Vehicle visual truth value obtaining method and device, vehicle, medium and program

Abstract

The invention relates to the technical field of vehicles, in particular to a vehicle visual truth value obtaining method and device, a vehicle, a medium and a program.The method comprises the steps that image data of a target vehicle at the target moment and front-back multi-frame image data corresponding to the same timestamp of a sampling vehicle and the target vehicle are obtained; identifying the image data of the target moment and the annotation data of the same three-dimensional target in the multi-frame image data; and converting the labeling data of the three-dimensional target of the sampling vehicle to the pose of the corresponding three-dimensional target in the target vehicle coordinate system, and generating a visual truth value in the target vehicle coordinate system according to the image data at the target moment and the converted pose of the three-dimensional target. Therefore, the problems that the cost is high due to the fact that different vehicle types train different deep learning models to recognize image data, manpower and material resources are wasted due to the fact that repeated collection is needed, and the applicability is low due to the fact that the same deep learning model cannot be suitable for various vehicles in the prior art are solved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a method, device, vehicle, medium and program for obtaining a vehicle visual truth value. Background Art

[0002] At present, the generation of true value data in the field of autonomous driving often relies on the collection equipment installed on the collection vehicle, such as lidar, camera, millimeter wave radar, etc. Data is collected through these sensors, and then manually labeled, and finally used for model training. However, the deep learning model trained by the data collected on the collection vehicle can often only be applied to the same model. If other models are used, the model will often perform very poorly. In essence, this is because the data sets used by the model during training and testing are not from the same sample distribution space.

[0003] In the related technology, different deep learning models are trained for different types of cars, and a set of data acquisition equipment needs to be installed on each type of car, especially lidar, which is very expensive; data needs to be collected and labeled repeatedly, which wastes time and manpower costs; the cost increases exponentially with each additional type of car; therefore, different deep learning models are trained to recognize image data for different types of cars, resulting in high costs and the need for repeated collection, which wastes manpower and material resources; the same deep learning model cannot be applied to multiple vehicles, resulting in low applicability. Summary of the invention

[0004] The present application provides a method, device, vehicle, storage medium and program product for obtaining the true value of vehicle vision, so as to solve the problems in the related technology of training different deep learning models for different vehicle models to recognize image data, resulting in high cost, requiring multiple repeated collections and wasting manpower and material resources, and the same deep learning model cannot be applied to multiple vehicles, resulting in low applicability.

[0005] The first aspect of the present application provides a method for obtaining a vehicle visual truth value, comprising the following steps: obtaining image data of a target vehicle at a target time and multiple frames of image data before and after a sampling vehicle corresponding to the same timestamp as the target vehicle; identifying the labeled data of the same three-dimensional target in the image data at the target time and the multiple frames of image data; converting the labeled data of the three-dimensional target of the sampling vehicle to the corresponding three-dimensional target posture in the target vehicle coordinate system, and generating a visual truth value in the target vehicle coordinate system based on the image data at the target time and the converted three-dimensional target posture.

[0006] Optionally, converting the annotated data of the three-dimensional target of the sampling vehicle to the corresponding three-dimensional target posture in the target vehicle coordinate system includes: identifying the external parameters and positioning information of the sensor and camera of the sampling vehicle; converting the annotated data of the three-dimensional target of the sampling vehicle from the sampling vehicle coordinate system to the annotated data of the three-dimensional target in the world coordinate system according to the external parameters and the positioning information, and determining the actual posture of the three-dimensional target in the world coordinate system according to the annotated data; and converting the actual posture of the three-dimensional target in the world coordinate system into the corresponding posture of the three-dimensional target in the target vehicle coordinate system.

[0007] Optionally, determining the actual posture of the three-dimensional target in the world coordinate system based on the annotated data also includes: using quaternion spherical interpolation to calculate the rotation angle of the three-dimensional target posture of multiple frames before and after in the annotated data; using linear interpolation to calculate the translation vector of the three-dimensional target posture of multiple frames before and after in the annotated data; and determining the actual posture of the three-dimensional target posture in the world coordinate system corresponding to the same timestamp of the sampling vehicle and the target vehicle based on the rotation angle and translation vector.

