Road map generation method, back-annotation method, computer device and medium

Abstract

The application provides a road map generation method, a road map annotation method, a computer device and a medium. The generation method comprises the following steps: acquiring lane line parameters output by a preset camera on a preset vehicle and dynamic parameters of nearby moving targets, and acquiring vehicle attitude parameters output by an inertial navigation device on the preset vehicle; determining a driving track of the preset vehicle based on the vehicle attitude parameters; determining a first lane center line of a road where the preset vehicle is located based on the driving track; generating road static data based on the lane line parameters, the vehicle attitude parameters and the first lane center line; and generating dynamic scene data based on the dynamic parameters of the nearby moving targets and the vehicle attitude parameters. According to the application, the lane line parameters output by the camera, the dynamic parameters of the nearby moving targets and the vehicle attitude parameters output by the inertial navigation device are used to determine the static road and the dynamic scene, so as to generate the road map, reduce the cost of generating the road map, and improve the efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of road map, in particular to a road map generation method, a road map annotation method, a computer device and a medium. BACKGROUND

[0002] In the development process of automatic driving function, the road map plays an important role, which can be used as the basis for matching vehicle positioning and path planning in automatic driving, and can assist in environment perception. In the test of automatic driving function, the road map can be used as the basic environment information in the scene modeling of virtual test of automatic driving.

[0003] The production of the road map is usually to generate a local point cloud map by using the collected laser point cloud data, and then to produce the map by using the manual annotation method through the annotation tool. It can be seen that this map production method is very time-consuming and laborious.

[0004] Therefore, the existing road map generation scheme has the technical problems of high cost and low efficiency. SUMMARY

[0005] The present application provides a road map generation method, a road map annotation method, a computer device and a medium, which aims to reduce the cost of generating the road map and improve the generation efficiency.

[0006] In one aspect, the present application provides a road map generation method, which includes road static data and dynamic scene data on the road, and the method comprises:

[0007] Obtaining lane line parameters output by a preset camera on a preset vehicle and dynamic parameters of nearby moving targets, and obtaining vehicle attitude parameters output by an inertial navigation device on the preset vehicle;

[0008] Determining a driving trajectory of the preset vehicle based on the vehicle attitude parameters;

[0009] Determining a first lane center line of a road where the preset vehicle is located based on the driving trajectory;

[0010] Generating the road static data based on the lane line parameters, the vehicle attitude parameters and the first lane center line;

[0011] Generating the dynamic scene data based on the dynamic parameters of the nearby moving targets and the vehicle attitude parameters.

[0012] In one possible implementation of the present application, the generating the road static data based on the lane line parameters, the vehicle attitude parameters and the first lane center line comprises:

[0013] determine a number and a type of lanes in a same driving direction as the preset vehicle based on the lane line parameters, to obtain lane information;

[0014] determine whether the preset vehicle has turned or made a U-turn based on the vehicle posture parameters, to determine whether a location of the preset vehicle is an intersection, to obtain first intersection information;

[0015] determine a first road shape of a road where the preset vehicle is located based on a shape of the first lane center line;

[0016] generate the road static data based on the lane information, the first intersection information, and the first road shape.

[0017] In a possible implementation manner of the present application, the generating the road static data based on the lane information, the first intersection information, and the first road shape comprises:

[0018] determine whether a vehicle crosses the road where the preset vehicle is located based on the dynamic parameters of the nearby moving target, to determine a position of an intersection in the road where the preset vehicle is located, to obtain second intersection information;

[0019] generate the road static data based on the lane information, the first intersection information, the second intersection information, and the first road shape.

[0020] In a possible implementation manner of the present application, the generating the dynamic scene data based on the dynamic parameters of the nearby moving target and the vehicle posture parameters comprises:

[0021] determine a first motion process of the nearby moving target based on the dynamic parameters of the nearby moving target;

[0022] determine a second motion process of the preset vehicle based on the vehicle posture parameters;

[0023] generate the dynamic scene data based on the first motion process and the second motion process in a same time period.

[0024] In a possible implementation manner of the present application, the determining the first lane center line of the road where the preset vehicle is located based on the driving track comprises:

[0025] determine whether the preset vehicle has changed lanes based on the vehicle posture parameters;

[0026] if the preset vehicle has changed lanes, determine a lane changing distance of the preset vehicle;

[0027] correct the driving track based on the lane changing distance, and use a shape of the corrected driving track as a shape of the first lane center line of the road where the preset vehicle is located.

[0028] In one possible implementation of this application, determining the lane-changing distance of the preset vehicle includes:

[0029] Get the total lane width between the lane where the vehicle was located before changing lanes and the lane where the vehicle is located after changing lanes.

[0030] Based on the total lane width, determine the average lane width between the lane where the preset vehicle was located before changing lanes and the lane where the preset vehicle was located after changing lanes.

[0031] The average lane width is used as the preset lane change distance for vehicles.

