Light blanket data processing method and device, vehicle and storage medium

Abstract

The invention provides a light blanket data processing method and device, a vehicle and a storage medium. The method comprises the following steps: acquiring initial track point data and track point adjustment parameter information; performing optimization processing on the initial track point data according to the track point adjustment parameter information to obtain target track point data; performing rendering processing based on the target track point data to generate a vehicle navigation guide light blanket; and displaying the vehicle navigation guide light blanket in an augmented reality head-up display navigation interface of the vehicle. According to the invention, the technical problem of low smoothness of the light blanket in a light blanket data processing method provided in the related art is solved.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving technology, and more particularly to a light carpet data processing method, device, vehicle, and storage medium. Background Art

[0002] In the Augmented Reality Head-Up Display (AR-HUD), the navigation light carpet, as an intuitive and visually deep guidance tool, can effectively assist the driver in understanding the vehicle's direction of travel and road environment, thereby improving the driving experience and safety. However, since the light carpet centerline data comes from multiple sources and the unprocessed data often lacks smoothness, direct display may cause a visual sense of unrefinedness, affecting the user experience. The light carpet data processing methods in related technologies make it difficult to maintain the precise correspondence between the light carpet and the original path, and while pursuing a smooth effect, they sacrifice the dynamic stability of the light carpet, which can easily lead to unclear navigation instructions and even mislead the driver. Therefore, how to achieve efficient smoothing of light carpet data while ensuring that the light carpet is close to the real path has become a key technical problem that needs to be solved urgently.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] The embodiments of the present disclosure provide a light carpet data processing method, device, vehicle, and storage medium to at least solve the technical problem of low light carpet smoothness existing in the light carpet data processing method provided in the related art.

[0005] According to one aspect of an embodiment of the present disclosure, a light carpet data processing method is provided, including: obtaining initial trajectory point data and trajectory point adjustment parameter information, wherein the initial trajectory point data is used to represent light carpet centerline data generated by fusing multi-source vehicle data, and the trajectory point adjustment parameter information includes: smoothing item parameters and constraint item parameters, the smoothing item parameters are used to control the smoothness of the vehicle navigation guidance light carpet, and the constraint item parameters are used to control the degree of fit between the vehicle navigation guidance light carpet and the initial trajectory point data; optimizing the initial trajectory point data according to the trajectory point adjustment parameter information to obtain target trajectory point data, wherein the target trajectory point data is used to construct the vehicle navigation guidance light carpet; rendering processing is performed based on the target trajectory point data to generate a vehicle navigation guidance light carpet, wherein the vehicle navigation guidance light carpet is used to provide navigation driving guidance for the vehicle; and displaying the vehicle navigation guidance light carpet in an augmented reality head-up display navigation interface of the vehicle.

[0006] Optionally, optimizing the initial trajectory point data according to the trajectory point adjustment parameter information to obtain the target trajectory point data includes: uniformly step sampling the initial trajectory point data to obtain a trajectory point sampling result, wherein the spacing between multiple trajectory points in the trajectory point sampling result is the same; and optimizing the trajectory point sampling result using the trajectory point adjustment parameter information to obtain the target trajectory point data.

[0007] Optionally, the initial trajectory point data is sampled with a uniform step size to obtain a trajectory point sampling result, including: in response to the number of trajectory points corresponding to the initial trajectory point data being greater than a preset number threshold, the initial trajectory point data is array-converted to obtain a trajectory point array; and interpolation processing is performed using the preset step size and the trajectory point array to obtain a trajectory point sampling result.

[0008] Optionally, the trajectory point sampling results are optimized using the trajectory point adjustment parameter information to obtain the target trajectory point data, including: performing differential calculation based on the trajectory point sampling results to obtain a target differential matrix, wherein the target differential matrix is ​​used to represent the curvature change corresponding to the trajectory point sampling results; determining the objective function matrix and the linear term vector according to the target differential matrix and the trajectory point adjustment parameter information, wherein the objective function matrix is ​​used to smoothly adjust the trajectory point sampling results, and the linear term vector is used to perform distance constraints on the trajectory point sampling results; and performing optimization solution using the objective function matrix and the linear term vector to obtain the target trajectory point data.

[0009] Optionally, determining the objective function matrix based on the target difference matrix and the trajectory point adjustment parameter information includes: using the target difference matrix and the smoothing term parameters to determine the smoothing optimization variables, and using the constraint term parameters to determine the constrained optimization variables; merging the smoothing optimization variables and the constrained optimization variables of the trajectory point sampling results to obtain the objective function matrix.

[0010] Optionally, rendering processing is performed based on the target trajectory point data to generate a vehicle navigation guide light carpet, including: obtaining light carpet style data, wherein the light carpet style data includes at least one of the following: color style, shape style, texture style; rendering the target trajectory point data based on the light carpet style data to generate a vehicle navigation guide light carpet.

[0011] According to another aspect of an embodiment of the present disclosure, a light carpet data processing device is also provided, including: an acquisition module for acquiring initial trajectory point data and trajectory point adjustment parameter information, wherein the initial trajectory point data is used to represent the light carpet centerline data generated by fusing multi-source vehicle data, and the trajectory point adjustment parameter information includes: smoothing item parameters and constraint item parameters, the smoothing item parameters are used to control the smoothness of the vehicle navigation guide light carpet, and the constraint item parameters are used to control the degree of fit between the vehicle navigation guide light carpet and the initial trajectory point data; an optimization module for optimizing the initial trajectory point data according to the trajectory point adjustment parameter information to obtain target trajectory point data, wherein the target trajectory point data is used to construct a vehicle navigation guide light carpet; a generation module for rendering based on the target trajectory point data to generate a vehicle navigation guide light carpet, wherein the vehicle navigation guide light carpet is used to provide navigation driving guidance for the vehicle; and a display module for displaying the vehicle navigation guide light carpet in the vehicle's augmented reality head-up display navigation interface.