[0008] Optionally, converting the actual posture of the three-dimensional target in the world coordinate system into the posture of the corresponding three-dimensional target in the target vehicle coordinate system includes: identifying the relative position of the sampling vehicle and the target vehicle and the sensor and camera extrinsic parameters of the target vehicle; based on the relative position and the sensor and camera extrinsic parameters of the target vehicle, converting the actual posture of the three-dimensional target in the world coordinate system into the posture of the corresponding three-dimensional target in the target vehicle coordinate system.

[0009] Optionally, before identifying the labeling data of the same three-dimensional target in the image data at the target moment and the multi-frame image data, it includes: preprocessing all three-dimensional targets in the image data at the target moment and the multi-frame image data; inputting the preprocessed image data into a labeling model, and the labeling model outputs the labeling data of the corresponding three-dimensional target, and the labeling data includes the posture, size, yaw angle and target name of the three-dimensional target.

[0010] Optionally, the method further includes: controlling the distance between the target vehicle and the sampling vehicle to be within a preset range.

[0011] The second aspect of the present application provides a vehicle visual truth acquisition device, including: an acquisition module, used to acquire image data of a target vehicle at a target time and multiple frames of image data before and after the sampling vehicle and the target vehicle corresponding to the same timestamp; an identification module, used to identify the labeled data of the same three-dimensional target in the image data at the target time and the multiple frames of image data; a conversion module, used to convert the labeled data of the three-dimensional target of the sampling vehicle to the corresponding three-dimensional target posture in the target vehicle coordinate system, and generate the visual truth value in the target vehicle coordinate system according to the image data at the target time and the converted three-dimensional target posture.

[0012] A third aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to execute the method for acquiring the vehicle visual truth value as described in the above embodiment.

[0013] The fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to perform the vehicle visual true value acquisition method as described in the above embodiment.

[0014] The fifth aspect of the present application provides a computer program product, including a computer program or instructions, characterized in that when the computer program or instructions are executed, the vehicle visual true value acquisition method as described in the above embodiment is implemented.

[0015] Therefore, this application has at least the following beneficial effects:

[0016] The embodiments of the present application can obtain the image data of the target vehicle at the target time and the previous and subsequent multiple frames of image data corresponding to the same timestamp of the sampling vehicle and the target vehicle; identify the labeled data of the same three-dimensional target in the image data at the target time and the multiple frames of image data; convert the labeled data of the three-dimensional target of the sampling vehicle to the position and posture of the corresponding three-dimensional target in the target vehicle coordinate system, and generate the visual true value in the target vehicle coordinate system based on the image data at the target time and the converted three-dimensional target posture, which can save a lot of time, manpower, material resources and overall cost, and has high collection efficiency and more accurate data.

[0017] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0019] Figure 1A flowchart of a method for obtaining a vehicle visual truth value provided according to an embodiment of the present application;

[0020] Figure 2 A schematic diagram of a method for obtaining a vehicle visual truth value according to an embodiment of the present application;

[0021] Figure 3 This is a block diagram of an example of a vehicle visual truth value acquisition device provided according to an embodiment of the present application;

[0022] Figure 4 It is a schematic diagram of the structure of a vehicle provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0024] The following describes the vehicle visual truth value acquisition method, device, vehicle, storage medium and program of the embodiment of the present application with reference to the accompanying drawings. In view of the problem that different deep learning models are trained to recognize image data for different models in the related technology mentioned in the background technology center, resulting in high cost, multiple repeated acquisitions are required to waste manpower and material resources, and the same deep learning model cannot be applied to multiple vehicles, resulting in low applicability, the present application provides a vehicle visual truth value acquisition method, in which the image data of the target vehicle at the target time and the image data of the sampling vehicle before and after the same timestamp of the target vehicle are obtained; the image data at the target time and the annotated data of the same three-dimensional target in the multiple frames of image data are identified; the annotated data of the three-dimensional target of the sampling vehicle is converted to the corresponding three-dimensional target position in the target vehicle coordinate system, and the visual truth value in the target vehicle coordinate system is generated according to the image data at the target time and the converted three-dimensional target position, which can save a lot of time, manpower, material resources and overall cost, and the acquisition efficiency is high and the data is more accurate. Thus, the problem that different deep learning models are trained to recognize image data for different models in the related technology, resulting in high cost, multiple repeated acquisitions are required to waste manpower and material resources, and the same deep learning model cannot be applied to multiple vehicles, resulting in low applicability, is solved.