[0032] In one possible implementation of this application, after determining the center line of the first lane of the road where the preset vehicle is located based on the driving trajectory, the method further includes:

[0033] Obtain the second road shape of the road where the vehicle is located from the preset map data source;

[0034] Based on the shape of the center line of the first lane, determine the first road shape of the road where the preset vehicle is located;

[0035] Determine the similarity between the first road shape and the second road shape;

[0036] When the similarity is greater than a preset similarity, the step of generating the road static data based on the lane line parameters, the vehicle posture parameters, and the first lane centerline is executed.

[0037] On the other hand, this application provides a road map generation apparatus, the apparatus comprising:

[0038] The acquisition unit is used to acquire lane line parameters and dynamic parameters of nearby moving targets output by a preset camera on a preset vehicle, as well as vehicle attitude parameters output by an inertial navigation device on the preset vehicle.

[0039] The first determining unit is used to determine the driving trajectory of the preset vehicle based on the vehicle attitude parameters.

[0040] The second determining unit is used to determine the center line of the first lane of the road where the preset vehicle is located based on the driving trajectory.

[0041] The first generation unit is used to generate the road static data based on the lane line parameters, the vehicle attitude parameters, and the first lane centerline.

[0042] The second generation unit is used to generate the dynamic scene data based on the dynamic parameters of the nearby moving target and the vehicle attitude parameters.

[0043] On the other hand, this application also provides a method for re-injection, the method comprising:

[0044] Simulation modeling is performed on the static road data in the road map generated by any of the above generation methods to obtain the road model;

[0045] Simulation modeling is performed based on the dynamic scene data in the road map to obtain multiple moving target models on the road model and the motion parameters of the multiple moving target models.

[0046] Based on the road model, multiple moving target models on the road model, and the motion parameters of the multiple moving target models, a dynamic simulation scene model of the road map is generated;

[0047] Acquire simulation video data at a specified location and from a specified viewpoint in the dynamic simulation scene model;

[0048] The simulated video data is injected into the terminal where the specified algorithm is located.

[0049] On the other hand, this application also provides a computer device, the computer device comprising:

[0050] One or more processors;

[0051] Memory; and

[0052] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the methods described above.

[0053] On the other hand, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to perform the steps in the above method.

[0054] This application provides a road map generation method, a back-annotation method, a computer device, and a medium. The generation method includes: acquiring lane line parameters and dynamic parameters of nearby moving targets output by a preset camera on a preset vehicle, and acquiring vehicle attitude parameters output by an inertial navigation device on the preset vehicle; determining the driving trajectory of the preset vehicle based on the vehicle attitude parameters; determining the center line of the first lane of the road where the preset vehicle is located based on the driving trajectory; generating static road data based on the lane line parameters, vehicle attitude parameters, and the first lane center line; and generating dynamic scene data based on the dynamic parameters of nearby moving targets and the vehicle attitude parameters. Compared with traditional methods, this application uses lane line parameters output by a camera, dynamic parameters of nearby moving targets, and vehicle attitude parameters output by an inertial navigation device to determine the static road and dynamic scene, thereby generating a road map, reducing the cost of generating road maps and increasing efficiency. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is a schematic diagram of a road map generation system provided in an embodiment of this application;

[0057] Figure 2 This is a schematic flowchart of an embodiment of the road map generation method provided in this application.

[0058] Figure 3 This is a schematic flowchart of an embodiment of the modified driving trajectory provided in this application.

[0059] Figure 4 yes Figure 3 A schematic diagram of the process of correcting the driving trajectory;

[0060] Figure 5 This is a schematic diagram of an embodiment of the road map generation device provided in this application.

[0061] Figure 6 This is a schematic diagram of an embodiment of the computer device provided in this application. Detailed Implementation

[0062] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0063] In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0064] In this application, the term "exemplary" is used to mean "serving as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details.

[0065] In other instances, well-known structures and processes will not be described in detail to avoid unnecessary detail that would obscure the description of this application. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0066] This application provides a method for generating road maps, a method for re-annotating them, a computer device, and a medium, which will be described in detail below.

[0067] like Figure 1 As shown, Figure 1 This is a schematic diagram (Figure 0) of a road map generation system provided in an embodiment of this application. The road map generation system may include a computer device 100, which integrates a road map generation apparatus, such as... Figure 1 Computer equipment 100.

[0068] In this embodiment, the computer device 100 can be a terminal or a server. When the computer device 100 is a server, it can be a standalone server or a server network composed of servers.

[0069] Alternatively, a server cluster, such as the computer device 100 described in the embodiments of this application, includes, but is not limited to, computers, network hosts, single network servers, multiple sets of network servers, or cloud servers constructed from multiple servers. The cloud server is constructed from a large number of computers or network servers based on cloud computing.

[0070] It is understood that when the computer device 100 in this embodiment is a terminal, the terminal used can be...

[0071] This refers to a device that includes both receiving and transmitting hardware, specifically a device with receiving and transmitting hardware capable of performing bidirectional communication over a bidirectional communication link. Such a device may include cellular or other communication devices, having a single-line display, a multi-line display, or no multi-line display. Specifically, computer device 100 may be a desktop terminal or a mobile terminal; it may also be a mobile phone, tablet computer, laptop computer, etc.

