Scene reconstruction method and system and electronic equipment
By acquiring vehicle driving data and environmental information, the vehicle driving trajectory is automatically determined and static maps and dynamic scene files are generated, which solves the problems of time-consuming and inefficient scene reconstruction in existing technologies and realizes efficient and accurate automatic scene reconstruction.
Patent Information
- Application Number
- CN202510953950.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-10
- Publication Date
- 2025-10-17
AI Technical Summary
In existing technologies, scene reconstruction in road testing of vehicle assisted driving functions is time-consuming and inefficient, and the quality of the reconstructed scene depends on the understanding of simulation engineers, resulting in inefficient reconstruction of autonomous driving scenes.
By acquiring the target vehicle's driving data and environmental information, the vehicle's driving trajectory is automatically determined, static map files and dynamic scene files are generated, and automatic scene reconstruction is achieved using the distance between the vehicle and the lane line and environmental information.
It achieves efficient and fast scene reconstruction, ensures the quality of the reconstructed scene, eliminates the need for manual reconstruction, and improves reconstruction efficiency and accuracy.
Smart Images
Figure CN120807687A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the field of assisted driving, and in particular to a scene reconstruction method and system and an electronic device. BACKGROUND
[0002] For road testing of the assisted driving function of a vehicle, problem data is usually recorded by a road testing engineer, and the recorded data is handed over to a simulation engineer to perform scene reconstruction of the problem data in a simulation test environment.
[0003] For scene reconstruction of the problem data, the simulation engineer needs to analyze and locate the problem, determine the time period that needs to be reconstructed, and then use the scene information synchronized by the camera to plan the logical scene. The scene corresponding to the problem data is manually reconstructed based on the above information.
[0004] However, manual scene reconstruction is time-consuming and inefficient, and the quality of the reconstructed scene is related to the understanding of the simulation engineer. SUMMARY
[0005] Therefore, the present application provides a scene reconstruction method, system and electronic device, and the specific solutions are as follows:
[0006] A scene reconstruction method comprises:
[0007] Obtaining driving data of a target vehicle collected during driving of the target vehicle and environmental information of the target vehicle during driving of the target vehicle;
[0008] Determining a vehicle driving trajectory of the target vehicle based on the driving data of the target vehicle;
[0009] Generating a static map file using a distance between the target vehicle and a lane line included in the driving data of the target vehicle and the vehicle driving trajectory;
[0010] Generating a dynamic scene file based on the vehicle driving trajectory and the environmental information, so as to obtain a reconstructed scene composed of the vehicle driving trajectory, the static map file and the dynamic scene file.
[0011] Further, the generating of the static map file using the distance between the target vehicle and the lane line included in the driving data of the target vehicle and the vehicle driving trajectory comprises:
[0012] Determining lane information passed through by the target vehicle during driving of the target vehicle using the distance between the target vehicle and the lane line included in the driving data of the target vehicle and the vehicle driving trajectory, the lane information at least including a lane line trajectory and a lane width of a lane passed through by the target vehicle;
[0013] generate a static map file based on the lane information.
[0014] Further, the distance between the target vehicle and the lane line included in the driving data of the target vehicle and the vehicle driving trajectory are used to determine the lane information passed by the target vehicle during driving.
[0015] If it is determined that the distance between the target vehicle and the lane line at the first time is not included in the driving data of the target vehicle, the distance between the target vehicle and the lane line at the second time included in the driving data is determined, wherein the second time is a time before the first time, and the time interval between the first time and the second time is less than a specific time length.
[0016] The distance between the target vehicle and the lane line at the second time included in the driving data is used to determine the lane line trajectory and the lane width of the lane passed by the target vehicle at the first time.
[0017] Further, the distance between the target vehicle and the lane line included in the driving data of the target vehicle and the vehicle driving trajectory are used to determine the lane information passed by the target vehicle during driving.
[0018] If it is determined that the distance between the target vehicle and the lane line at the first time is not included in the driving data of the target vehicle, the distance between the target vehicle and the lane line at the second time included in the driving data is determined, wherein the second time is a time before the first time, and the time interval between the first time and the second time is less than a specific time length.
[0019] The distance between the target vehicle and the lane line at the second time included in the driving data is used to determine the lane line trajectory and the lane width of the lane passed by the target vehicle at the first time.
[0020] Further, the distance between the target vehicle and the lane line included in the driving data of the target vehicle and the vehicle driving trajectory are used to determine the lane information passed by the target vehicle during driving.
[0021] The distance between the target vehicle and the lane line included in the driving data of the target vehicle is used to segment the lane passed by the target vehicle during driving to obtain the distance between the target vehicle and the lane line and the vehicle driving trajectory corresponding to each segment of the lane.
[0022] The distance between the target vehicle and the lane line and the vehicle driving trajectory corresponding to each segment of the lane are used to determine the lane information of each segment of the lane passed by the target vehicle during driving.
[0023] Further, the generating the static map file based on the lane information comprises:
[0024] The lane information is written in a first language to generate the static map file, wherein the first language is used to describe the static map.
[0025] Further, the generating the dynamic scene file based on the vehicle trajectory and the environment information comprises:
[0026] The information of the traffic participant in the environment information is obtained, and the information of the traffic participant at least comprises a distance of the traffic participant relative to the target vehicle, a speed, and a pose of the traffic participant;
[0027] The information of the traffic participant and the vehicle trajectory are stored into a target file;
[0028] The dynamic event is written in a second language based on the target file to generate the dynamic scene file, wherein the second language is used to describe the dynamic scene.
[0029] A scene reconstruction system comprises:
[0030] An obtaining unit is configured to obtain driving data of a target vehicle collected during driving of the target vehicle and environment information of the target vehicle during driving of the target vehicle;
[0031] A determining unit is configured to determine a vehicle trajectory of the target vehicle based on the driving data of the target vehicle;
[0032] A first generating unit is configured to generate a static map file by using a distance between the target vehicle and a lane line included in the driving data of the target vehicle and the vehicle trajectory;
[0033] A second generating unit is configured to generate a dynamic scene file based on the vehicle trajectory and the environment information, so as to obtain a reconstructed scene composed of the vehicle trajectory, the static map file, and the dynamic scene file.