[0012] Optionally, the optimization module is further used to: perform uniform step sampling on the initial trajectory point data to obtain a trajectory point sampling result, wherein the spacing between multiple trajectory points in the trajectory point sampling result is the same; and optimize the trajectory point sampling result using the trajectory point adjustment parameter information to obtain the target trajectory point data.

[0013] Optionally, the optimization module is further used to: in response to the number of trajectory points corresponding to the initial trajectory point data being greater than a preset number threshold, perform array conversion processing on the initial trajectory point data to obtain a trajectory point array; and perform interpolation processing using a preset step size and the trajectory point array to obtain a trajectory point sampling result.

[0014] Optionally, the optimization module is also used to: perform differential calculation based on the trajectory point sampling results to obtain a target differential matrix, wherein the target differential matrix is ​​used to represent the curvature change corresponding to the trajectory point sampling results; determine the objective function matrix and linear term vector based on the target differential matrix and the trajectory point adjustment parameter information, wherein the objective function matrix is ​​used to smoothly adjust the trajectory point sampling results, and the linear term vector is used to perform distance constraints on the trajectory point sampling results; use the objective function matrix and the linear term vector to perform optimization solution to obtain the target trajectory point data.

[0015] Optionally, the optimization module is also used to: determine the smooth optimization variables using the target difference matrix and the smooth term parameters, and determine the constrained optimization variables using the constraint term parameters; merge the smooth optimization variables and the constrained optimization variables of the trajectory point sampling results to obtain the objective function matrix.

[0016] Optionally, the generation module is also used to: obtain light carpet style data, wherein the light carpet style data includes at least one of the following: color style, shape style, texture style; render the target trajectory point data based on the light carpet style data to generate a vehicle navigation guidance light carpet.

[0017] According to another aspect of an embodiment of the present disclosure, a vehicle is further provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the light carpet data processing method in the embodiment of the present disclosure.

[0018] According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program. When the executable program runs, the device where the storage medium is located is controlled to execute the light carpet data processing method in the embodiments of the present disclosure.

[0019] According to another aspect of the embodiments of the present disclosure, a computer program product is further provided. The computer program product includes computer instructions. When the computer instructions are executed by a processor, the light carpet data processing method in the embodiments of the present disclosure is implemented.

[0020] In the embodiment of the present disclosure, by acquiring initial trajectory point data and trajectory point adjustment parameter information, and optimizing the initial trajectory point data according to the trajectory point adjustment parameter information, target trajectory point data is obtained, and then rendering processing is performed based on the target trajectory point data to generate a vehicle navigation guide light carpet, and finally the vehicle navigation guide light carpet is displayed in the vehicle's augmented reality head-up display navigation interface, thereby providing the driver with more accurate and smooth navigation guidance and reducing visual interference, thereby achieving the technical effect of improving the smoothness of the light carpet data, and thus solving the technical problem of low light carpet smoothness existing in the light carpet data processing method provided in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of the present disclosure. The exemplary embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation of the present disclosure. In the drawings:

[0022] Figure 1 is a flow chart of a light carpet data processing method according to one embodiment of the present disclosure;

[0023] Figure 2 is a schematic diagram of a light carpet data processing method according to one embodiment of the present disclosure;

[0024] Figure 3 It is a structural block diagram of a light carpet data processing device according to one embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present disclosure.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] The light carpet data processing method in the related art is difficult to maintain the accurate correspondence between the light carpet and the original path, and sacrifices the dynamic stability of the light carpet while pursuing a smooth effect, which can easily lead to unclear navigation instructions and even mislead the driver.

[0028] Specifically, the light carpet data processing methods in related technologies often find it difficult to find an ideal balance between pursuing the smoothness of the light carpet path and maintaining its accurate correspondence with the original path. This technical limitation results in the light carpet appearing smoother on display, but failing to accurately reflect the vehicle's actual driving route. Especially at turns or forks in the road, the deviation of the light carpet path will cause the navigation instructions to become unclear, misleading the driver, thereby increasing uncertainty and risk during driving. In addition, while existing methods improve the smoothness of the light carpet, they often sacrifice its dynamic stability, causing the light carpet to experience delays or incoherent jumps when updating, which will affect the driver's trust in and utilization efficiency of the navigation information, and thus reduce the overall performance and user experience of AR-HUD in navigation application scenarios.

[0029] According to an embodiment of the present disclosure, a method embodiment of a light carpet data processing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] The method embodiment can be executed in an electronic device or similar computing device including a memory and a processor. Taking running on a computer terminal as an example, the computer terminal may include one or more processors (processors may include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microcontroller unit (MCU), a programmable logic device (Field Programmable Gate Array, FPGA), a neural network processor (NPU), a tensor processing unit (TPU), an artificial intelligence (AI) type processor, etc.) and a memory for storing data. Optionally, the above-mentioned computer terminal may also include a transmission device, an input and output device, and a display device for communication functions. It will be understood by those skilled in the art that the above-mentioned structural description is only illustrative and does not limit the structure of the above-mentioned computer terminal. For example, the computer terminal may also include more or fewer components than the above-mentioned structural description, or have a configuration different from the above-mentioned structural description.