[0072] Those skilled in the art will understand that Figure 1 The application environments shown are only the five application scenarios of Scheme 1 of this application, and are not intended to limit the application scenarios of this application. Other application environments are also possible.

[0073] To include than Figure 1 The number of computer devices shown is more or less, for example Figure 1 Only one computer device is shown in the diagram. It is understood that the road map generation system may also include one or more other computer devices, which are not specified here.

[0074] In addition, such as Figure 1 As shown, the road map generation system may also include a memory 200 for storing data, such as lane line parameters, dynamic parameters of nearby moving targets, and vehicle attitude parameters.

[0075] It should be noted that, Figure 1 The schematic diagram of the road map generation system shown is merely an example. The road map generation system and scenario described in this application embodiment are for the purpose of more clearly illustrating the technical solutions of this application embodiment and do not constitute a limitation on the technical solutions provided in this application embodiment. As those skilled in the art will know, with the evolution of road map generation systems and the emergence of new business scenarios, the technical solutions provided in this application embodiment are also applicable to similar technical problems.

[0076] Next, we will introduce the road map generation method and the back-annotation method provided in the embodiments of this application.

[0077] In this embodiment of the road map generation method, the road map generation device is used as the execution subject. For the sake of simplicity and ease of description, the execution subject will be omitted in the subsequent method embodiments. The road map generation device is applied to a computer device.

[0078] Please see Figure 2 , Figure 2 This is a schematic flowchart of an embodiment of the road map generation method provided in this application. The road map generation method includes:

[0079] 201. Obtain lane line parameters and dynamic parameters of nearby moving targets output by the preset camera on the preset vehicle, and obtain vehicle attitude parameters output by the inertial navigation device on the preset vehicle.

[0080] The preset vehicle in this application embodiment is generally a map data collection vehicle, which is equipped with a preset camera and an inertial navigation device.

[0081] The preset camera is an intelligent camera used to identify the surrounding road environment during the driving of the preset vehicle and output the following road-related information: lane line parameters (including the number of lane lines, lane line type (e.g., solid lines, dashed lines, double solid lines, etc.), lane line color, width, etc.), and dynamic parameters of nearby moving targets (e.g., pedestrians, vehicles, etc.) (e.g., position relative to the preset vehicle, direction of movement, speed). The preset camera can also output other information such as identified traffic signs, which is not limited here. In the lane line parameters output by the preset camera, there are generally four lane lines. For example, the preset camera can capture four lane lines: a, b, c, and d. Lane a is a double yellow line. Lanes b, c, and d are on one side of the double yellow line a. There are other lane lines on the other side of the double yellow line a that the preset camera does not capture. When the preset vehicle is driving in lanes b and c, the preset camera can identify the four lane lines a, b, c, and d from the images it captures and output the corresponding lane line parameters describing these four lane lines.

[0082] An inertial navigation system (INS) is typically an inertial navigation system within a pre-defined vehicle. It is used to identify the vehicle's attitude during its movement and output corresponding attitude information. This attitude information may include the following: speed, acceleration, angular velocity, yaw angle, and position.

[0083] It should be noted that the lane line parameters output by the preset camera, the dynamic parameters of nearby moving targets, and the vehicle attitude parameters output by the inertial navigation device are preset data of the vehicle within the same time period, in order to facilitate the generation of road maps.

[0084] 202. Determine the preset vehicle trajectory based on vehicle attitude parameters;

[0085] In this embodiment, the driving trajectory of a preset vehicle can be determined based on the change in the vehicle's position over time in the vehicle attitude parameters. Alternatively, a more accurate driving trajectory can be determined by comprehensively considering factors such as speed, acceleration, angular velocity, yaw angle, and position in the vehicle attitude parameters, thereby improving the accuracy of the generated road map.

[0086] 203. Based on the driving trajectory, determine the center line of the first lane of the road where the vehicle is located;

[0087] In this embodiment, the lane center line is a lane line used to separate oncoming and offcoming lanes. For example, the lane center line can be a double yellow line or a single yellow line. Taking a double yellow line as an example, one side of the double yellow line has several lanes in one direction, and the other side has several lanes in the opposite direction.

[0088] In some embodiments of this application, determining the center line of the first lane of the road where the preset vehicle is located based on the driving trajectory may include: directly using the shape of the driving trajectory as the shape of the center line of the first lane of the road where the preset vehicle is located, thereby obtaining a separate center line of the first lane. In other embodiments of this application, when determining the center line of the first lane of the road where the preset vehicle is located, the lane-changing situation of the preset vehicle may also be considered; for details, please refer to [link / reference needed]. Figure 3 The illustrated embodiment.