[0034] An electronic device comprises:
[0035] a processor configured to obtain driving data of a target vehicle collected during the driving process of the target vehicle and information about the environment in which the target vehicle is located during the driving process; determine a driving trajectory of the target vehicle based on the driving data of the target vehicle; generate a static map file using the distance between the target vehicle and a lane line included in the driving data of the target vehicle and the vehicle driving trajectory; and generate a dynamic scene file based on the vehicle driving trajectory and the environmental information to obtain a reconstructed scene composed of the vehicle driving trajectory, the static map file, and the dynamic scene file;
[0036] The memory is used to store the program required by the processor to execute the above processing process.
[0037] A readable storage medium for storing at least one set of instructions;
[0038] The instruction set is used to be called and to execute at least any of the scene reconstruction methods described above.
[0039] It can be seen from the above technical solutions that the scene reconstruction method, system and electronic device disclosed in the present application obtain the target vehicle's driving data and the environmental information of the target vehicle during the driving process; determine the target vehicle's driving trajectory based on the target vehicle's driving data; generate a static map file using the distance between the target vehicle and the lane line and the vehicle's driving trajectory included in the target vehicle's driving data; generate a dynamic scene file based on the vehicle's driving trajectory and environmental information, so as to obtain a reconstructed scene consisting of the vehicle's driving trajectory, the static map file and the dynamic scene file. When scene reconstruction is required, this solution obtains the target vehicle's driving data and environmental information during the driving process, and first determines the target vehicle's driving trajectory, and generates a static map file based on the vehicle's driving trajectory and driving data. At the same time, it generates a dynamic scene file using the vehicle's driving trajectory and environmental information, thereby obtaining a reconstructed scene consisting of the vehicle's driving trajectory, the static map file and the dynamic scene file, realizing automatic reconstruction of the scene with high efficiency and short time consumption, and ensuring the quality of the reconstructed scene without the need for manual reconstruction, thus avoiding the problem of the inability to ensure the quality of the manually reconstructed scene. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0041] Figure 1A flowchart of a scene reconstruction method disclosed by an embodiment of the present application;
[0042] Figure 2 A flowchart of a scene reconstruction method disclosed by an embodiment of the present application;
[0043] Figure 3 A schematic diagram of a trajectory of a target vehicle in a road test process disclosed by an embodiment of the present application;
[0044] Figure 4 A schematic diagram of a corresponding relationship between a target vehicle and a lane and a lane line disclosed by an embodiment of the present application;
[0045] Figure 5 A flowchart of a scene reconstruction method disclosed by an embodiment of the present application;
[0046] Figure 6 A structural schematic diagram of a scene reconstruction system disclosed by an embodiment of the present application;
[0047] Figure 7 A structural schematic diagram of an electronic device disclosed by an embodiment of the present application. DETAILED DESCRIPTION
[0048] The embodiments of the present application are described below in conjunction with the accompanying drawings. The terms used in the embodiment part of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.
[0049] The embodiments of the present application are described below in conjunction with the accompanying drawings. It is known to those skilled in the art that, as technology develops and new scenarios appear, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.
[0050] The terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, and this is only a distinguishing way used in the description of the embodiments of the present application to describe the objects with the same attributes. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, so that the processes, methods, systems, products or devices containing a series of units do not necessarily limit to those units, but can include other units not clearly listed or inherent to these processes, methods, products or devices.
[0051] The present application discloses a scene reconstruction method, a flowchart thereof is shown as Figure 1 , including:
[0052] Step S11, obtaining driving data of a target vehicle collected in a driving process of the target vehicle and environment information in which the target vehicle is located in the driving process of the target vehicle;
[0053] Step S12, determining a vehicle driving trajectory of the target vehicle based on the driving data of the target vehicle;
[0054] Step S13, generating a static map file by using a distance between the target vehicle and a lane line included in the driving data of the target vehicle and the vehicle driving trajectory;
[0055] Step S14, generating a dynamic scene file based on the vehicle driving trajectory and the environment information, so as to obtain a reconstructed scene composed of the vehicle driving trajectory, the static map file and the dynamic scene file.
[0056] For road testing of an auxiliary driving function of a vehicle, problem data is usually recorded by a road testing engineer, and the recorded data is handed over to a simulation engineer to perform scene reconstruction of the problem data in a simulation test environment. For scene reconstruction of the problem data, the simulation engineer needs to analyze and locate the problem to determine a time period that needs to be reconstructed, and then logically plan a scene by using synchronous scene information of a camera. The scene corresponding to the problem data is manually reconstructed based on the above information. However, manual reconstruction of the scene has problems such as long time consumption and low efficiency, and the quality of the reconstructed scene is related to the understanding of the simulation engineer on the scene.
[0057] Therefore, the present scheme automatically performs scene reconstruction. When scene reconstruction is needed, driving data in a driving process of a target vehicle and environment information are obtained, a vehicle driving trajectory of the target vehicle is determined based on the driving data, a static map file is further generated based on the vehicle driving trajectory, a dynamic scene file is generated based on the vehicle driving trajectory and the environment information, and a reconstructed scene composed of the vehicle driving trajectory, the static map file and the dynamic scene file is automatically reconstructed, so that the reconstruction efficiency and quality are ensured without manual reconstruction.
[0058] Road testing is a test on a driving state of a vehicle on a road. If there is problem data in the road testing, in order to determine a reason for the problem data, original data of the vehicle in a test process needs to be collected and scene reconstruction is performed to reconstruct scenes of the vehicle in different road sections in the test process, so as to analyze the reason for the problem data.
[0059] Therefore, when scene reconstruction is needed, a vehicle corresponding to the scene that needs to be reconstructed, i.e., a vehicle corresponding to problem data in road testing, is determined as a target vehicle, and driving data and environment information of the target vehicle in the road testing are obtained.
[0060] The driving data, i.e., the collected parameters of the target vehicle in the road test process, such as the speed, acceleration, heading angle, and timestamp of the target vehicle collected by the inertial navigation sensor on the target vehicle in the road test process, can also include the distance between the target vehicle and the lane line; the environmental data can be the information of the environment in which the target vehicle is located during the road test process, such as the speed, position, and attitude of each traffic participant on the road collected by the image collection sensor during the road test process, and road network information.