[0031] The memory can be used to store computer programs, such as software programs and modules of application software, such as the computer program corresponding to the optical carpet data processing method in the embodiments of the present disclosure. The processor executes the computer program stored in the memory to perform various functional applications and data processing, thereby implementing the aforementioned optical carpet data processing method. The memory can include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory can further include memory remotely located relative to the processor, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0032] The transmission device is used to receive or send data via a network. Specific examples of the aforementioned network may include a wireless network provided by the mobile terminal's communications provider. In one embodiment, the transmission device includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In one embodiment, the transmission device may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0033] The display device can be, for example, a touch-screen liquid crystal display (LCD) and a touch display (also referred to as a "touch screen" or "touch display screen"). The liquid crystal display can enable the user to interact with the user interface of the mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), and the user can interact with the GUI by finger contacts and / or gestures on the touch-sensitive surface. The human-computer interaction functions here optionally include the following interactions: creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital videos, playing digital music and / or web browsing, etc. The executable instructions for performing the above-mentioned human-computer interaction functions are configured / stored in a computer program product or readable storage medium executable by one or more processors.

[0034] Figure 1 is a flow chart of a light carpet data processing method according to one embodiment of the present disclosure. Figure 1 As shown, the method includes the following steps:

[0035] Step S11: Acquire initial trajectory point data and trajectory point adjustment parameter information, wherein the initial trajectory point data is used to represent the light carpet centerline data generated by fusing multi-source vehicle data, and the trajectory point adjustment parameter information includes: smoothing item parameters and constraint item parameters, wherein the smoothing item parameters are used to control the smoothness of the vehicle navigation guidance light carpet, and the constraint item parameters are used to control the degree of fit between the vehicle navigation guidance light carpet and the initial trajectory point data;

[0036] The initial trajectory point data is a series of coordinate points collected in real time by the vehicle's multi-source sensors and processed through a fusion algorithm. It represents the vehicle's predicted or actual location along its travel path. Specifically, this initial trajectory point data includes, but is not limited to, the trajectory point's horizontal (X), vertical (Y), and elevation (Z) coordinates, as well as motion parameters such as speed and direction.

[0037] This multi-source vehicle data is comprehensive information collected from sensor components such as the vehicle's GPS, cameras, radar, and inertial measurement units (IMUs). It includes, but is not limited to, the vehicle's precise location, real-time images of the road environment, the distances and locations of surrounding obstacles, and the vehicle's motion. The fusion of this multi-source data aims to improve the accuracy and reliability of path prediction. By comprehensively analyzing this multi-source information, a more comprehensive understanding of the vehicle's current driving status and environmental conditions can be achieved, resulting in more accurate and reliable light carpet centerline data, providing drivers with clear and precise navigation guidance.

[0038] For example, when fusing multi-source vehicle data, the data must first be preprocessed. Specifically, because different sensor types may have different sampling frequencies and time delays, the data must be calibrated and synchronized in both time and space to ensure that data from each sensor can be compared and integrated within the same time window. Furthermore, because sensor signals often contain noise, filtering techniques (such as Kalman filtering and median filtering) can be applied to remove or reduce the effects of noise and improve data quality.

[0039] Subsequently, information extraction and correlation are performed on the preprocessed multi-source data. Specifically, meaningful features can be extracted from the sensor data, such as precise location information from GPS data, road signs, pedestrians, and vehicles from camera images, and obstacle distances and angles from radar data. This allows the feature information from different sensors to be correlated. For example, a forward obstacle detected by a camera can be matched with the distance measured by radar to confirm the obstacle's exact location.

[0040] Furthermore, the extracted and associated data can be fused using weighted fusion, Kalman filtering, particle filtering, and deep learning algorithms. After data fusion, the actual application effects of the fusion results, such as the vehicle's autonomous driving performance, can be used as feedback to adjust the parameters of the data preprocessing, feature extraction, and fusion algorithms, forming a closed-loop mechanism for continuous optimization.

[0041] For example, based on an assessment of sensor data quality, different weights can be assigned to each set of sensor data. Multi-source data can then be fused by calculating a weighted average. For example, GPS positioning data, which is highly reliable in open areas, can be given a higher weight. However, in urban canyons, where multipath effects can cause GPS signal quality to degrade, the weight of GPS positioning data can be reduced, while the weight of camera visual recognition data can be increased. This dynamic weighting mechanism allows weighted fusion to flexibly address variations in data quality across different scenarios, thereby providing more stable and accurate estimates of vehicle status and environmental perception.

[0042] The aforementioned light carpet centerline data is a set of coordinate points representing the core trajectory of the light carpet, generated through fusion analysis and preliminary processing of multi-source vehicle data. This data is crucial for connecting virtual navigation with real-world driving scenarios. It must accurately reflect vehicle direction and road conditions while also being effectively rendered by the AR-HUD, providing drivers with intuitive, easy-to-follow navigation cues.

[0043] The smoothing parameter (α) controls the smoothness of the vehicle navigation guidance light carpet. A higher α value results in a smoother curve. Therefore, optimizing the initial trajectory point data using the smoothing parameter can reduce the number of curve inflection points corresponding to the initial trajectory point data, thereby improving visual quality. However, an excessively high α value can cause the vehicle navigation guidance light carpet to deviate significantly from the initial trajectory point data, affecting navigation accuracy. Therefore, the α value needs to be adjusted based on the specific driving scenario and user needs to achieve optimal display quality and navigation performance.