[0089] It should be noted that, through the solutions of this application embodiment, even without obtaining map data (or map data of sufficient accuracy), the shape of the first lane centerline can still be obtained through the above processing, thereby providing a sufficiently accurate basis for the construction of the simulation scene based on it. For example, regardless of whether map data is obtained, a dynamic simulation scene model can be constructed based on lane line parameters, dynamic parameters of nearby moving targets, and vehicle attitude parameters. At the same time, this application embodiment does not exclude the possibility of combining map data. In some embodiments of this application, after determining the first lane centerline of the road where the preset vehicle is located based on the driving trajectory, it may further include: obtaining the shape of the second road where the preset vehicle is located from a preset map data source. The preset map data source may be a pre-obtained online map. Based on the shape of the first lane centerline, the first road shape of the road where the preset vehicle is located is determined. It should be noted that the data sources for the first road shape and the second road shape are different. The first road shape is determined based on the driving trajectory of the preset vehicle, while the second road shape is obtained from a preset map data source. The similarity between the first road shape and the second road shape is determined. When the similarity is greater than a preset similarity, the accuracy of the determined first vehicle centerline is considered high, and the step of generating static road data based on lane line parameters, vehicle attitude parameters, and the first lane centerline is executed. When the similarity is less than or equal to the preset similarity, the accuracy of the determined first vehicle centerline is considered low, and the step of generating static road data based on lane line parameters, vehicle attitude parameters, and the first lane centerline is not executed.

[0090] Furthermore, since the obtained lane line parameters, dynamic parameters of nearby moving targets, and vehicle attitude parameters are parameters over a period of time, after step 201, this time period can be divided into multiple time segments. Each time segment corresponds to a portion of lane line parameters, a portion of dynamic parameters, and a portion of vehicle attitude parameters. In this way, only for the lane line parameters, vehicle attitude parameters, and first lane centerline of the time segment with a similarity greater than a preset similarity, the generation of road static data and subsequent steps based on the lane line parameters, vehicle attitude parameters, and first lane centerline can be performed.

[0091] 204. Based on lane line parameters, vehicle attitude parameters, and the center line of the first lane, generate static road data;

[0092] The road map in this embodiment includes static road data, which refers to fixed, unchanging data on the road, such as the number of lanes, lane types (e.g., motor vehicle lanes, non-motor vehicle lanes, emergency lanes, bus lanes), intersections, and road shape. For example, the road map can be an OpenX map. OpenX is a set of protocols developed for maps needed for automated driving testing. OpenX maps mainly include OpenDRIVE data and OpenSCENARIO data. OpenDRIVE data is used to describe static road information, while OpenSCENARIO data is used to describe dynamic information and traffic participant behavior. Therefore, static road data can be OpenDRIVE data.

[0093] In some embodiments of this application, generating static road data based on lane line parameters, vehicle attitude parameters, and the center line of the first lane may include: determining the number and type of lanes traveling in the same direction as the preset vehicle based on the lane line parameters, thereby obtaining lane information (the lane information includes the number and type of lanes traveling in the same direction as the preset vehicle). For example, when the number of lane lines in the lane line parameters is 4, the number of lanes can be 3. Another example is when the lane line parameters include double solid lines, the lanes on either side of the double solid lines are motor vehicle lanes. Based on the vehicle attitude parameters, determining whether the preset vehicle has turned / made a U-turn to determine whether the preset vehicle's location is an intersection, thereby obtaining the first lane center line. The system includes: 1) intersection information (including the location information of the intersection within the road where the preset vehicle is located); 2) change in the vehicle's orientation based on changes in the yaw angle in the vehicle's attitude parameters, thus determining whether the preset vehicle has turned / made a U-turn. It is understood that a preset vehicle's turn / U-turn generally occurs at an intersection; 3) determining the first road shape based on the shape of the first lane centerline, i.e., using the shape of the first lane centerline as the first road shape; and 4) generating static road data based on lane information, first intersection information, and first road shape (which may also be supplemented by map information from a pre-acquired online map).

[0094] In some embodiments of this application, generating static road data based on lane information, first intersection information, and first road shape may include: determining whether a vehicle crosses the road where a preset vehicle is located based on dynamic parameters of nearby moving targets, thereby determining the intersection location within the road where the preset vehicle is located, and obtaining second intersection information; generating static road data based on lane information, first intersection information, second intersection information, and first road shape. It is understood that when other vehicles cross the road where the preset vehicle is located, it indicates that there is an intersection at the location where the vehicle crosses; therefore, the second intersection information includes the location information of the intersection within the road where the preset vehicle is located. By combining the first intersection information and the second intersection information to generate static road data, the generated static road data becomes more accurate and complete.

[0095] It should be noted that in the road described by the static road data, the shape of the road matches the shape of the center line of the first lane, the number of lanes, lane width, lane type, etc. in the road match the lane information, and the intersection situation in the road (such as where there are intersections and what type of intersections) matches the intersection information. Thus, it can more accurately reflect the actual road environment in which the preset vehicle is driving. At the same time, the static road data also describes how the preset vehicle moves over a period of time, such as the position of the preset vehicle on the road at each moment.

[0096] 205. Generate dynamic scene data based on the dynamic parameters of nearby moving targets and vehicle attitude parameters.

[0097] The road map in this embodiment includes dynamic scene data on the road. Dynamic scene data refers to data that dynamically changes on the road, such as the position, speed, and driving status of vehicles and pedestrians on the road at the same time. The driving status may include lane changing, turning, braking, etc. Taking an OpenX map as an example, the dynamic scene data can be OpenSCENARIO data in the OpenX map.