[0025] Specifically, Figure 1 A flowchart of a method for obtaining vehicle visual truth values ​​provided in an embodiment of the present application.

[0026] like Figure 1 As shown, the vehicle visual true value acquisition method includes the following steps:

[0027] In step S101, image data of a target vehicle at a target time and multiple frames of image data before and after the sampling vehicle corresponding to the same timestamp as the target vehicle are acquired.

[0028] It can be understood that the embodiments of the present application can obtain the image data of the target vehicle at the target time and the multiple frames of image data before and after the sampling vehicle corresponding to the same timestamp as the target vehicle, so as to facilitate the subsequent identification of the image data at the target time and the annotation data of the same three-dimensional target in the multiple frames of image data.

[0029] It should be noted that the sampling vehicle equipped with a complete set of data acquisition equipment and the target vehicle equipped with a camera collect data at the same time.

[0030] In step S102, the image data at the target moment and the annotation data of the same three-dimensional target in the multi-frame image data are identified.

[0031] It can be understood that the embodiments of the present application can identify the image data at the target moment and the annotation data of the same three-dimensional target in multiple frames of image data, so as to facilitate the subsequent generation of the visual true value in the target vehicle coordinate system for the data collected at the same timestamp, thereby improving accuracy.

[0032] In an embodiment of the present application, before identifying the image data at the target moment and the annotation data of the same three-dimensional target in the multi-frame image data, it includes: preprocessing the image data at the target moment and all three-dimensional targets in the multi-frame image data; inputting the preprocessed image data into the annotation model, and the annotation model outputs the annotation data of the corresponding three-dimensional target, and the annotation data includes the posture, size, yaw angle and target name of the three-dimensional target.

[0033] Among them, the preprocessing includes extracting the image data corresponding to the closest features from the image data collected by the sampling vehicle and the image data collected by the target vehicle through appearance features, position, speed and other information, and dedistorting, reducing noise and enhancing edges, without specific limitations.

[0034] It can be understood that the embodiments of the present application can preprocess the image data at the target moment and all three-dimensional targets in the multi-frame image data; input the preprocessed image data into the annotation model, and the annotation model outputs the annotation data of the corresponding three-dimensional target, thereby making the annotation data more accurate, so as to facilitate the subsequent generation of the visual true value in the target vehicle coordinate system.

[0035] In step S103, the annotated data of the three-dimensional target of the sampling vehicle is converted to the corresponding three-dimensional target posture in the target vehicle coordinate system, and the visual true value in the target vehicle coordinate system is generated according to the image data at the target moment and the converted three-dimensional target posture.

[0036] It can be understood that the embodiment of the present application converts the annotated data of the three-dimensional target of the sampling vehicle into the position and posture of the corresponding three-dimensional target in the target vehicle coordinate system, and generates the visual true value in the target vehicle coordinate system based on the image data at the target moment and the position and posture of the converted three-dimensional target, which can save a lot of time, manpower, material resources and overall cost, and has high collection efficiency and more accurate data.

[0037] In an embodiment of the present application, the annotated data of the three-dimensional target of the sampling vehicle is converted to the corresponding three-dimensional target posture in the target vehicle coordinate system, including: identifying the external parameters and positioning information of the sensor and camera of the sampling vehicle; converting the annotated data of the three-dimensional target of the sampling vehicle from the sampling vehicle coordinate system to the annotated data of the three-dimensional target in the world coordinate system according to the external parameters and positioning information, and determining the actual posture of the three-dimensional target in the world coordinate system according to the annotated data; converting the actual posture of the three-dimensional target in the world coordinate system into the corresponding posture of the three-dimensional target in the target vehicle coordinate system.