[0044] The constraint parameter (β) controls the distance or degree of fit between the vehicle's navigation guidance light carpet and the initial trajectory point data. A larger β value indicates a preference for maintaining proximity to the initial trajectory points during optimization to avoid path deviations caused by excessive smoothing. A smaller β value indicates a greater degree of path adjustment acceptable in pursuit of smoothness, resulting in a smoother light carpet visual effect. Properly setting the β value balances the authenticity and visual quality of the light carpet centerline, ensuring that the navigation information displayed in the AR-HUD is both accurate and visually appealing, thereby improving driving safety and comfort.

[0045] Step S12, optimizing the initial track point data according to the track point adjustment parameter information to obtain target track point data, wherein the target track point data is used to construct a vehicle navigation guide light carpet;

[0046] For example, by applying trajectory point adjustment parameter information to optimize the initial trajectory point data, the generated target trajectory point data can retain the key features of the original path while presenting a smoother and more natural curve shape, reducing the path incoherence and visual abruptness caused by multi-source data fusion, thereby not only improving the visual quality of the light carpet navigation elements displayed by the AR-HUD, but also improving the accuracy and reliability of navigation guidance, providing drivers with more intuitive, comfortable and safe driving assistance information.

[0047] Step S13, performing rendering processing based on the target trajectory point data to generate a vehicle navigation guidance light carpet, wherein the vehicle navigation guidance light carpet is used to provide navigation driving guidance for the vehicle;

[0048] The above-mentioned vehicle navigation guidance light carpet is a virtual image presented in the AR-HUD. It is based on the optimized target trajectory point data and uses rendering technology to form a continuous, smooth, colorful, and diversely shaped light strip or path sign. It is used to intuitively display navigation information such as the road conditions, turning directions, lane changes, etc. in front of the vehicle, providing the driver with real-time and accurate driving guidance.

[0049] Step S14: displaying a vehicle navigation guidance light carpet in the vehicle's augmented reality head-up display navigation interface.

[0050] The above-mentioned augmented reality head-up display navigation interface (i.e. AR-HUD) is a display system integrated into the vehicle's front windshield or transparent display screen. It can integrate virtual navigation information with the real road environment and present it directly in the driver's field of vision, without the driver having to divert his eyes to look at the traditional instrument panel or central control screen.

[0051] The navigation information displayed in the AR-HUD includes, but is not limited to, a navigation light blanket, driving speed, speed limit indicators, obstacle warnings, and traffic sign recognition. It is typically superimposed on the actual road in the form of 3D or 2D augmented images. Furthermore, the AR-HUD supports gesture control and voice recognition, allowing the driver to adjust the displayed content while maintaining focus on the road.

[0052] Based on the above steps S11 to S14, by obtaining initial trajectory point data and trajectory point adjustment parameter information, and optimizing the initial trajectory point data according to the trajectory point adjustment parameter information, the target trajectory point data is obtained, and then rendering processing is performed based on the target trajectory point data to generate a vehicle navigation guide light carpet. Finally, the vehicle navigation guide light carpet is displayed in the vehicle's augmented reality head-up display navigation interface, thereby providing the driver with more accurate and smooth navigation guidance and reducing visual interference, thereby achieving the technical effect of improving the smoothness of the light carpet data, and thus solving the technical problem of low light carpet smoothness in the light carpet data processing method provided in the related art.

[0053] The light carpet data processing method in the embodiment of the present disclosure is further introduced below.

[0054] Optionally, in step S12, the initial trajectory point data is optimized according to the trajectory point adjustment parameter information to obtain the target trajectory point data including:

[0055] Step S121, performing uniform step sampling on the initial trajectory point data to obtain a trajectory point sampling result, wherein the intervals between multiple trajectory points in the trajectory point sampling result are the same;

[0056] Step S122 , optimizing the trajectory point sampling results using the trajectory point adjustment parameter information to obtain target trajectory point data.

[0057] The uniform step sampling method is an algorithm that ensures that the points on the light carpet trajectory are evenly distributed. The algorithm inserts new points between the initial trajectory points so that the distance (or step size) between any two points remains constant.

[0058] The trajectory point sampling results are a series of coordinate points obtained by interpolating and adjusting the initial trajectory point data. These coordinate points are evenly distributed along the initial light carpet trajectory, and the straight-line distance between each point and its adjacent points is equal to ensure continuity and uniformity throughout the entire path. Specifically, the trajectory point sampling results include not only the key turning points of the initial trajectory but also the intermediate points calculated based on the sampling step size, which serve as input for the subsequent smoothing algorithm.

[0059] Exemplarily, first, the sampling step length is calculated based on the total length of the initial trajectory point data and the expected number of sampling points. Subsequently, the initial trajectory point data is cumulatively calculated, that is, starting from the starting point, the cumulative value of the straight-line distance from each trajectory point to the starting point is calculated along the initial trajectory, thereby obtaining the actual distance information between each two points. Furthermore, based on the cumulative distance and the sampling step length, interpolation techniques (such as linear interpolation, spline interpolation, etc.) are used to generate new sampling points on the initial trajectory to ensure that the straight-line distance between any two points is equal to the set sampling step length. Finally, the generated new sampling points are combined with the initial trajectory point data to form a trajectory point sampling result. Through the above method, even if the initial trajectory point data comes from multiple places and is irregular, a trajectory point sampling result with uniform spacing can be obtained, providing more consistent and controllable data input for the subsequent smoothing algorithm.

[0060] Based on the above steps S121 to S122, uniform step sampling can not only generate evenly distributed trajectory points, but also reduce the complexity of data processing, providing more stable and consistent data input for subsequent smoothing processing and light carpet rendering.