[0098] In some embodiments of this application, generating dynamic scene data based on the dynamic parameters of nearby moving targets and vehicle attitude parameters may include: determining a first motion process of nearby moving targets based on the dynamic parameters of nearby moving targets, wherein multiple nearby moving targets may exist simultaneously on the road where the preset vehicle is located, and the nearby moving targets may be nearby vehicles, pedestrians, etc., and different nearby moving targets correspond to different first motion processes; determining a second motion process of the preset vehicle based on the vehicle attitude parameters; and generating dynamic scene data based on the first motion process and the second motion process within the same time period.

[0099] It should be noted that the road scene described by the dynamic scene data includes the activity process of the preset vehicles and nearby moving targets.

[0100] The road map generation method provided in this application determines the static road and dynamic scene by using lane line parameters output by the camera, dynamic parameters of nearby moving targets, and vehicle attitude parameters output by the inertial navigation device, thereby generating a road map, reducing the cost of generating road maps and increasing efficiency.

[0101] In some embodiments of this application, based on the road map generation method, a back-annotation method is also provided, which includes:

[0102] Simulation modeling is performed on the static road data in the road map generated by any of the above generation methods to obtain a road model, which is a simulated road, including simulated road surface, simulated lane lines, simulated road signs, etc.

[0103] Simulation modeling is performed based on dynamic scene data in road maps to obtain multiple moving target models on the road model and the motion parameters of multiple moving target models. The moving target models are the simulated dynamic objects, including simulated dynamic people, vehicles, etc.

[0104] Based on a road model, multiple moving target models on the road model, and the motion parameters of the multiple moving target models, a dynamic simulation scene model of the road map is generated. The dynamic simulation scene model includes a road model, moving target models that can move according to motion parameters, and simulated static objects such as simulated static people, vehicles, road signs, etc. It can be understood that the scene displayed by the dynamic simulation scene model is the same as or similar to the scene of the preset vehicle and its vicinity during the actual driving process of the preset vehicle.

[0105] Acquire simulation video data at a specified location and from a specified viewpoint in a dynamic simulation scene model. The specified location can be any location in the dynamic simulation scene model, such as the roof of a preset vehicle. The specified viewpoint can be any direction, such as the viewpoint facing the front or rear of the preset vehicle. The simulation video data is the image rendered from the specified location and viewpoint.

[0106] The simulation video data is injected into the terminal where the specified algorithm is located. The specified algorithm can be a vehicle control algorithm, a perception and recognition algorithm, etc. The vehicle control algorithm can be a related algorithm of intelligent driving. The terminal where the vehicle control algorithm is located is used to train, verify, and test the vehicle control algorithm. It can be understood that after the simulation video data is injected back into the terminal where the specified algorithm is located, the terminal where the specified algorithm is located can train, verify, and test the specified algorithm based on the simulation video data.

[0107] The solutions disclosed in this application, through the construction of dynamic simulation scene models and the rendering of simulated video data, can provide richer, freer, and more diverse materials with different perspectives and framing positions for training, verification, and testing. For example, if a vehicle does not have a roof-mounted camera, the solution based on this application can generate simulated video data from cameras at positions and perspectives such as the front and rear of the vehicle roof. Furthermore, it can effectively ensure that the constructed dynamic simulation scene model accurately reflects the real scene. This makes the training, verification, and testing of vehicle control algorithms, perception and recognition algorithms, etc., more meaningful and helps ensure the effectiveness of such training, verification, and testing.

[0108] Based on the above embodiments of this application, the beneficial effects of the above embodiments are described in detail as follows:

[0109] 1. The embodiments of this application can be used to generate road maps based on information collected by a preset camera and inertial navigation device on a preset vehicle when map data is completely unavailable or map data with sufficient accuracy is unavailable. These maps can then be used to construct dynamic simulation scene models.

[0110] 2. Because the map data from the preset map data source is often not updated in a timely manner and has a lag, for example, some roads in reality are under construction or rerouting, but the map data has not been updated accordingly, making the map data inaccurate. Therefore, this application generates road maps by directly collecting information from preset cameras and inertial navigation devices on preset vehicles, and uses this information to construct dynamic simulation scene models, using only the map data from the preset map data source as an auxiliary verification method.

[0111] 3. If map data from a pre-defined map data source is used directly to construct a dynamic simulation scene model, then accurate positioning of the pre-defined vehicle is required when placing the dynamic and static objects detected by the pre-defined vehicle into the dynamic simulation scene model. However, the accuracy and precision of the pre-defined vehicle's positioning may be difficult to guarantee. For example, in tunnels or under conditions of poor communication, accurate positioning data of the pre-defined vehicle may not be available. In such cases, the constructed dynamic simulation scene model is prone to errors. The embodiments of this application do not have this problem and are less likely to produce similar errors.

