Map rendering method and device, equipment and storage medium

Abstract

The embodiment of the invention relates to the technical field of auxiliary driving, and discloses a map rendering method, device and equipment and a storage medium, and the method comprises the steps: when a vehicle position is updated but a map is not updated, comparing current vehicle pose data with previous vehicle pose data, and determining the pose offset of a vehicle in a vehicle position updating time period; adjusting a vector road surface in the map based on the pose offset; and rendering the adjusted vector road surface. By applying the technical scheme of the invention, the problem of'floating 'or dislocation of the vehicle can be effectively solved, and the accuracy of the rendering result is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of assisted driving technology, specifically to a map rendering method, apparatus, device, and storage medium. Background Technology

[0002] In the fields of intelligent transportation and autonomous driving, positioning systems update vehicle positions at a relatively high frequency, while perception systems (such as cameras and LiDAR) are responsible for capturing road environment information and updating maps at a relatively low frequency. When the positioning system has updated the vehicle's position, but the perception system is still using the old map, the rendering result will show the vehicle "floating" in the wrong position or misaligned with environmental objects (such as obstacles and lane lines). For example, the vehicle may have actually changed lanes, but the rendered image may still show it in its original lane.

[0003] Figure 1 This is a schematic diagram of the road surface Bitmap provided by the present invention. Currently, when drawing the road surface, a Bitmap image is used. Each pixel or element in the Bitmap image needs to be classified as ground / non-ground, which involves complex image processing or point cloud segmentation algorithms (such as semantic segmentation and deep learning model inference), resulting in a huge amount of computation. Although gridding can improve the efficiency of ground / non-ground recognition, it will cause the edge drawing to appear rectangular (jagged or blocky and discontinuous), affecting visual smoothness and environmental perception accuracy. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention provide a map rendering method, apparatus, device and storage medium to solve the problem of vehicles "floating" or being misaligned due to asynchronous vehicle location updates and map updates in the prior art.

[0005] According to one aspect of the present invention, a map rendering method is provided, the method comprising:

[0006] When the vehicle position is updated but the map is not updated, the current vehicle pose data is compared with the previous vehicle pose data to determine the vehicle's pose offset during the vehicle position update period.

[0007] Based on the pose offset, the vector road surface in the map is adjusted;

[0008] Render the adjusted vector road surface.

[0009] According to another aspect of the present invention, a map rendering apparatus is provided, comprising:

[0010] The determination module is used to compare the current vehicle pose data with the previous vehicle pose data when the vehicle position is updated but the map is not updated, and to determine the vehicle's pose offset during the vehicle position update period.

[0011] An adjustment module is used to adjust the vector road surface in the map based on the pose offset;

[0012] The rendering module is used to render the adjusted vector road surface.

[0013] According to another aspect of the present invention, a map rendering device is provided, comprising:

[0014] The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus.

[0015] The memory is used to store at least one executable instruction that causes the processor to perform the map rendering method as described above.

[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, the storage medium storing at least one executable instruction that causes a map rendering device / apparatus to perform the map rendering method described above.

[0017] This invention addresses the issue of vehicle "floating" or misalignment by adjusting vector road surfaces using pose offset when the map remains unchanged after vehicle position updates. This ensures accurate alignment between the vehicle model and the vector road surface in the rendered image. This method effectively solves the problem of vehicle "floating" or misalignment, improving the accuracy of the rendering results. Using vector road surfaces instead of Bitmap images avoids the jagged edges caused by meshing in traditional Bitmap rendering. The use of vector graphics makes road edges smoother and the visual effect more natural. Compared to the complex image processing or point cloud segmentation algorithms in Bitmap rendering, adjusting and rendering using vector road surfaces reduces computation. This not only improves the system's real-time performance but also reduces the demand for computing resources. Dynamically adjusting the vector road surface to adapt to changes in vehicle position better handles situations with low map update frequency. This solution, by combining vehicle pose offset adjustment and vector road surface rendering, significantly improves the accuracy and efficiency of map rendering while reducing computational complexity.