[0061] First, the vehicle driving trajectory of the target vehicle in the road test process is determined, and the driving data of the target vehicle is used to fit the vehicle driving trajectory. The speed, acceleration, heading angle, and timestamp of the target vehicle in the driving data can be converted into absolute position coordinate point information changing with time, i.e., the initial trajectory of the target vehicle, through integration and coordinate system conversion.
[0062] The coordinate system conversion can specifically be converting the vehicle coordinate system into a geodetic coordinate system to facilitate the construction of a scene in a unified coordinate system.
[0063] Further, to avoid the influence of sensor noise in the driving data collection process and to eliminate the error in the initial trajectory of the target vehicle, Kalman filtering can be used to smooth the initial trajectory of the target vehicle to obtain a processed vehicle driving trajectory of the target vehicle. The vehicle driving trajectory of the target vehicle eliminates the influence of sensor noise and avoids errors in the determined driving trajectory.
[0064] After obtaining the vehicle driving trajectory of the target vehicle, a static map file and a dynamic scene file can be generated using the vehicle driving trajectory of the target vehicle, thereby obtaining a reconstructed scene composed of at least the vehicle driving trajectory of the target vehicle, the static map file, and the dynamic scene file.
[0065] The sensors on the target vehicle can collect the distance between the sensors and the lane line at each time point, i.e., the distance between the target vehicle and the lane line corresponding to each time. The driving data can include the distance between the target vehicle and the lane line. Based on the vehicle driving trajectory of the target vehicle and the distance between the target vehicle and the lane line corresponding to each time, a static map file can be generated.
[0066] Since the environmental information may include: information such as the speed, position, posture, etc. of each traffic participant on the road of the target vehicle collected by the image acquisition sensor during the road test, as well as road network information, after determining the vehicle driving trajectory of the target vehicle, a dynamic scene file can be jointly generated based on the vehicle driving trajectory of the target vehicle, the information of each traffic participant, and the road network information to construct a dynamic scene.
[0067] The scene reconstruction method disclosed in this embodiment obtains the target vehicle's driving data and the environmental information of the target vehicle during the driving process; determines the target vehicle's driving trajectory based on the target vehicle's driving data; generates a static map file using the distance between the target vehicle and the lane line and the vehicle's driving trajectory included in the target vehicle's driving data; and generates a dynamic scene file based on the vehicle's driving trajectory and environmental information, so as to obtain a reconstructed scene consisting of the vehicle's driving trajectory, the static map file, and the dynamic scene file. When scene reconstruction is required, this solution obtains the target vehicle's driving data and environmental information during the driving process, and first determines the target vehicle's driving trajectory, and generates a static map file based on the vehicle's driving trajectory and driving data. At the same time, it generates a dynamic scene file using the vehicle's driving trajectory and environmental information, thereby obtaining a reconstructed scene consisting of the vehicle's driving trajectory, the static map file, and the dynamic scene file. This achieves automatic scene reconstruction with high efficiency and short time consumption, and ensures the quality of the reconstructed scene without the need for manual reconstruction, thus avoiding the problem of unguaranteed quality of manually reconstructed scenes.
[0068] This embodiment discloses a scene reconstruction method, the flow chart of which is as follows: Figure 2 Shown, including:
[0069] Step S21: obtaining the target vehicle's driving data and the target vehicle's driving environment information collected during the target vehicle's driving process;
[0070] Step S22: determining a vehicle driving trajectory of the target vehicle based on the driving data of the target vehicle;
[0071] Step S23: using the distance between the target vehicle and the lane line and the vehicle's driving trajectory included in the target vehicle's driving data, determine lane information passed by the target vehicle during the driving process, where the lane information includes at least: the lane line trajectory and lane width of the lane passed by the target vehicle;
[0072] Step S24: Generate a static map file based on the lane information;
[0073] Step S25: Generate a dynamic scene file based on the vehicle driving trajectory and environmental information, so as to obtain a reconstructed scene consisting of the vehicle driving trajectory, the static map file and the dynamic scene file.
[0074] After obtaining the driving data of the target vehicle collected in the driving process of the target vehicle, the driving data of the target vehicle can be used to determine the vehicle driving trajectory of the target vehicle. After determining the vehicle driving trajectory of the target vehicle, a static map file and a dynamic scene file can be generated based on the vehicle driving trajectory respectively to realize the reconstruction of the scene.
[0075] The static map file can be generated based on the vehicle driving trajectory of the target vehicle. Specifically, the distance between the target vehicle and the lane line included in the driving data of the target vehicle can be obtained. The lane and the lane width of the lane through which the target vehicle passes at each time point can be determined based on the distance between the target vehicle and the lane line at each time point and the vehicle driving trajectory, so as to further determine the lane line trajectory. The static map file can be generated based on the lane line trajectory and the lane width.
[0076] The vehicle driving trajectory of the target vehicle can be a trajectory composed of road segments through which the target vehicle passes at each time point during the road test, as shown in FIG. 1. Figure 3 As shown in FIG. 1, the target vehicle passes through the first road segment r1 at the first time t1 to the second time t2, passes through the second road segment r2 at the second time t2 to the third time t3, and passes through the third road segment r3 at the third time t3 to the fourth time t4.
[0077] The distance between the target vehicle and the lane line included in the driving data of the target vehicle not only includes the distance between the target vehicle and the lane line of the lane in which the target vehicle is located, but also includes the distance between the target vehicle and the lane line of other lanes outside the lane in which the target vehicle is located. For example, when the target vehicle is located in the second lane, the sensors on the target vehicle can collect the distance between the target vehicle and the lane line of the second lane, and also can collect the distance between the target vehicle and the lane line of the third lane and the first lane. The third lane is the lane on the right side of the second lane, and the first lane is the lane on the left side of the second lane.