[0112] In some embodiments of this application, the vehicle may change lanes during the process of determining the center line of the first lane of the road where the vehicle is located using its driving trajectory. Generally, lane changes are not considered when determining a vehicle's driving trajectory, as the trajectory is typically used to trace the vehicle's journey, and lane changes do not affect this tracing. However, the embodiments of this application aim to construct a dynamic simulation scenario model and perform data back-injection. The vehicle control algorithm and perception recognition algorithm focus precisely on the various events that occur during the vehicle's movement. Therefore, whether the vehicle changes lanes is crucial when determining the driving trajectory of the vehicle and accordingly deciding the lane shape. Furthermore, the dynamic simulation scenario model is generally a simulation of the scene traversed by the vehicle over a certain distance and time. Since the distance and time are usually short, whether the vehicle changes lanes significantly impacts the shape of the driving trajectory, highlighting the importance of lane changes.

[0113] Furthermore, since lane centerlines are generally determined by combining the driving trajectories of multiple vehicles, some of which changed lanes and some did not, the impact of a few vehicles changing lanes on the lane centerline can be eliminated by accumulating and fusing the driving trajectories of multiple vehicles. Therefore, it is generally not necessary to correct the driving trajectories. However, this application constructs a dynamic simulation scene model based on a single vehicle (i.e., a preset vehicle), and there is no accumulation and fusion of multiple driving trajectories. Therefore, it is necessary to correct the driving trajectory of the preset vehicle.

[0114] Therefore, in order to ensure the accuracy of the determined road shape, a trajectory correction process can be introduced, specifically as follows: Figure 3 As shown, based on the driving trajectory, the center line of the first lane of the road where the preset vehicle is located is determined, including:

[0115] 301. Based on vehicle attitude parameters, determine whether the preset vehicle has changed lanes;

[0116] In this embodiment of the application, the changes in vehicle attitude parameters such as acceleration, angular velocity, yaw angle, and position are used to determine whether the preset vehicle has changed lanes.

[0117] 302. If the preset vehicle changes lanes, determine the lane change distance of the preset vehicle;

[0118] In this embodiment, the lane change distance refers to the amount of influence of a preset vehicle lane change on its driving trajectory.

[0119] In some embodiments of this application, determining the lane-changing distance of a preset vehicle includes: obtaining the total lane width between the lane the preset vehicle was in before changing lanes and the lane the preset vehicle is in after changing lanes (e.g., in...). Figure 4In this context, the total lane width can be the distance L between lane line a and lane line c; based on the total lane width, the average lane width between the lane where the vehicle was before changing lanes and the lane where the vehicle is after changing lanes is determined (e.g., in...). Figure 4 In this context, the average lane width can be L / 2; the average lane width is used as the preset lane change distance for vehicles.

[0120] 303. Based on the lane change distance, correct the driving trajectory, and use the shape of the corrected driving trajectory as the shape of the first lane centerline of the road where the vehicle is located, to obtain the first lane centerline of the road where the vehicle is located.

[0121] In this embodiment of the application, the driving trajectory is corrected based on the lane change distance. Specifically, the trajectory after the lane change is translated in the opposite direction of the lane change direction, and the translation distance is the lane change distance, thus obtaining the corrected driving trajectory. For example, in Figure 4 In the middle, the trajectory after the lane change is Figure 4 The corrected driving trajectory for the middle section, section 2, is as follows: Figure 4 If the right-hand portion of trajectory 1 + trajectory 2 is not corrected, then... Figure 4 The middle section, trajectory 1 and trajectory 2, will be fitted together, resulting in a curved shape.

[0122] The solution disclosed in this application corrects the driving trajectory of a preset vehicle when the vehicle changes lanes, so as to ensure the accuracy of the determined road shape.

[0123] To better implement the road map generation method in the embodiments of this application, based on the road map generation method, the embodiments of this application also provide a road map generation device, such as... Figure 5 As shown, the road map generation device 500 includes:

[0124] The acquisition unit 501 is used to acquire lane line parameters and dynamic parameters of nearby moving targets output by a preset camera on a preset vehicle, as well as vehicle attitude parameters output by an inertial navigation device on the preset vehicle.

[0125] The first determining unit 502 is used to determine the driving trajectory of the preset vehicle based on the vehicle attitude parameters.

[0126] The second determining unit 503 is used to determine the center line of the first lane of the road where the preset vehicle is located based on the driving trajectory.

[0127] The first generation unit 504 is used to generate the road static data based on the lane line parameters, the vehicle attitude parameters, and the first lane centerline.

[0128] The second generation unit 505 is used to generate the dynamic scene data based on the dynamic parameters of the nearby moving target and the vehicle attitude parameters.

[0129] The road map generation apparatus provided in this application determines the static road and dynamic scene by using lane line parameters output by a camera, dynamic parameters of nearby moving targets, and vehicle attitude parameters output by an inertial navigation device, thereby generating a road map, reducing the cost of generating road maps and increasing efficiency.

[0130] In some embodiments of this application, the first generation unit 504 is specifically used for:

[0131] Based on the lane line parameters, the number and type of lanes in the same direction of travel as the preset vehicle are determined to obtain lane information;

[0132] Based on the vehicle posture parameters, it is determined whether the preset vehicle has turned / made a U-turn, so as to determine whether the location of the preset vehicle is an intersection, and the first intersection information is obtained.