[0018] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0019] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0020] Figure 1 A schematic diagram of the road surface bitmap provided by the present invention is shown;

[0021] Figure 2 A flowchart illustrating a first embodiment of the map rendering method provided by the present invention is shown;

[0022] Figure 3 A flowchart illustrating a second embodiment of the map rendering method provided by the present invention is shown;

[0023] Figure 4 A flowchart illustrating the generation of road boundary topological polygons provided by the present invention is shown;

[0024] Figure 5 This diagram illustrates the process of extracting road boundary pixels provided by the present invention.

[0025] Figure 6 A flowchart of the map rendering method provided by the present invention is shown;

[0026] Figure 7 A schematic diagram of an embodiment of the map rendering apparatus provided by the present invention is shown;

[0027] Figure 8 A schematic diagram of an embodiment of the map rendering device provided by the present invention is shown;

[0028] Figure 9 A structural schematic diagram of an embodiment of the vehicle provided by the present invention is shown. Detailed Implementation

[0029] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0030] Figure 2 A flowchart illustrating a first embodiment of the map rendering method of the present invention is shown, which can be executed by a domain controller in a vehicle, such as an autonomous driving domain controller. Figure 2 As shown, the method includes the following steps:

[0031] Step 210: When the vehicle position is updated but the map is not updated, compare the current vehicle pose data with the previous vehicle pose data to determine the vehicle's pose offset during the vehicle position update period.

[0032] This occurs when vehicle location data is updated but the map is not, specifically when the vehicle's positioning system (such as GPS or other positioning sensors) frequently updates the vehicle's position, while the perception system (such as cameras or LiDAR) updates the map less frequently. The current vehicle pose data (position and attitude) is compared with previous pose data. This comparison allows us to determine the vehicle's pose shift during the location update period. This shift reflects the vehicle's movement and changes in orientation during the period when the map was not updated.

[0033] Step 220: Adjust the vector road surface in the map based on the pose offset.

[0034] Based on the pose offset determined in step 210, the vector road surfaces in the map are adjusted. This means adjusting the displayed position of the roads according to the actual movement of the vehicle to ensure the accuracy of map rendering. The rendered map will be used to support autonomous driving decisions and path planning.

[0035] Step 230: Render the adjusted vector road surface.

[0036] By rendering the adjusted vector road surface, the vehicle model displayed on the map is ensured to be precisely aligned with the vector road surface. This process avoids the phenomenon of vehicles "floating" on the map or being misaligned with roads and environmental objects (such as obstacles and lane lines). This method effectively solves the vehicle misalignment problem caused by map update lag, ensuring the real-time and accuracy requirements of the autonomous driving system.

[0037] This invention addresses the issue of vehicle "floating" or misalignment by adjusting vector road surfaces using pose offset when the map remains unchanged after vehicle position updates. This ensures accurate alignment between the vehicle model and the vector road surface in the rendered image. This method effectively solves the problem of vehicle "floating" or misalignment, improving the accuracy of the rendering results. Using vector road surfaces instead of Bitmap images avoids the jagged edges caused by meshing in traditional Bitmap rendering. The use of vector graphics makes road edges smoother and the visual effect more natural. Compared to the complex image processing or point cloud segmentation algorithms in Bitmap rendering, adjusting and rendering using vector road surfaces reduces computation. This not only improves the system's real-time performance but also reduces the demand for computing resources. Dynamically adjusting the vector road surface to adapt to changes in vehicle position better handles situations with low map update frequency. This solution, by combining vehicle pose offset adjustment and vector road surface rendering, significantly improves the accuracy and efficiency of map rendering while reducing computational complexity.

[0038] Figure 3A flowchart illustrating another embodiment of the map rendering method of the present invention is shown, which can be executed by a domain controller in a vehicle, such as an autonomous driving domain controller. Figure 3 As shown, the method includes the following steps:

[0039] Step 310: When the vehicle position is updated but the map is not updated, compare the current vehicle pose data with the previous vehicle pose data to determine the vehicle's pose offset during the vehicle position update period.

[0040] Pose offset includes position offset and attitude offset. Position offset refers to the displacement change of the vehicle in a three-dimensional coordinate system or a planar coordinate system, while attitude offset describes the change of the vehicle's direction or angle.

[0041] Step 320: Based on the pose offset, translate and / or rotate the vector road surface in the map.

[0042] In this step, the vector road surface in the map is translated and / or rotated accordingly based on the determined pose offset.

