurality of coordinate points, the lane centerline is drawn, and the drawn lane centerline is used as the smoothing result.

5. The method according to claim 4, wherein, After determining the multiple coordinate points traversed from one endpoint of the lane centerline to be smoothed to another based on the coordinates of any endpoint of the lane centerline to be smoothed, the direction of the lane centerline to be smoothed at that endpoint, and the average directional change of the lane centerline to be smoothed per unit length, the method further includes: The multiple coordinate points are divided to obtain multiple groups of coordinate points; The process of drawing a lane centerline based on the two endpoints of the lane centerline to be smoothed and the plurality of coordinate points, and using the drawn lane centerline as the smoothing result, includes: For each set of coordinate points, draw the lane centerline based on the coordinate points contained in the set and the two endpoints. The lane centerline with the largest curvature among the multiple lane centerlines drawn based on the multiple coordinate point groups is taken as the smoothing result.

6. The method according to claim 5, wherein, Before using the lane centerline with the largest curvature among the multiple lane centerlines drawn based on the multiple coordinate point groups as the smoothing result, the process also includes: From the multiple lane centerlines drawn, determine the lane centerlines whose distance from the lane lines is less than the preset safety distance; Delete the lane center lines that are less than the preset safety distance from the multiple lane center lines that have been drawn.

7. The method according to any one of claims 1-6, wherein, for multiple smoothing results corresponding to the same lane, selecting the smoothing result with the largest curvature as the target smoothing result corresponding to the lane includes: For multiple smoothing results corresponding to the same lane, the smoothing result with the largest curvature is determined from the smoothing results whose steering direction is consistent with the steering direction of the lane as the target smoothing result corresponding to the lane.

8. A device for drawing lane centerlines, wherein, include: The acquisition module is used to acquire the original lane centerline of the separation and merging scenario, which refers to a lane scenario in which multiple lanes are connected to a single lane; The extraction module is used to extract multiple lane center lines with the same starting point from the lane center line of the connection area between the lane and the single lane for each of the multiple lanes as lane center lines to be smoothed. The smoothing module is used to smooth the center line of each lane to be smoothed, and obtain the smoothing result. The determination module is used to select the smoothing result with the largest curvature as the target smoothing result corresponding to the lane from multiple smoothing results corresponding to the same lane. The connection module is used to connect the target smoothing result corresponding to each lane with the remaining lane centerline of the separation and merging scenario to obtain the target lane centerline of the separation and merging scenario.

9. A computer device, wherein, include: A memory and a processor, wherein the memory stores a computer program that, when executed by the processor, implements the method as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program that, when executed by a computer device, causes the computer device to perform the method as described in any one of claims 1-7.

Images