[0061] Optionally, in step S121, uniform step sampling is performed on the initial trajectory point data to obtain the trajectory point sampling result, including:

[0062] Step S1211, in response to the number of trajectory points corresponding to the initial trajectory point data being greater than a preset number threshold, performing array conversion processing on the initial trajectory point data to obtain a trajectory point array;

[0063] Step S1212: perform interpolation processing using the preset step size and the trajectory point array to obtain trajectory point sampling results.

[0064] The array conversion process mentioned above refers to the process of converting the initial trajectory point data into an array format that is convenient for computer operation. The initial trajectory point data may be stored in various forms, such as a linked list, a tuple set, or a series of coordinates in a text file. In order to improve the computational efficiency and facilitate the subsequent interpolation and smoothing processing, the initial trajectory point data can be sequentially converted into a two-dimensional array, where each row represents the coordinate information of a point, such as (x i ,y i ).

[0065] The above-mentioned interpolation processing methods include but are not limited to linear interpolation, polynomial interpolation, parametric spline interpolation, nearest neighbor interpolation, etc. Among them, linear interpolation is the simplest interpolation method by inserting new points in a straight line between two original points; polynomial interpolation inserts new points by fitting low-order polynomial curves, which can provide smoother transition points than linear interpolation; parametric spline interpolation approximates the original trajectory by using piecewise polynomials (usually cubic splines) to generate smooth curves; nearest neighbor interpolation selects the original point closest to the desired position as the coordinate of the new point, which is simple and fast, but in some cases may result in an unsmooth result. The specific interpolation method can be selected according to the specific application scenario and the requirements for smoothness and computing resources.

[0066] For example, since at least two points are required to define a line segment or calculate the distance between two points, the preset number threshold can be set to 2. Only when the number of trajectory points corresponding to the initial trajectory point data is greater than 2, the initial trajectory point data can be array-converted to obtain a trajectory point array. When the number of trajectory points corresponding to the initial trajectory point data is less than 2, that is, there is only one initial trajectory point and the trajectory curve cannot be formed, it is necessary to display "Insufficient trajectory points, unable to generate discrete points!" in the AR-HUD to inform the user that there is a problem with the data input, and at the same time request to resend or update the trajectory point data until the number of trajectory points corresponding to the initial trajectory point data is greater than 2.

[0067] Furthermore, after completing the array conversion process to obtain the trajectory point array, a parametric spline interpolation method can be used to interpolate the trajectory point array based on a preset step size to obtain the trajectory point sampling results. Specifically, the X and Y coordinates in the trajectory point array are used as the input of the spline interpolation, and the coefficients and parameterized representation of the spline curve are calculated using the Splprep function. Next, new parameter values ​​can be defined according to the preset step size, and the corresponding X and Y coordinates of the new parameter values ​​can be calculated along the spline curve using the Splev function to obtain the trajectory point sampling results.

[0068] Based on the above steps S1211 to S1212, by performing array conversion and parametric spline interpolation processing on the initial trajectory point data, the smoothness and visual effect of the light carpet can be improved, ensuring the accurate display of the light carpet in the AR-HUD and the effectiveness of the navigation assistance function.

[0069] Optionally, in step S122, the trajectory point sampling result is optimized using the trajectory point adjustment parameter information to obtain target trajectory point data including:

[0070] Step S1221: performing differential calculation based on the trajectory point sampling results to obtain a target differential matrix, wherein the target differential matrix is ​​used to represent the curvature change corresponding to the trajectory point sampling results;

[0071] Step S1222: determining an objective function matrix and a linear term vector based on the target difference matrix and the trajectory point adjustment parameter information, wherein the objective function matrix is ​​used to perform smooth adjustment on the trajectory point sampling results, and the linear term vector is used to perform distance constraints on the trajectory point sampling results;

[0072] Step S1223, using the objective function matrix and the linear term vector to perform optimization and solve, to obtain the target trajectory point data.

[0073] The above-mentioned difference calculation methods include but are not limited to first-order difference, second-order difference, higher-order difference and central difference calculation methods. In the embodiment of the present disclosure, the curvature or rate of change between each point in the trajectory point sampling result is quantified by the second-order difference calculation method, that is, the degree of curvature of the curve segment formed by the current point and the adjacent points before and after, so as to evaluate the smoothness and change trend of the curve. Specifically, a second-order difference of 0 indicates that the sequence is linear (no curvature), and a smaller second-order difference indicates that the sequence changes smoothly.

[0074] The target difference matrix is ​​a sparse matrix, typically expressed as (n-2) × n, where n is the total number of trajectory points. In subsequent embodiments of this disclosure, the target difference matrix is ​​represented by D. The non-zero elements of D are distributed along the diagonal and on both sides of the diagonal. They are used to calculate the curvature change at each sampling point. These elements serve as constraints in the subsequent optimization process, guiding the smoothing of the light carpet centerline while maintaining its consistency with the initial trajectory path.

[0075] For example, for the sampled trajectory point array, the second-order difference can be calculated by constructing a matrix D of shape (n-2)×n. The specific construction rule is as follows: the diagonal elements (i, i) and (i, i+2) are 1, (i, i+1) is -2, and the remaining elements are 0. Therefore, when D is applied to the trajectory point array X, the result of each row will reflect the curvature change of the corresponding trajectory point, that is, (D·x)[i]=x[i+2]-2x[i+1]+x[i], which actually quantifies the local curvature of each sampling point.