[0043] In one alternative approach, the vector road surface is extracted as follows:

[0044] The vehicle's anchor point is determined from the acquired prior road environment image. The anchor point represents the vehicle's reference point in the prior road environment image, which corresponds to the prior vehicle pose data in time.

[0045] Based on anchor points, road boundary pixels in prior road environment images are identified;

[0046] Starting from the identified road boundary pixels, a pre-defined exploration algorithm is used to search in the prior road environment image to identify the set of pixels of the road boundary in the prior road environment image;

[0047] A vector road surface is generated based on the set of pixels.

[0048] In this embodiment, an anchor point is determined from the acquired prior road environment image. This anchor point serves as a reference point for locating the vehicle's position in the image. The anchor point is selected based on prior vehicle pose data, which is temporally synchronized with the prior road environment image. This means the anchor point reflects the vehicle's specific position at a particular point in time. Once the anchor point is determined, the next step is to identify road boundary pixels in the prior road environment image. These pixels identify the road edges and are crucial for defining the road's shape and location. Starting with the identified road boundary pixels, a pre-defined exploration algorithm is used to search the image. The algorithm aims to find all pixels related to the road boundaries in the image, forming a complete set of pixels. Finally, based on the identified set of pixels, a vector road surface is generated. This vectorized road surface allows the road boundaries to be represented in precise geometry on the map.

[0049] Specifically, the preset exploration algorithm can be an 8-directional search algorithm that combines a priority queue and a hash table to efficiently identify all road boundary pixels in the image and then generate road boundary topological polygons.

[0050] Reference Figure 4 The diagram shows a flowchart of generating a road boundary topological polygon provided by this invention. Specifically, a priority queue can be created, and the identified road boundary pixels are inserted into the priority queue as starting nodes, with their cost values ​​set to 0. A hash table is simultaneously constructed, recording the predecessor node information and corresponding cost values ​​of each node, with the predecessor of the starting node marked as itself. When the priority queue is not empty, an eight-directional mesh exploration is performed with the current node as the center; the cost of each adjacent node is calculated; if an adjacent node has not been visited or the new path has a better cost, its predecessor node information and cost value are updated, and it is re-inserted into the priority queue. Based on the predecessor relationship chain recorded in the hash table, the boundary nodes are connected to form a closed polygon.

[0051] In one alternative approach, road boundary pixels in a prior road environment image are identified based on anchor points, which may specifically include the following steps:

[0052] Generate a ray starting from the anchor point;

[0053] For rays, monitor their propagation path in prior road environment images and record the pixels along the path and their neighborhood information during propagation.

[0054] For a given pixel along a road, if the neighborhood information of that pixel meets a preset condition, then that pixel is identified as a road boundary pixel.

[0055] In this embodiment, rays are generated starting from anchor points. These rays can extend outward from the anchor points at different angles to cover different directions in the image. For each ray, its propagation path in the prior road environment image is monitored. During the ray propagation, each pixel along the ray and its neighborhood information are recorded. Neighborhood information typically includes features such as color, brightness, and texture around the pixel. For each pixel along the ray, its neighborhood information is checked to see if it meets preset conditions. Preset conditions can be specific color changes, brightness differences, texture features, etc., used to identify road boundaries. If the neighborhood information of a pixel along the ray meets these preset conditions, it is identified as a road boundary pixel. This ray- and neighborhood information-based detection method can accurately extract road boundaries in complex image environments.

[0056] In one alternative approach, if the neighborhood information of the pixel along the line meets a preset condition, then the pixel along the line is determined as a road boundary pixel. Specifically, this may include the following steps:

[0057] If the neighboring pixels of a pixel along the line include both passable and impassable pixels, then the pixel along the line is determined as a road boundary pixel.

[0058] In this embodiment, for a given line-bound pixel, its surrounding neighboring pixels are examined. If both passable and impassable pixels exist in the neighborhood of the line-bound pixel, then the line-bound pixel is determined to be a road boundary pixel. Passable pixels typically represent the road surface and have specific color, brightness, or texture characteristics, while impassable pixels may represent road edges, obstacles, or other non-road areas. This determination is based on the characteristic that road boundaries are usually located between passable and impassable areas.