[0078] As shown in FIG. 2, the distance between the target vehicle and the lane line included in the driving data of the target vehicle includes the distance between the target vehicle and the lane line of the lane in which the target vehicle is located, and also includes the distance between the target vehicle and the lane line of other lanes outside the lane in which the target vehicle is located. Figure 4 As shown in FIG. 2, the distance between the target vehicle and the lane line included in the driving data of the target vehicle includes the distance between the target vehicle and the lane line of the lane in which the target vehicle is located, and also includes the distance between the target vehicle and the lane line of other lanes outside the lane in which the target vehicle is located.
[0079] The distance between the target vehicle and the different lane lines at different time instants can be used to determine the lane in which the target vehicle is located at different time instants, the width of the lane at different time instants, and the position of the lane line corresponding to the target vehicle at different time instants.
[0080] The position of the lane line corresponding to the target vehicle at different time instants determined can be combined with the vehicle trajectory to obtain the lane line trajectory of the lane through which the target vehicle passes during the test, and thus the lane information, including at least the lane line trajectory of the lane through which the target vehicle passes and the width of the lane, can be determined. The lane line trajectory can be the trajectory of the lane lines on both sides of the lane in which the target vehicle is located, or the trajectory of the lane line on one side of the lane in which the target vehicle is located. If the lane line trajectory is on one side, the lane line on one side of the lane can be randomly selected for fitting the lane line trajectory.
[0081] In addition, the lane in which the target vehicle is located at different time instants and the width of the lane can be combined with the vehicle trajectory to obtain the trajectory of the lane through which the target vehicle passes during the test, which can correspond to the lane line trajectory.
[0082] After the distance between the target vehicle and the lane lines of each lane in the road segment through which the target vehicle passes at different time instants is determined, the number of lanes and the width of the lane included in different road segments can be determined, and thus the initial static map file of the road segment through which the target vehicle passes at different time instants can be fitted. Based on the initial static map file, the lane through which the target vehicle passes at different time instants on the initial static map file can be fitted based on the lane line trajectory of the lane through which the target vehicle passes, and thus the static map file can be obtained.
[0083] The scenario reconstruction method disclosed in the embodiment comprises the following steps: obtaining the driving data of a target vehicle collected during the driving of the target vehicle and the environmental information in which the target vehicle is located during the driving of the target vehicle; determining the vehicle driving trajectory of the target vehicle based on the driving data of the target vehicle; determining the lane information through which the target vehicle passes during the driving of the target vehicle based on the distance between the target vehicle and the lane line included in the driving data of the target vehicle and the vehicle driving trajectory, the lane information including at least the lane line trajectory of the lane through which the target vehicle passes and the width of the lane; generating a static map file based on the lane information; and generating a dynamic scenario file based on the vehicle driving trajectory and the environmental information, so as to obtain a reconstructed scenario composed of the vehicle driving trajectory, the static map file, and the dynamic scenario file. After the vehicle driving trajectory is obtained, the lane line trajectory of the lane through which the target vehicle passes and the width of the lane are determined based on the vehicle driving trajectory and the distance between the target vehicle and the lane line, and thus the static map file is generated, so as to ensure the accuracy of the lane and the lane line in the generated static map file.
[0084] Further, in the scene reconstruction method disclosed in the embodiment, the distance between the target vehicle and the lane line included in the driving data of the target vehicle and the driving track of the vehicle are used to determine the lane information passed by the target vehicle during driving, which can further include:
[0085] If it is determined that the distance between the target vehicle and the lane line at the first time is not included in the driving data of the target vehicle, the distance between the target vehicle and the lane line at the second time included in the driving data is determined, wherein the second time is a time before the first time, and the time interval between the first time and the second time is less than a specific time length; the distance between the target vehicle and the lane line at the second time included in the driving data is used to determine the lane line track and the lane width of the lane passed by the target vehicle at the first time.
[0086] In the process of determining the lane information, there may be a case of lane line disappearance, and whether the lane line disappears can be determined by the driving data, that is, it is determined that in the corresponding driving data of the target vehicle in this time period of the target vehicle test, which time corresponding to the distance between the target vehicle and the lane line is missing, then the missing time is determined as the first time, that is, there is a case of lane line disappearance at the first time.
[0087] For example: the target vehicle performs road test in the time period of 10:20-11:30 on a certain day, wherein only the distance between 10:37:05-10:38:32 is not detected between the target vehicle and the lane line in this time period, then each time in the time period of 10:37:05-10:38:32 is determined as the first time, and in the time period of 10:37:05-10:38:32, there is a case of lane line disappearance on the lane passed by the target vehicle.
[0088] In this case, in order to determine the lane information of the target vehicle in this period, that is, the lane line track and the lane width, the distance between the target vehicle and the lane line at the time before this period can be used to determine the distance between the target vehicle and the lane line in this period.
[0089] For example, to determine the distance between the target vehicle and the lane line at 10:37:05, the distance between the target vehicle and the lane line at a second time can be determined, wherein the second time is a time before the first time, and the time interval between the first time and the second time is less than a specific time length. For example, the second time is 10:37:04. The driving data obtained at 10:37:04 includes the distance between the target vehicle and the lane line. The time interval between 10:37:04 and 10:37:05 is short, and it can be assumed that the lane width does not change significantly and the vehicle does not deviate significantly laterally within this short time interval (the difference in the distance between the target vehicle and the lane line at different times determines the size of the lateral deviation of the vehicle). Alternatively, the lane width and the lateral deviation of the vehicle change according to the changes in the time period from 10:37:04 to 10:37:03. Therefore, the lane line trajectory and the lane width of the lane passed by the target vehicle at 10:37:05 can be determined based on the distance between the target vehicle and the lane line included in the driving data obtained at 10:37:04.
[0090] If it is determined that the lane width does not change and the vehicle does not deviate laterally significantly between 10:37:04 and 10:37:05, the distance between the target vehicle and the lane line included in the driving data obtained at 10:37:04 is the distance between the target vehicle and the lane line corresponding to the time of 10:37:05, and the lane line trajectory and the lane width of the lane passed by the target vehicle at 10:37:05 are determined based on this.