[0076] The above linear term vector can be expressed as:

[0077] q=-β·x_ref

[0078] Among them, q is the linear term vector; β is the constraint term parameter; x_ref is the original coordinate of the trajectory point sampling result.

[0079] Furthermore, the objective function matrix and linear term vector can be determined based on the target difference matrix and trajectory point adjustment parameter information, and then optimized using the objective function matrix and linear term vector to obtain the target trajectory point data. Specifically, an operator splitting quadratic programming solver (OSQP solver) can be used for optimization to obtain the target trajectory point data.

[0080] Based on the above steps S1221 to S1223, the target difference matrix is ​​obtained by performing differential calculation on the trajectory point sampling results, and then the objective function matrix and linear term vector are constructed in combination with the trajectory point adjustment parameter information. Finally, through the optimization solution process, the target trajectory point data that is both smooth and close to the original trajectory is obtained, thereby ensuring that the light carpet displayed in the AR-HUD can provide clear navigation instructions while being consistent with the height of the actual route, thereby improving the driving experience and driving safety.

[0081] Optionally, step S1222, determining the objective function matrix according to the target difference matrix and the trajectory point adjustment parameter information includes:

[0082] Step S21, determining smoothing optimization variables using the target difference matrix and smoothing term parameters, and determining constrained optimization variables using the constraint term parameters;

[0083] Step S22 , merging the smoothing optimization variables and the constrained optimization variables of the trajectory point sampling results to obtain an objective function matrix.

[0084] The above smooth optimization variables can be expressed as:

[0085] P smooth =α·D T D

[0086] Among them, P smooth is the smoothing optimization variable; α is the smoothing term parameter; D T D is the transposed product of the target difference matrix.

[0087] The above constrained optimization variables can be expressed as:

[0088] P proximity =β·I

[0089] Among them, P proximity is the constraint optimization variable; β is the constraint parameter; I is the unit matrix, which is used to ensure that the optimized trajectory points are as close as possible to the initial trajectory points.

[0090] Furthermore, the objective function matrix P can be expressed as:

[0091] P=[P smooth +P proximity ,P smooth +P proximity ]

[0092] Based on the above steps S21 to S22, by combining the smooth optimization variables and the constrained optimization variables, an optimization objective function matrix that comprehensively considers smoothness and conformity can be constructed, thereby obtaining an optimized light carpet that is both smooth and close to the original trajectory.

[0093] Optionally, in step S13, performing rendering processing based on the target trajectory point data to generate a vehicle navigation guide light carpet includes:

[0094] Step S131, obtaining light carpet pattern data, wherein the light carpet pattern data includes at least one of the following: color pattern, shape pattern, and texture pattern;

[0095] Step S132 : Rendering the target track point data based on the light carpet pattern data to generate a vehicle navigation guidance light carpet.

[0096] Exemplarily, when rendering is performed based on the target trajectory point data, it is first necessary to import the corresponding rendering library, such as OpenGL, Unity3D, etc., for realizing graphics rendering. Next, based on the acquired light carpet style data, the specific parameters of the color style, shape style and / or texture style are set. For example, the color style can be specified as a gradient color band to distinguish different road areas or navigation stages; the shape style can include the width and edge shape (such as smooth or jagged) of the light carpet; when setting the texture style, certain visual effects can be added to the light carpet, such as road texture or dynamic effects, to enhance the visual experience of AR-HUD. Furthermore, the optimized target trajectory point data can be used to construct a three-dimensional model of the light carpet, and the target trajectory point data can be rendered based on the light carpet style data to generate a vehicle navigation guidance light carpet.

[0097] For example, to improve rendering efficiency and visual quality, the rendering process can be optimized, for example, by using level of detail (LOD) technology to dynamically adjust the detail level of the light carpet, or by using real-time lighting and shadow effects to enhance the three-dimensionality and realism of the light carpet.

[0098] Based on the above steps S131 to S132, an accurate and smooth light carpet shape is generated based on the optimized target trajectory point data, and the appearance of the light carpet is beautified by combining various visual elements (such as color, shape and texture), which can enhance the clarity and attractiveness of the navigation instructions, thereby providing the driver with safer, more intuitive and effective navigation assistance.

[0099] Figure 2 is a schematic diagram of a light carpet data processing method according to one embodiment of the present disclosure, such as Figure 2 As shown in the figure, the left side shows the light carpet trajectory curve generated based on the initial trajectory points in the related art, and the right side shows the optimized light carpet trajectory curve generated by the light carpet data processing method in the embodiment of the present disclosure. It can be seen that the optimized light carpet trajectory curve generated by the light carpet data processing method in the embodiment of the present disclosure not only closely matches the actual road trajectory, but also is smoother and more beautiful.

[0100] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present disclosure.

[0101] The presently disclosed embodiments also provide a light carpet data processing device for implementing the aforementioned embodiments and preferred implementations. Details already described will not be repeated. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. While the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0102] Figure 3 is a structural block diagram of a light carpet data processing device according to one embodiment of the present disclosure, such as Figure 3 As shown, the device includes:

[0103] An acquisition module 301 is configured to acquire initial trajectory point data and trajectory point adjustment parameter information, wherein the initial trajectory point data represents light carpet centerline data generated by fusing multi-source vehicle data. The trajectory point adjustment parameter information includes smoothing term parameters and constraint term parameters. The smoothing term parameters are used to control the smoothness of the vehicle navigation guidance light carpet, and the constraint term parameters are used to control the degree of fit between the vehicle navigation guidance light carpet and the initial trajectory point data.