[0038] It can be understood that the embodiments of the present application can identify the external parameters and positioning information of the sensors and cameras of the sampling vehicle; convert the annotation data of the three-dimensional target of the sampling vehicle from the sampling vehicle coordinate system into the annotation data of the three-dimensional target in the world coordinate system according to the external parameters and positioning information, and determine the actual position and posture of the three-dimensional target in the world coordinate system according to the annotation data; convert the actual position and posture of the three-dimensional target in the world coordinate system into the position and posture of the corresponding three-dimensional target in the target vehicle coordinate system, which can save a lot of time, manpower, material resources and overall cost, and has high collection efficiency and more accurate data.

[0039] In an embodiment of the present application, determining the actual posture of a three-dimensional target in a world coordinate system based on the annotated data also includes: calculating the rotation angle of the three-dimensional target posture of multiple frames before and after in the annotated data using quaternion spherical interpolation; calculating the translation vector of the three-dimensional target posture of multiple frames before and after in the annotated data using linear interpolation; and determining the actual posture of the three-dimensional target posture in the world coordinate system corresponding to the same timestamp of the sampling vehicle and the target vehicle based on the rotation angle and the translation vector.

[0040] It can be understood that the embodiments of the present application can use quaternion spherical interpolation to calculate the rotation angle of the three-dimensional target posture of multiple frames before and after in the annotated data; use linear interpolation to calculate the translation vector of the three-dimensional target posture of multiple frames before and after in the annotated data; determine the actual posture of the three-dimensional target posture in the world coordinate system corresponding to the same timestamp of the sampling vehicle and the target vehicle based on the rotation angle and the translation vector, so as to improve the accuracy of the three-dimensional target posture data.

[0041] Specifically, using quaternion spherical interpolation, assume that there are two rotation states R1 and R2, which correspond to two different time points, and calculate the rotation state Rt at any given time t between these two time points; wherein, the new quaternion qt is calculated using the spherical linear interpolation formula:

[0042]

[0043] Where t represents the interpolation ratio from q1 to q2, 0≤t≤1.

[0044] Calculate the new translation vector Pt using the linear interpolation formula:

[0045] Pt=P1+t·ΔP,

[0046] Where t represents the interpolation ratio from P1 to P2, 0≤t≤1.

[0047] In an embodiment of the present application, the actual posture of the three-dimensional target in the world coordinate system is converted into the posture of the corresponding three-dimensional target in the target vehicle coordinate system, including: identifying the relative position of the sampling vehicle and the target vehicle and the sensor and camera extrinsic parameters of the target vehicle; according to the relative position and the sensor and camera extrinsic parameters of the target vehicle, the actual posture of the three-dimensional target in the world coordinate system is converted into the posture of the corresponding three-dimensional target in the target vehicle coordinate system.

[0048] It can be understood that the embodiments of the present application can identify the relative positions of the sampling vehicle and the target vehicle and the sensor and camera extrinsic parameters of the target vehicle; based on the relative positions and the sensor and camera extrinsic parameters of the target vehicle, the actual position of the three-dimensional target in the world coordinate system is replaced with the corresponding three-dimensional target position in the target vehicle coordinate system, which can save a lot of time, manpower, material resources and overall costs, and has high collection efficiency and more accurate data.

[0049] In an embodiment of the present application, it also includes: controlling the distance between the target vehicle and the sampling vehicle to be within a preset range.

[0050] Among them, the preset range can be 20m or 10m, which can be set according to actual needs without specific limitation.

[0051] It can be understood that the embodiment of the present application controls the distance between the target vehicle and the sampling vehicle within a preset range, improves the quality and real-time performance of data collection, ensures the accuracy of data collection, and reduces the complexity of subsequent calculations.

[0052] According to the vehicle visual truth acquisition method proposed in the embodiment of the present application, the image data of the target vehicle at the target time and the previous and subsequent multiple frames of image data corresponding to the same timestamp of the sampling vehicle and the target vehicle are acquired; the annotation data of the same three-dimensional target in the image data at the target time and the multiple frames of image data are identified; the annotation data of the three-dimensional target of the sampling vehicle is converted to the position and posture of the corresponding three-dimensional target in the target vehicle coordinate system, and the visual truth value in the target vehicle coordinate system is generated according to the image data at the target time and the position and posture of the converted three-dimensional target, which can save a lot of time, manpower, material resources and overall cost, and has high collection efficiency and more accurate data.