[0133] Based on the shape of the center line of the first lane, determine the first road shape of the road where the preset vehicle is located;

[0134] Based on the lane information, the first intersection information, and the first road shape, the static road data is generated.

[0135] In some embodiments of this application, the first generation unit 504 is specifically used for:

[0136] Based on the dynamic parameters of the nearby moving targets, it is determined whether a vehicle crosses the road where the preset vehicle is located, so as to determine the intersection position in the road where the preset vehicle is located and obtain the second intersection information.

[0137] Based on the lane information, the first intersection information, the second intersection information, and the first road shape, the static road data is generated.

[0138] In some embodiments of this application, the second generation unit 505 is specifically used for:

[0139] Based on the dynamic parameters of the nearby moving target, the first motion process of the nearby moving target is determined;

[0140] Based on the vehicle attitude parameters, the second motion process of the preset vehicle is determined;

[0141] The dynamic scene data is generated based on the first motion process and the second motion process within the same time period.

[0142] In some embodiments of this application, the second determining unit 503 is specifically used for:

[0143] Based on the vehicle attitude parameters, determine whether the preset vehicle has changed lanes;

[0144] If the preset vehicle changes lanes, determine the lane change distance of the preset vehicle;

[0145] Based on the lane change distance, the driving trajectory is corrected, and the shape of the corrected driving trajectory is used as the shape of the center line of the first lane of the road where the vehicle is located.

[0146] In some embodiments of this application, the second determining unit 503 is specifically used for:

[0147] Get the total lane width between the lane where the vehicle was located before changing lanes and the lane where the vehicle is located after changing lanes.

[0148] Based on the total lane width, determine the average lane width between the lane where the preset vehicle was located before changing lanes and the lane where the preset vehicle was located after changing lanes.

[0149] The average lane width is used as the preset lane change distance for vehicles.

[0150] In some embodiments of this application, the first generating unit 504 is further configured to:

[0151] Obtain the second road shape of the road where the vehicle is located from the preset map data source;

[0152] Based on the shape of the center line of the first lane, determine the shape of the first road where the preset vehicle is located.

[0153] Determine the similarity between the shapes of the first road and the second road;

[0154] When the similarity is greater than a preset similarity, the step of generating the road static data based on the lane line parameters, the vehicle posture parameters, and the first lane centerline is executed.

[0155] In addition to the road map generation methods and apparatus and the back-annotation method described above, embodiments of this application also provide a computer device that integrates any of the road map generation apparatuses provided in the embodiments of this application. The computer device includes:

[0156] One or more processors;

[0157] Memory; and

[0158] One or more applications, wherein the applications are stored in memory and configured to be executed by a processor as steps of any of the methods in any of the embodiments of the above methods.

[0159] This application also provides a computer device that integrates any of the road map generation apparatuses provided in this application. For example... Figure 6 As shown, it illustrates a structural schematic diagram of the computer device involved in the embodiments of this application, specifically:

[0160] The computer device may include components such as a processor 601 with one or more processing cores, a storage unit 602 with one or more computer-readable storage media, a power supply 603, and an input unit 604. Those skilled in the art will understand that... Figure 6 The computer device structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0161] The processor 601 is the control center of the computer device. It connects various parts of the computer device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the storage unit 602, and by calling data stored in the storage unit 602, thereby providing overall monitoring of the computer device. Optionally, the processor 601 may include one or more processing cores; preferably, the processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 601.

[0162] Storage unit 602 can be used to store software programs and modules. Processor 601 executes various functional applications and data processing by running the software programs and modules stored in storage unit 602. Storage unit 602 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, storage unit 602 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, storage unit 602 may also include a memory controller to provide processor 601 with access to storage unit 602.

[0163] The computer device also includes a power supply 603 that supplies power to the various components. Preferably, the power supply 603 can be logically connected to the processor 601 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 603 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0164] The computer device may also include an input unit 604, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0165] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in the embodiments of this application, the processor 601 in the computer device loads the executable files corresponding to the processes of one or more applications into the storage unit 602 according to the following instructions, and the processor 601 runs the applications stored in the storage unit 602 to realize various functions, as follows:

[0166] Acquire lane line parameters and dynamic parameters of nearby moving targets output by the preset camera on the preset vehicle, and acquire vehicle attitude parameters output by the inertial navigation device on the preset vehicle.

[0167] Based on the vehicle attitude parameters, the driving trajectory of the preset vehicle is determined;

[0168] Based on the driving trajectory, determine the center line of the first lane of the road where the preset vehicle is located;

[0169] The road static data is generated based on the lane line parameters, the vehicle attitude parameters, and the first lane centerline;

[0170] The dynamic scene data is generated based on the dynamic parameters of the nearby moving target and the vehicle attitude parameters.