[0104] An optimization module 302 is configured to optimize the initial trajectory point data according to the trajectory point adjustment parameter information to obtain target trajectory point data, wherein the target trajectory point data is used to construct a vehicle navigation guide light carpet;

[0105] A generation module 303 is configured to perform rendering processing based on the target trajectory point data to generate a vehicle navigation guidance light carpet, wherein the vehicle navigation guidance light carpet is used to provide navigation driving guidance for the vehicle;

[0106] The display module 304 is configured to display a vehicle navigation guidance light carpet in an augmented reality head-up display navigation interface of the vehicle.

[0107] Optionally, the optimization module 302 is further used to: perform uniform step sampling on the initial trajectory point data to obtain a trajectory point sampling result, wherein the spacing between multiple trajectory points in the trajectory point sampling result is the same; and optimize the trajectory point sampling result using the trajectory point adjustment parameter information to obtain the target trajectory point data.

[0108] Optionally, the optimization module 302 is further used to: in response to the number of trajectory points corresponding to the initial trajectory point data being greater than a preset number threshold, perform array conversion processing on the initial trajectory point data to obtain a trajectory point array; and perform interpolation processing using a preset step size and the trajectory point array to obtain a trajectory point sampling result.

[0109] Optionally, the optimization module 302 is also used to: perform differential calculation based on the trajectory point sampling results to obtain a target differential matrix, wherein the target differential matrix is ​​used to represent the curvature change corresponding to the trajectory point sampling results; determine the objective function matrix and the linear term vector based on the target differential matrix and the trajectory point adjustment parameter information, wherein the objective function matrix is ​​used to smoothly adjust the trajectory point sampling results, and the linear term vector is used to perform distance constraints on the trajectory point sampling results; use the objective function matrix and the linear term vector to perform optimization solution to obtain the target trajectory point data.

[0110] Optionally, the optimization module 302 is further used to: determine the smooth optimization variables using the target difference matrix and the smooth term parameters, and determine the constrained optimization variables using the constraint term parameters; merge the smooth optimization variables and the constrained optimization variables of the trajectory point sampling results to obtain the objective function matrix.

[0111] Optionally, the generation module 303 is further used to: obtain light carpet style data, wherein the light carpet style data includes at least one of the following: color style, shape style, texture style; render the target trajectory point data based on the light carpet style data to generate a vehicle navigation guidance light carpet.

[0112] It should be noted that the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0113] According to another aspect of an embodiment of the present disclosure, a vehicle is further provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the light carpet data processing method in the embodiment of the present disclosure.

[0114] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0115] S1. Obtaining initial trajectory point data and trajectory point adjustment parameter information, wherein the initial trajectory point data is used to represent light carpet centerline data generated by fusing multi-source vehicle data, and the trajectory point adjustment parameter information includes: smoothing item parameters and constraint item parameters. The smoothing item parameters are used to control the smoothness of the vehicle navigation guidance light carpet, and the constraint item parameters are used to control the degree of fit between the vehicle navigation guidance light carpet and the initial trajectory point data.

[0116] S2, optimizing the initial trajectory point data according to the trajectory point adjustment parameter information to obtain target trajectory point data, wherein the target trajectory point data is used to construct a vehicle navigation guidance light carpet;

[0117] S3, performing rendering processing based on the target trajectory point data to generate a vehicle navigation guidance light carpet, wherein the vehicle navigation guidance light carpet is used to provide navigation driving guidance for the vehicle;

[0118] S4, displays the vehicle navigation guidance light carpet in the vehicle's augmented reality head-up display navigation interface.

[0119] According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program. When the executable program runs, the device where the storage medium is located is controlled to execute the light carpet data processing method in the embodiments of the present disclosure.

[0120] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0121] S1. Obtaining initial trajectory point data and trajectory point adjustment parameter information, wherein the initial trajectory point data is used to represent light carpet centerline data generated by fusing multi-source vehicle data, and the trajectory point adjustment parameter information includes: smoothing item parameters and constraint item parameters. The smoothing item parameters are used to control the smoothness of the vehicle navigation guidance light carpet, and the constraint item parameters are used to control the degree of fit between the vehicle navigation guidance light carpet and the initial trajectory point data.

[0122] S2, optimizing the initial trajectory point data according to the trajectory point adjustment parameter information to obtain target trajectory point data, wherein the target trajectory point data is used to construct a vehicle navigation guidance light carpet;

[0123] S3, performing rendering processing based on the target trajectory point data to generate a vehicle navigation guidance light carpet, wherein the vehicle navigation guidance light carpet is used to provide navigation driving guidance for the vehicle;

[0124] S4, displays the vehicle navigation guidance light carpet in the vehicle's augmented reality head-up display navigation interface.

[0125] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0126] According to another aspect of the embodiments of the present disclosure, a computer program product is further provided. The computer program product includes computer instructions. When the computer instructions are executed by a processor, the light carpet data processing method in the embodiments of the present disclosure is implemented.

[0127] Optionally, in this embodiment, the computer program product may be configured as a computer program for executing the following steps:

[0128] S1. Obtaining initial trajectory point data and trajectory point adjustment parameter information, wherein the initial trajectory point data is used to represent light carpet centerline data generated by fusing multi-source vehicle data, and the trajectory point adjustment parameter information includes: smoothing item parameters and constraint item parameters. The smoothing item parameters are used to control the smoothness of the vehicle navigation guidance light carpet, and the constraint item parameters are used to control the degree of fit between the vehicle navigation guidance light carpet and the initial trajectory point data.