[0053] The following will be combined Figure 2 The vehicle visual true value acquisition method of this application is described in detail as follows:

[0054] First, the sampling vehicle and the target vehicle collect data at the same time. The target vehicle is in front, and the sampling vehicle needs to follow the target vehicle closely, keeping the distance between the sampling vehicle and the target vehicle within 20m. Do not be too far away, and do not insert other vehicles in between. The data collected by the sampling vehicle includes point cloud, image, and positioning data, and the data collected by the target vehicle generally only has image data and positioning data.

[0055] Secondly, after the data collection is completed, the data collected by the sampling vehicle must be labeled. The labeling is generally performed on the point cloud, which can be done manually or in advance. After the labeling is completed, each 3D target has its corresponding position, size, yaw angle and target ID.

[0056] Finally, for the image data collected by the target vehicle, it is necessary to find the two frames of data before and after the sampling vehicle and the corresponding timestamp, and unify the 3D targets annotated in these two frames into the world coordinate system through external parameters and positioning information, and obtain the pose of the same target in the two frames before and after in the world coordinate system. For rotation, quaternion spherical interpolation is used, and for translation, linear interpolation is used to obtain the pose of the target at the timestamp collected by the target vehicle. Then, the target can be converted to the target vehicle coordinate system through the positioning information and external parameters of the target vehicle to generate the visual true value corresponding to the target vehicle.

[0057] In summary, this application only requires the installation of a set of data acquisition equipment on the collection vehicle, and other vehicle models can use this method to generate the true value of the corresponding vehicle model, which can save a lot of time, manpower and economic costs.

[0058] Next, the vehicle visual truth value acquisition device proposed in accordance with the embodiment of the present application is described with reference to the accompanying drawings.

[0059] Figure 3 It is a block diagram of a vehicle visual truth acquisition device according to an embodiment of the present application.

[0060] like Figure 3As shown, the vehicle visual true value acquisition device 10 includes: an acquisition module 100, a recognition module 200 and a conversion module 300.

[0061] Among them, the acquisition module 100 is used to obtain the image data of the target vehicle at the target time and the previous and subsequent multiple frames of image data corresponding to the same timestamp of the sampling vehicle and the target vehicle; the recognition module 200 is used to identify the image data at the target time and the annotation data of the same three-dimensional target in the multiple frames of image data; the conversion module 300 is used to convert the annotation data of the three-dimensional target of the sampling vehicle to the corresponding three-dimensional target posture in the target vehicle coordinate system, and generate the visual true value in the target vehicle coordinate system according to the image data at the target time and the converted three-dimensional target posture.

[0062] It should be noted that the above explanation of the embodiment of the vehicle visual truth value acquisition method is also applicable to the vehicle visual truth value acquisition device of this embodiment, and will not be repeated here.

[0063] According to the vehicle visual truth value acquisition device proposed in the embodiment of the present application,

[0064] Acquire the image data of the target vehicle at the target time and the previous and subsequent multiple frames of image data corresponding to the same timestamp as the target vehicle; identify the labeled data of the same three-dimensional target in the image data at the target time and the multiple frames of image data; convert the labeled data of the three-dimensional target of the sampling vehicle to the position and posture of the corresponding three-dimensional target in the target vehicle coordinate system, and generate the visual true value in the target vehicle coordinate system according to the image data at the target time and the converted three-dimensional target posture, which can save a lot of time, manpower, material resources and overall cost, and has high collection efficiency and more accurate data.

[0065] Figure 4 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle may include:

[0066] Memory 401 , processor 402 , and a computer program stored in the memory 401 and executable on the processor 402 .

[0067] When the processor 402 executes the program, the vehicle visual true value acquisition method provided in the above embodiment is implemented.

[0068] Furthermore, the vehicle also includes:

[0069] The communication interface 403 is used for communication between the memory 401 and the processor 402 .

[0070] The memory 401 is used to store computer programs that can be executed on the processor 402 .

[0071] The memory 401 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0072] If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0073] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can communicate with each other through an internal interface.

[0074] The processor 402 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0075] An embodiment of the present application also provides a computer-readable storage medium on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the above-mentioned vehicle visual true value acquisition method is implemented.