[0091] If it is determined that the lane width and the lateral deviation of the vehicle change according to the changes in the time period from 10:37:04 to 10:37:03, the change value of the lane width and the change value of the lateral deviation of the vehicle in the time period from 10:37:04 to 10:37:05 are determined based on the change value of the lane width and the change value of the lateral deviation of the vehicle in the time period from 10:37:04 to 10:37:03. The lane line trajectory and the lane width of the lane passed by the target vehicle at 10:37:05 are determined based on the change value of the lane width and the change value of the lateral deviation of the vehicle in the time period from 10:37:04 to 10:37:05, and the distance between the target vehicle and the lane line included in the driving data obtained at 10:37:04.
[0092] In the above manner, the lane line trajectory is automatically fitted to form the lane line trajectory when the lane line disappears, ensuring the accuracy of the lane line trajectory and improving the restoration degree of the reconstructed scene.
[0093] Further, the scenario reconstruction method disclosed in the embodiment determines the lane information passed by the target vehicle during the driving process of the target vehicle by using the distance between the target vehicle and the lane line included in the driving data of the target vehicle and the vehicle driving trajectory, and can further include the following steps:
[0094] If it is determined that the target vehicle switches lanes at the third time based on the distance between the target vehicle and the lane line, the lateral distance driven by the target vehicle when switching lanes is determined based on the distance between the target vehicle and the lane line; and the lane line trajectory and the lane width of the lane passed by the target vehicle at the third time are determined based on the lateral distance and the vehicle driving trajectory.
[0095] The vehicle may switch lanes during driving, so when determining the lane line trajectory in the lane information, it is further necessary to determine whether the target vehicle switches lanes.
[0096] The distance between the target vehicle and the lane line can be used to determine whether the target vehicle switches lanes. If the distance between the target vehicle A and the lane line m1 changes from 0.5 meters to 4 meters, it can be determined that the target vehicle A switches lanes, and switches to the lane away from the lane line m1. If the distance between the target vehicle A and the lane line m1 changes from 0.5 meters to 1 meter, it can be determined that the target vehicle A does not switch lanes. Therefore, whether the target vehicle switches lanes can be determined based on the change amount of the distance between the target vehicle and the lane line and the size of a certain threshold.
[0097] If it is determined that the distance between the target vehicle and the lane line at the third time relative to the change amount of the distance between the target vehicle and the lane line at the previous time of the third time is greater than a certain threshold, it can be determined that the target vehicle switches lanes. At this time, the lateral distance driven by the target vehicle when switching lanes is determined based on the change amount, such as the distance between the target vehicle A and the lane line m1 changing from 0.5 meters to 4 meters, which can be determined as the lateral distance driven by the target vehicle when switching lanes is 3.5 meters.
[0098] After determining the lateral distance driven by the target vehicle when switching lanes, the lane line trajectory formed by the lane line before the third time is translated by the lateral distance to obtain the lane line trajectory of the target vehicle at the third time and the time before the third time, that is, the lane line trajectory after switching lanes.
[0099] In the above manner, the lane line trajectory is automatically fitted when the target vehicle switches lanes to form the lane line trajectory, which ensures the accuracy of the lane line trajectory and improves the restoration degree of the reconstructed scene.
[0100] The embodiment discloses a scenario reconstruction method, and a flowchart thereof is shown in Figure 5 The method comprises the following steps:
[0101] Step S51, obtaining driving data of the target vehicle collected in the driving process of the target vehicle and environment information in which the target vehicle is located in the driving process of the target vehicle;
[0102] Step S52, determining a vehicle driving trajectory of the target vehicle based on the driving data of the target vehicle;
[0103] Step S53, segmenting a lane through which the target vehicle passes in the driving process of the target vehicle based on the distance between the target vehicle and the lane line included in the driving data of the target vehicle, to obtain the distance between the target vehicle and the lane line and the vehicle driving trajectory corresponding to each segment of the lane;
[0104] Step S54, determining lane information of each segment of the lane through which the target vehicle passes in the driving process of the target vehicle based on the distance between the target vehicle and the lane line and the vehicle driving trajectory corresponding to each segment of the lane;
[0105] Step S55, generating a static map file based on the lane information;
[0106] Step S56, generating a dynamic scene file based on the vehicle driving trajectory and the environment information, so as to obtain a reconstructed scene composed of the vehicle driving trajectory, the static map file and the dynamic scene file.
[0107] The lane information can include a lane line trajectory and a lane width of the lane through which the target vehicle passes.
[0108] When fitting the lane line trajectory, in order to ensure that the fitted lane line trajectory can be smoothly transitioned and at the same time reduce the calculation complexity, a segmented fitting manner can be used.
[0109] The lane through which the target vehicle passes in the driving process of the target vehicle can be segmented based on the distance between the target vehicle and the lane line included in the driving data of the target vehicle, to obtain a plurality of segments of the lane. Specifically, the lane can be first segmented based on the distance between the target vehicle and two lane lines of the current lane, to obtain a plurality of segments of the lane, and based on the change of the distance between the target vehicle and the two lane lines of the current lane, it can be determined whether the width of the current lane through which the target vehicle passes changes, that is, the lane is segmented based on the change of the lane width. In the plurality of segments of the lane, the lane width corresponding to each segment of the lane is different, or the change of the lane width between each adjacent two segments of the lane exceeds a target threshold.
[0110] For example, in the target vehicle road test process, the distance between the target vehicle and the two lane lines of the current lane does not change significantly from the starting point to the first position in the distance traveled by the target vehicle, and the section from the starting point to the first position is determined as the first lane section; the distance between the target vehicle and the two lane lines of the current lane starts to change from the first position, and the distance between the target vehicle and the two lane lines of the current lane does not change significantly from the second position after the first position to the third position, so the section from the first position to the second position is determined as the second lane section, and the section from the second position to the third position is determined as the third lane section, and so on, until the end of the road test, at which time, a plurality of lane sections can be obtained.
[0111] Wherein, whether the distance between the target vehicle and the two lane lines of the current lane changes significantly can be determined based on the change rate or based on the change difference.
[0112] When calculating the lane width, the lane width can be calculated based on different lane sections.