[0171] Therefore, embodiments of this application provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk, etc. The computer-readable storage medium stores multiple instructions, which can be loaded by a processor to execute the steps in any of the methods provided in embodiments of this application. For example, the instructions can execute the following steps:

[0172] Acquire lane line parameters and dynamic parameters of nearby moving targets output by the preset camera on the preset vehicle, and acquire vehicle attitude parameters output by the inertial navigation device on the preset vehicle.

[0173] Based on the vehicle attitude parameters, the driving trajectory of the preset vehicle is determined;

[0174] Based on the driving trajectory, determine the center line of the first lane of the road where the preset vehicle is located;

[0175] The road static data is generated based on the lane line parameters, the vehicle attitude parameters, and the first lane centerline;

[0176] The dynamic scene data is generated based on the dynamic parameters of the nearby moving target and the vehicle attitude parameters.

[0177] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0178] The foregoing has provided a detailed description of a road map generation method, a back-annotation method, a computer device, and a medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and its core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for generating a road map, characterized in that, The road map includes static road data and dynamic scene data on the road, and the generation method includes: Acquire lane line parameters and dynamic parameters of nearby moving targets output by the preset camera on the preset vehicle, and acquire vehicle attitude parameters output by the inertial navigation device on the preset vehicle. Based on the vehicle attitude parameters, the driving trajectory of the preset vehicle is determined; Based on the driving trajectory, determine the center line of the first lane of the road where the preset vehicle is located; The road static data is generated based on the lane line parameters, the vehicle attitude parameters, and the first lane centerline; The dynamic scene data is generated based on the dynamic parameters of the nearby moving targets and the vehicle attitude parameters; The step of generating the road static data based on the lane line parameters, the vehicle attitude parameters, and the first lane centerline includes: Based on the lane line parameters, the number and type of lanes in the same direction of travel as the preset vehicle are determined to obtain lane information; Based on the vehicle posture parameters, it is determined whether the preset vehicle has turned / made a U-turn, so as to determine whether the location of the preset vehicle is an intersection, and the first intersection information is obtained. Based on the shape of the center line of the first lane, determine the first road shape of the road where the preset vehicle is located; Based on the lane information, the first intersection information, and the first road shape, the static road data is generated; The step of determining the center line of the first lane of the road where the vehicle is located based on the driving trajectory includes: Based on the vehicle attitude parameters, determine whether the preset vehicle has changed lanes; If the preset vehicle changes lanes, determine the lane change distance of the preset vehicle; Based on the lane change distance, the driving trajectory is corrected, and the shape of the corrected driving trajectory is used as the shape of the center line of the first lane of the road where the vehicle is located.

2. The method for generating a road map as described in claim 1, characterized in that, The process of generating the static road data based on the lane information, the first intersection information, and the first road shape includes: Based on the dynamic parameters of the nearby moving targets, it is determined whether a vehicle crosses the road where the preset vehicle is located, so as to determine the intersection position in the road where the preset vehicle is located and obtain the second intersection information. Based on the lane information, the first intersection information, the second intersection information, and the first road shape, the static road data is generated.

3. The method for generating road maps as described in claim 1, characterized in that, The generation of the dynamic scene data based on the dynamic parameters of the nearby moving target and the vehicle attitude parameters includes: Based on the dynamic parameters of the nearby moving target, the first motion process of the nearby moving target is determined; Based on the vehicle attitude parameters, the second motion process of the preset vehicle is determined; The dynamic scene data is generated based on the first motion process and the second motion process within the same time period.

4. The method for generating a road map as described in claim 1, characterized in that, Determining the lane-changing distance of the preset vehicle includes: Get the total lane width between the lane where the vehicle was located before changing lanes and the lane where the vehicle is located after changing lanes. Based on the total lane width, determine the average lane width between the lane where the preset vehicle was located before changing lanes and the lane where the preset vehicle was located after changing lanes. The average lane width is used as the preset lane change distance for vehicles.

5. The method for generating a road map as described in claim 1, characterized in that, After determining the center line of the first lane of the road where the preset vehicle is located based on the driving trajectory, the method further includes: Obtain the second road shape of the road where the vehicle is located from the preset map data source; Based on the shape of the center line of the first lane, determine the first road shape of the road where the preset vehicle is located; Determine the similarity between the first road shape and the second road shape; When the similarity is greater than a preset similarity, the step of generating the road static data based on the lane line parameters, the vehicle posture parameters, and the first lane centerline is executed.

6. A reinjection method, characterized in that, The reinjection method includes: A road model is obtained by simulation modeling based on the static road data in the road map generated by the generation method according to any one of claims 1 to 5. Simulation modeling is performed based on the dynamic scene data in the road map to obtain multiple moving target models on the road model and the motion parameters of the multiple moving target models. Based on the road model, multiple moving target models on the road model, and the motion parameters of the multiple moving target models, a dynamic simulation scene model of the road map is generated; Acquire simulation video data at a specified location and from a specified viewpoint in the dynamic simulation scene model; The simulated video data is injected into the terminal where the specified algorithm is located.

7. A computer device, characterized in that, The computer device includes: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, It stores a computer program, which is loaded by a processor to perform the steps of the method according to any one of claims 1 to 6.

Images