[0076] An embodiment of the present application also provides a computer program product, including a computer program or instructions, characterized in that when the computer program or instructions are executed, the above-mentioned vehicle visual truth acquisition method is implemented.

[0077] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0078] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0079] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0080] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of multiple of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0081] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

Claims

1. A method for obtaining a vehicle visual truth value, characterized in that: The following steps are involved: Obtain image data of the target vehicle at the target time and multiple frames of image data before and after the sampling vehicle corresponding to the same timestamp as the target vehicle; Identify the image data at the target moment and the annotation data of the same three-dimensional target in the multiple frames of image data; The labeled data of the three-dimensional target of the sampling vehicle is converted to the corresponding three-dimensional target posture in the target vehicle coordinate system, and the visual true value in the target vehicle coordinate system is generated according to the image data at the target moment and the converted three-dimensional target posture.

2. The method for obtaining the vehicle visual truth value according to claim 1, characterized in that: The step of converting the labeled data of the three-dimensional target of the sampling vehicle into the corresponding position and posture of the three-dimensional target in the target vehicle coordinate system includes: Identify sensor and camera external parameters and positioning information of the sampled vehicle; Converting the labeled data of the three-dimensional target of the sampling vehicle from the sampling vehicle coordinate system to the labeled data of the three-dimensional target in the world coordinate system according to the external reference and the positioning information, and determining the actual position and posture of the three-dimensional target in the world coordinate system according to the labeled data; The actual position and posture of the three-dimensional target in the world coordinate system is converted into the corresponding position and posture of the three-dimensional target in the target vehicle coordinate system.

3. The method for obtaining the vehicle visual truth value according to claim 2, characterized in that: Determining the actual position and posture of the three-dimensional target in the world coordinate system according to the labeled data also includes: The rotation angle of the three-dimensional target pose of the previous and next multiple frames in the labeled data is calculated using quaternion spherical interpolation; The translation vector of the 3D target pose of the previous and next multiple frames in the annotated data is calculated using linear interpolation; The actual position and posture of the three-dimensional target position and posture in the world coordinate system corresponding to the same timestamp of the sampling vehicle and the target vehicle are determined according to the rotation angle and the translation vector.

4. The method for obtaining the vehicle visual truth value according to claim 3, characterized in that: The step of converting the actual position and posture of the three-dimensional target in the world coordinate system into the corresponding position and posture of the three-dimensional target in the target vehicle coordinate system includes: Identifying the relative positions of the sampling vehicle and the target vehicle and the sensor and camera extrinsic parameters of the target vehicle; According to the relative position and the sensor and camera external parameters of the target vehicle, the actual position and posture of the three-dimensional target in the world coordinate system is replaced by the corresponding three-dimensional target position and posture in the target vehicle coordinate system.

5. The vehicle visual truth value acquisition method according to claim 1, characterized in that: Before the image data at the target moment and the labeling data of the same three-dimensional target in the multi-frame image data are identified, the method includes: Preprocessing the image data at the target moment and all three-dimensional objects in the multi-frame image data; The preprocessed image data is input into a labeling model, and the labeling model outputs labeling data of the corresponding three-dimensional target, wherein the labeling data includes the position, size, yaw angle and target name of the three-dimensional target.

6. The vehicle visual truth value acquisition method according to claim 1, characterized in that: Also includes: The distance between the target vehicle and the sampling vehicle is controlled to be within a preset range.

7. A vehicle visual truth value acquisition device, characterized in that: include: An acquisition module, used to acquire the image data of the target vehicle at the target time and the previous and next multiple frames of image data corresponding to the same timestamp of the sampling vehicle and the target vehicle; A recognition module, used to recognize the image data at the target moment and the annotation data of the same three-dimensional target in the multi-frame image data; The conversion module is used to convert the annotated data of the three-dimensional target of the sampling vehicle into the corresponding three-dimensional target posture in the target vehicle coordinate system, and generate the visual true value in the target vehicle coordinate system according to the image data at the target moment and the converted three-dimensional target posture.

8. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for acquiring the vehicle visual true value as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, it is used to implement the vehicle visual true value acquisition method as described in any one of claims 1-6.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed, the vehicle visual true value acquisition method as described in any one of claims 1-6 is implemented.

Images