[0113] For the section where the distance between the target vehicle and the two lane lines of the current lane does not change significantly, the lane width can be calculated by averaging, for example, for the first lane section, a plurality of position points in the section from the starting point to the first position can be determined, the lane widths at the position points are calculated first, and then the average value is obtained, so as to obtain the lane width in the section from the starting point to the first position, without the need to calculate the lane width at each position point passed by the target vehicle, thereby improving the calculation efficiency of the lane width.
[0114] For the section where the distance between the target vehicle and the two lane lines of the current lane changes significantly, the lane width can be calculated based on a cubic polynomial, for example, for the kth lane section, the distance between the target vehicle and the two lane lines of the current lane changes significantly, four reference points (which can include at least the starting point, the ending point and two points in the middle section of the kth lane section) in the section can be determined, and the lane widths at the four reference points are calculated, then the formula f(x) = ax 3 + bx 2 + cx + d is used to obtain the cubic equation by interpolation, so as to calculate the lane width of the kth lane section, i.e., the overall lane width of the kth lane section, without the need to calculate the lane width at each position point, thereby improving the calculation efficiency.
[0115] The scene reconstruction method disclosed in the embodiment comprises the following steps: obtaining driving data of a target vehicle collected in a driving process of the target vehicle and environment information of the target vehicle in the driving process; determining a vehicle driving track of the target vehicle based on the driving data of the target vehicle; segmenting a lane passed through by the target vehicle in the driving process based on a distance between the target vehicle and a lane line included in the driving data of the target vehicle, to obtain a distance between the target vehicle and the lane line and the vehicle driving track corresponding to each segment of the lane; determining lane information of each segment of the lane passed through by the target vehicle in the driving process based on the distance between the target vehicle and the lane line and the vehicle driving track corresponding to each segment of the lane; generating a static map file based on the lane information; and generating a dynamic scene file based on the vehicle driving track and the environment information, so as to obtain a reconstructed scene composed of the vehicle driving track, the static map file and the dynamic scene file. In this scheme, the lane line track can be fitted in a segmented manner, so as to ensure the accuracy of the lane line track fitting and the restoration effect of the reconstructed scene.
[0116] Further, in the scene reconstruction method disclosed in the embodiment, the static map file can be generated in the following manner:
[0117] After obtaining the lane information, the lane information is written in a first language to generate a static map file, wherein the first language is used to describe the static map.
[0118] The lane information can include a lane line track, a lane width, a lane number, a lane color or a lane line color included in the environment information collected by an image collection sensor, a lane type and the like. The lane number is numbered based on a positional relationship between the lane and the lane line track, and the lane number is recorded in correspondence with the lane width. In addition, the lane information can further include the lane color or the lane line color included in the environment information collected by the image collection sensor, the lane type and the like.
[0119] The various lane information is written in the first language, so as to output a static map file (such as an.xodr file). The first language can be an OpenDRIVE standard syntax.
[0120] The OpenDRIVE standard syntax is a language used to describe static content in an automatic driving simulation neighborhood, and is mainly used to create and exchange a road network model and is suitable for a simulation scene requiring accurate description of a road environment.
[0121] In addition, in the scene reconstruction method disclosed in the embodiment, the dynamic scene file can be generated in the following manner:
[0122] obtaining information of a traffic participant in the environment information, the information of the traffic participant including at least a distance of the traffic participant relative to the target vehicle, a speed of the traffic participant, and a pose of the traffic participant; storing the information of the traffic participant and a vehicle driving trajectory into a target file; and based on the target file, performing dynamic event writing in a second language to generate a dynamic scene file, wherein the second language is used to describe the dynamic scene.
[0123] The environment information can be obtained by an image acquisition sensor or a sensor on the target vehicle. The environment information includes at least a distance of a traffic participant relative to the target vehicle, a speed of the traffic participant, and a pose of the traffic participant.
[0124] After obtaining the information of the traffic participant relative to the target vehicle, the speed of the traffic participant, and the pose of the traffic participant, the data of the traffic participant in the vehicle coordinate system can be converted to obtain the motion information of the traffic participant in the absolute coordinate system.
[0125] In order to facilitate calling and management, the vehicle driving trajectory and the motion information of the traffic participant can be stored in the target file, which can be a json file.
[0126] Based on the vehicle driving trajectory and the motion information of the traffic participant in the target file, dynamic event writing is performed in a second language to generate a dynamic scene file (such as a.xosc file), wherein the second language can be OpenSCENARIO standard syntax.
[0127] The OpenSCENARIO standard syntax is a language used to describe dynamic content in the automatic driving simulation field, and is mainly used to define and execute dynamic simulation scenes.
[0128] The scene reconstruction method disclosed in the embodiment can generate a static map file and a dynamic scene file conforming to the ASAM-OpenX format (the ASAM-OpenX format is a series of standards specified by the German Automation and Measurement System Standard Association, aiming to promote the development of automatic driving simulation testing field, and the ASAM-OpenX format covers different aspects of simulation testing scenes, providing a unified specification and framework for the development, testing and verification of automatic driving technology), which can be applied to any simulation platform supporting the Open format (such as Modelbase, VTD, CarMaker, etc.), has strong usability, and can be directly called by simulation software supporting the OpenX format, so as to ensure that the reconstructed scene can be directly applied to the simulation software; in addition, the static map file under the accumulation of big data can be used as a basis for generalization of random testing scenes in the future, and has a wide application range.
[0129] The scene reconstruction system disclosed in the embodiment has a structure as shown in Figure 6 The scene reconstruction system disclosed in the embodiment has a structure as shown in
[0130] The obtaining unit 61, the determining unit 62, the first generating unit 63 and the second generating unit 64.
[0131] The obtaining unit 61 is configured to obtain driving data of a target vehicle collected during driving of the target vehicle and environment information of the target vehicle during driving of the target vehicle.
[0132] The determining unit 62 is configured to determine a vehicle driving trajectory of the target vehicle based on the driving data of the target vehicle.
[0133] The first generating unit 63 is configured to generate a static map file based on a distance between the target vehicle and a lane line included in the driving data of the target vehicle and the vehicle driving trajectory.
[0134] The second generating unit 64 is configured to generate a dynamic scene file based on the vehicle driving trajectory and the environment information, so as to obtain a reconstructed scene composed of the vehicle driving trajectory, the static map file and the dynamic scene file.