[0129] S2, optimizing the initial trajectory point data according to the trajectory point adjustment parameter information to obtain target trajectory point data, wherein the target trajectory point data is used to construct a vehicle navigation guidance light carpet;

[0130] S3, performing rendering processing based on the target trajectory point data to generate a vehicle navigation guidance light carpet, wherein the vehicle navigation guidance light carpet is used to provide navigation driving guidance for the vehicle;

[0131] S4, displays the vehicle navigation guidance light carpet in the vehicle's augmented reality head-up display navigation interface.

[0132] The serial numbers of the above-mentioned embodiments of the present disclosure are for description only and do not represent the advantages or disadvantages of the embodiments.

[0133] In the above embodiments of the present disclosure, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0134] In the several embodiments provided in the present disclosure, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0135] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0136] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0137] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0138] The above is only a preferred embodiment of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present disclosure. These improvements and modifications should also be regarded as within the scope of protection of the present disclosure.

Claims

1. A light carpet data processing method, characterized in that: include: Acquiring initial trajectory point data and trajectory point adjustment parameter information, wherein the initial trajectory point data is used to represent light carpet centerline data generated by fusing multi-source vehicle data, and the trajectory point adjustment parameter information includes: a smoothing parameter and a constraint parameter, wherein the smoothing parameter is used to control the smoothness of the vehicle navigation guidance light carpet, and the constraint parameter is used to control the degree of fit between the vehicle navigation guidance light carpet and the initial trajectory point data; Optimizing the initial trajectory point data according to the trajectory point adjustment parameter information to obtain target trajectory point data, wherein the target trajectory point data is used to construct the vehicle navigation guide light carpet; Performing rendering processing based on the target trajectory point data to generate the vehicle navigation guide light carpet, wherein the vehicle navigation guide light carpet is used to provide navigation driving guidance for the vehicle; The vehicle navigation guidance light carpet is displayed in an augmented reality head-up display navigation interface of the vehicle.

2. The light carpet data processing method according to claim 1, characterized in that: Optimizing the initial trajectory point data according to the trajectory point adjustment parameter information to obtain the target trajectory point data includes: Performing uniform step sampling on the initial trajectory point data to obtain a trajectory point sampling result, wherein the intervals between multiple trajectory points in the trajectory point sampling result are the same; The trajectory point sampling result is optimized using the trajectory point adjustment parameter information to obtain the target trajectory point data.

3. The light carpet data processing method according to claim 2, characterized in that: Performing uniform step sampling on the initial trajectory point data to obtain the trajectory point sampling result includes: In response to the number of trajectory points corresponding to the initial trajectory point data being greater than a preset number threshold, performing array conversion processing on the initial trajectory point data to obtain a trajectory point array; Interpolation processing is performed using a preset step size and the trajectory point array to obtain the trajectory point sampling result.

4. The light carpet data processing method according to claim 2, characterized in that: Optimizing the trajectory point sampling result using the trajectory point adjustment parameter information to obtain the target trajectory point data includes: Performing differential calculation based on the trajectory point sampling results to obtain a target differential matrix, wherein the target differential matrix is ​​used to represent the curvature change corresponding to the trajectory point sampling results; Determining an objective function matrix and a linear term vector according to the target difference matrix and the trajectory point adjustment parameter information, wherein the objective function matrix is ​​used to smoothly adjust the trajectory point sampling results, and the linear term vector is used to perform distance constraints on the trajectory point sampling results; The objective function matrix and the linear term vector are used to perform optimization and solve to obtain the target trajectory point data.

5. The light carpet data processing method according to claim 4, characterized in that: Determining the objective function matrix according to the target difference matrix and the trajectory point adjustment parameter information includes: Determining smoothing optimization variables using the target difference matrix and the smoothing term parameters, and determining constrained optimization variables using the constraint term parameters; The smoothing optimization variables and the constrained optimization variables of the trajectory point sampling results are merged to obtain the objective function matrix.

6. The light carpet data processing method according to claim 1, characterized in that: Performing rendering processing based on the target trajectory point data to generate the vehicle navigation guide light carpet includes: Acquire light carpet pattern data, wherein the light carpet pattern data includes at least one of the following: color pattern, shape pattern, and texture pattern; The target trajectory point data is rendered based on the light carpet pattern data to generate the vehicle navigation guidance light carpet.

7. A light carpet data processing device, characterized in that: include: an acquisition module, configured to acquire initial trajectory point data and trajectory point adjustment parameter information, wherein the initial trajectory point data is used to represent light carpet centerline data generated by fusing multi-source vehicle data, and the trajectory point adjustment parameter information includes: a smoothing parameter and a constraint parameter, wherein the smoothing parameter is used to control the smoothness of the vehicle navigation guidance light carpet, and the constraint parameter is used to control the degree of fit between the vehicle navigation guidance light carpet and the initial trajectory point data; an optimization module, configured to optimize the initial trajectory point data according to the trajectory point adjustment parameter information to obtain target trajectory point data, wherein the target trajectory point data is used to construct the vehicle navigation guide light carpet; a generating module, configured to perform rendering processing based on the target trajectory point data to generate the vehicle navigation guide light carpet, wherein the vehicle navigation guide light carpet is used to provide navigation driving guidance for the vehicle; A display module is configured to display the vehicle navigation guide light carpet in an augmented reality head-up display navigation interface of the vehicle.

8. A vehicle, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the light carpet data processing method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the storage medium is located is controlled to execute the light carpet data processing method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product comprises computer instructions, which, when executed by a processor, implement the light carpet data processing method according to any one of claims 1 to 6.

Images