[0135] Further, the first generating unit is configured to:
[0136] determine lane information passed through by the target vehicle during driving of the target vehicle based on the distance between the target vehicle and the lane line included in the driving data of the target vehicle and the vehicle driving trajectory, the lane information at least including a lane line trajectory and a lane width of a lane passed through by the target vehicle; and generate the static map file based on the lane information.
[0137] Further, the first generating unit is configured to:
[0138] if it is determined that the distance between the target vehicle and the lane line at the first time is not included in the driving data of the target vehicle, determine a distance between the target vehicle and the lane line at a second time included in the driving data, wherein the second time is a time before the first time and a time interval between the first time and the second time is less than a specific time length; and determine the lane line trajectory and the lane width of the lane passed through by the target vehicle at the first time based on the distance between the target vehicle and the lane line at the second time included in the driving data.
[0139] Further, the first generating unit is configured to:
[0140] if it is determined that the target vehicle switches lanes at a third time based on the distance between the target vehicle and the lane line, determine a lateral distance traveled by the target vehicle when the target vehicle switches lanes based on the distance between the target vehicle and the lane line; and determine the lane line trajectory and the lane width of the lane passed through by the target vehicle at the third time based on the lateral distance and the vehicle driving trajectory.
[0141] Further, the first generating unit is configured to:
[0142] The distance between the target vehicle and the lane line included in the driving data of the target vehicle is used to segment the lane passed by the target vehicle during driving to obtain the distance between the target vehicle and the lane line and the vehicle driving track corresponding to each of the segmented lanes; and the lane information of each of the segmented lanes is determined based on the distance between the target vehicle and the lane line and the vehicle driving track corresponding to each of the segmented lanes.
[0143] Further, the first generating unit is configured to:
[0144] The lane information is written in the first language to generate a static map file, wherein the first language is used to describe the static map.
[0145] Further, the second generating unit is configured to:
[0146] The information of the traffic participant in the environment information is obtained, and the information of the traffic participant at least includes the distance of the traffic participant relative to the target vehicle, the speed and the posture of the traffic participant; the information of the traffic participant and the vehicle driving track are stored in a target file; and the dynamic event is written in the second language based on the target file to generate a dynamic scene file, wherein the second language is used to describe the dynamic scene.
[0147] The scene reconstruction system disclosed in the embodiment is implemented based on the scene reconstruction method disclosed in the above embodiment, and thus will not be described herein.
[0148] The scene reconstruction system disclosed in the embodiment obtains the driving data of the target vehicle collected during driving of the target vehicle and the environment information during driving of the target vehicle; determines the vehicle driving track of the target vehicle based on the driving data of the target vehicle; generates a static map file by using the distance between the target vehicle and the lane line included in the driving data of the target vehicle and the vehicle driving track; and generates a dynamic scene file based on the vehicle driving track and the environment information, so as to obtain a reconstructed scene composed of the vehicle driving track, the static map file and the dynamic scene file. In the scheme, when the scene reconstruction is needed, the driving data during driving of the target vehicle and the environment information are obtained, the vehicle driving track of the target vehicle is determined first, the static map file is generated based on the vehicle driving track and the driving data, the dynamic scene file is generated based on the vehicle driving track and the environment information, so as to obtain the reconstructed scene composed of the vehicle driving track, the static map file and the dynamic scene file, and the automatic reconstruction of the scene is realized, which is efficient, time-saving, and ensures the quality of the reconstructed scene, and avoids the problem that the quality of the manually reconstructed scene cannot be guaranteed.
[0149] The electronic device disclosed in the embodiment has a structure as shown in the structural schematic view Figure 7As shown, comprising:
[0150] The processor 71 and the memory 72.
[0151] The processor 71 is configured to obtain driving data of a target vehicle collected during driving of the target vehicle and environment information of the target vehicle during driving of the target vehicle, determine a vehicle driving track of the target vehicle based on the driving data of the target vehicle, generate a static map file by using a distance between the target vehicle and a lane line included in the driving data of the target vehicle and the vehicle driving track, and generate a dynamic scene file based on the vehicle driving track and the environment information, so as to obtain a reconstructed scene composed of the vehicle driving track, the static map file and the dynamic scene file.
[0152] The memory 72 is configured to store programs required by the processor to perform the above processing.
[0153] The electronic device disclosed in the embodiment is implemented based on the scene reconstruction method disclosed in the above embodiment, and thus will not be described herein.
[0154] The electronic device disclosed in the embodiment obtains driving data of a target vehicle collected during driving of the target vehicle and environment information of the target vehicle during driving of the target vehicle, determines a vehicle driving track of the target vehicle based on the driving data of the target vehicle, generates a static map file by using a distance between the target vehicle and a lane line included in the driving data of the target vehicle and the vehicle driving track, and generates a dynamic scene file based on the vehicle driving track and the environment information, so as to obtain a reconstructed scene composed of the vehicle driving track, the static map file and the dynamic scene file. In the scheme, when scene reconstruction is required, the driving data during driving of the target vehicle and the environment information are obtained, the vehicle driving track of the target vehicle is first determined, the static map file is generated based on the vehicle driving track and the driving data, and the dynamic scene file is generated based on the vehicle driving track and the environment information, so as to realize obtaining of the reconstructed scene composed of the vehicle driving track, the static map file and the dynamic scene file, realize automatic reconstruction of the scene, have high efficiency and short time consumption, and ensure the quality of the reconstructed scene, without manual reconstruction, and thus avoid the problem that the quality of the manually reconstructed scene cannot be ensured.
[0155] The embodiment of the present application further provides a readable storage medium having a computer program stored thereon, the computer program is loaded and executed by a processor, and each step of the above scene reconstruction method is realized, and the specific implementation process can be referred to the description of the corresponding part of the above embodiment, and the embodiment will not be described herein.
[0156] The application further provides a computer program product or computer program, which comprises computer instructions stored in a computer readable storage medium. A processor of an electronic device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the method provided in various optional implementations of the scene reconstruction method aspect or the scene reconstruction system aspect, and the specific implementation process can refer to the description of the corresponding embodiments.
[0157] In addition, it should be noted that the apparatus embodiments described above are merely illustrative, and the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment according to actual needs. In addition, the connection relationship between the modules in the apparatus embodiment provided by the application indicates that there is a communication connection between them, which can be implemented as one or more communication buses or signal lines.
[0158] Through the description of the above embodiments, those skilled in the art can clearly understand that the application can be realized by means of software and necessary general hardware, and of course, it can also be realized by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. Generally, functions completed by computer programs can be easily realized by corresponding hardware, and the specific hardware structure for realizing the same function can also be various, such as analog circuit, digital circuit or special circuit, etc. However, for the application, software program implementation is a better embodiment. Based on such understanding, the technical solutions of the application can be embodied in the form of software product, which is stored in a readable storage medium, such as a computer floppy disk, U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., including a plurality of instructions for making a computer device (which can be a personal computer, training device or network device, etc.) execute the method described in each embodiment of the application.
[0159] In the above embodiments, all or part can be realized by software, hardware, firmware or any combination thereof. When realized by software, it can be realized in the form of a computer program product in whole or in part.
[0160] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, training device or data center to another website, computer, training device or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be stored by the computer or a data storage device such as a training device, a data center, etc. integrated with one or more available media sets. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)), etc.
Claims
1. A scene reconstruction method, characterized in that: include: Obtaining driving data of the target vehicle collected during the driving process and environmental information of the target vehicle during the driving process; determining a vehicle driving trajectory of the target vehicle based on the driving data of the target vehicle; Generate a static map file using the distance between the target vehicle and the lane line and the vehicle's driving trajectory included in the target vehicle's driving data; A dynamic scene file is generated based on the vehicle driving trajectory and the environmental information, so as to obtain a reconstructed scene consisting of the vehicle driving trajectory, the static map file and the dynamic scene file.
2. The method according to claim 1, characterized in that The generating of a static map file by using the distance between the target vehicle and the lane line and the vehicle driving trajectory included in the driving data of the target vehicle includes: Determine lane information of the target vehicle during its travel using the distance between the target vehicle and the lane line and the vehicle's travel trajectory included in the target vehicle's travel data, wherein the lane information includes at least the lane line trajectory and lane width of the lane passed by the target vehicle; A static map file is generated based on the lane information.
3. The method according to claim 2, characterized in that The determining of lane information passed by the target vehicle during its travel using the distance between the target vehicle and the lane line and the vehicle travel trajectory included in the travel data of the target vehicle includes: If it is determined that the driving data of the target vehicle does not include the distance between the target vehicle and the lane line at the first moment, determine the distance between the target vehicle and the lane line at a second moment included in the driving data, wherein the second moment is a moment before the first moment and the time interval between the second moment and the first moment is less than a specific time length; The lane line trajectory and lane width of the lane passed by the target vehicle at the first moment are determined by using the distance between the target vehicle and the lane line at the second moment included in the driving data.
4. The method according to claim 2, characterized in that The determining of lane information passed by the target vehicle during its travel using the distance between the target vehicle and the lane line and the vehicle travel trajectory included in the travel data of the target vehicle includes: If it is determined based on the distance between the target vehicle and the lane line that the target vehicle switches lanes at the third moment, determining the lateral distance traveled by the target vehicle when switching lanes based on the distance between the target vehicle and the lane line; Based on the lateral distance and the vehicle driving trajectory, the lane line trajectory and lane width of the lane passed by the target vehicle at the third moment are determined.
5. The method according to claim 2, characterized in that The determining of lane information passed by the target vehicle during its travel using the distance between the target vehicle and the lane line and the vehicle travel trajectory included in the travel data of the target vehicle includes: Segmenting the lanes passed by the target vehicle during its travel based on the distance between the target vehicle and the lane line included in the travel data of the target vehicle, so as to obtain the distance between the target vehicle and the lane line and the vehicle travel trajectory corresponding to each lane in multiple lane segments; Based on the distance between the target vehicle and the lane line corresponding to each lane in the multiple lanes and the vehicle driving trajectory, lane information of each lane passed by the target vehicle during driving is determined.
6. The method according to claim 2, characterized in that The generating a static map file based on the lane information includes: The lane information is written in a first language to generate a static map file, wherein the first language is used to describe a static map.
7. The method according to claim 1, characterized in that The generating of a dynamic scene file based on the vehicle driving trajectory and the environmental information includes: Obtaining information of a traffic participant in the environmental information, wherein the information of the traffic participant includes at least: a distance and a speed of the traffic participant relative to the target vehicle, and a posture of the traffic participant; Storing the information of the traffic participants and the vehicle driving trajectory in a target file; Based on the target file, dynamic events are written in a second language to generate a dynamic scene file, wherein the second language is used to describe the dynamic scene.
8. A scene reconstruction system, characterized in that: include: An obtaining unit, configured to obtain driving data of the target vehicle collected during the driving process and information about the environment in which the target vehicle is located during the driving process; a determining unit, configured to determine a vehicle driving trajectory of the target vehicle based on the driving data of the target vehicle; A first generating unit is configured to generate a static map file using the distance between the target vehicle and the lane line and the vehicle driving trajectory included in the driving data of the target vehicle; The second generating unit is configured to generate a dynamic scene file based on the vehicle driving trajectory and the environmental information, so as to obtain a reconstructed scene consisting of the vehicle driving trajectory, the static map file and the dynamic scene file.
9. An electronic device, characterized in that: include: A processor, configured to obtain driving data of the target vehicle collected during the driving process and information about the environment in which the target vehicle is located during the driving process; Determining a vehicle driving trajectory of the target vehicle based on the driving data of the target vehicle; generating a static map file using the distance between the target vehicle and the lane line included in the driving data of the target vehicle and the vehicle driving trajectory; generating a dynamic scene file based on the vehicle driving trajectory and the environmental information, so as to obtain a reconstructed scene consisting of the vehicle driving trajectory, the static map file, and the dynamic scene file; The memory is used to store the program required by the processor to execute the above processing process.
10. A readable storage medium, characterized in that: for storing at least one set of instruction sets; The instruction set is used to be called and at least execute the scene reconstruction method according to any one of claims 1 to 7.