[0059] Reference Figure 5 The diagram illustrates the process of extracting road boundary pixels according to the present invention. Anchor points of vehicles are determined from the acquired prior road environment image. Rays are generated starting from these anchor points. For each ray, its propagation path in the prior road environment image is monitored, and each ray along the path and its neighborhood information are recorded. For a given ray, its surrounding neighboring pixels are checked. If both passable and impassable pixels exist simultaneously in the neighborhood of the ray, then the ray is identified as a road boundary pixel.

[0060] In one alternative approach, a vector road surface is generated based on a set of pixels, which may specifically include the following steps:

[0061] Based on the relative positional relationship between each pixel in the pixel set and the anchor point in the pixel coordinate system, the pixels in the pixel set are mapped to the vehicle coordinate system with the anchor point as the origin;

[0062] Curve fitting is performed on the set of pixels after coordinate transformation to generate the road boundary curve;

[0063] A vector road surface is generated based on the road boundary curve.

[0064] In this embodiment, firstly, based on the relative positional relationship between each pixel in the pixel set and the anchor point in the pixel coordinate system, these pixels are mapped to a vehicle coordinate system with the anchor point as the origin. Curve fitting is then performed on the coordinate-transformed pixel set. Curve fitting can use various methods, such as polynomial fitting, spline curve fitting, or other suitable mathematical models, to generate a smooth road boundary curve. Based on the generated road boundary curve, a vectorized road surface is created. The vectorized road surface can be used for map rendering, path planning, and other applications, providing an accurate geometric representation.

[0065] Alternatively, the pixel set after coordinate transformation can be thinned first, and then curve fitting can be performed on the thinned pixel set to generate the road boundary curve. Data thinning aims to reduce the number of data points while maintaining the overall shape and characteristics of the data. By reducing redundant data points, computational complexity can be reduced and processing speed can be improved. For example, in the vehicle coordinate system, if the distance between any two pixels in the pixel set is less than a preset distance threshold, such as 0.15 meters, then one pixel can be selected from the pair and removed from the pixel set.

[0066] This solution can extract accurate vector road surfaces from road environment images, providing precise road information support for autonomous driving systems.

[0067] Step 330: Render the adjusted vector road surface.

[0068] The above method ensures that the vehicle models in the rendered map are aligned with the vector road surfaces, thus avoiding misalignment.

[0069] In one alternative approach, rendering the adjusted vector road surface may include the following steps:

[0070] The adjusted vector road surface is then triangulated.

[0071] Render the set of triangles obtained through triangulation.

[0072] Triangulation is the process of decomposing a complex polygon into a series of non-overlapping triangles. In this embodiment, the adjusted vector road surface is triangulated, decomposing it into multiple triangles to generate a set of triangles that collectively cover the entire road surface.

[0073] Rendering is the process of converting geometric data into a visual image. A graphics rendering engine is used to render a set of triangles. In the rendered map, vehicle models are precisely aligned with vector road surfaces, avoiding misalignment.

[0074] Reference Figure 6 The diagram shows a flowchart of the map rendering method provided by this invention. The process begins with acquiring a road environment image from a sensor or camera. A reference point for the vehicle in the image is determined for subsequent coordinate transformation and vector road surface adjustment. Rays are generated starting from anchor points to identify road boundary pixels in the image. Based on an 8-direction search algorithm, a priority queue and hash table are used for topology reconstruction to construct the topological structure of the road boundary. The 8-direction search algorithm is mainly used to locally explore around the boundary pixels, finding adjacent boundary pixels to identify the set of pixels representing the road boundary in the image. The pixels in the set are mapped to the vehicle coordinate system. The pixel set after coordinate transformation is thinned to reduce the data volume and improve processing efficiency. Curve fitting is performed on the pixel set after data thinning to generate a smooth road boundary curve. Based on this road boundary curve, a vector road surface is generated. When the vehicle position is updated but the map is not updated, the vehicle's pose offset during the vehicle position update period is determined. Based on the pose offset, the vector road surface in the map is adjusted. The adjusted vector road surface is triangulated. The set of triangles obtained through triangulation is rendered to obtain a high-precision map that can be used for driving assistance.

[0075] This invention addresses the issue of vehicle "floating" or misalignment by adjusting vector road surfaces using pose offset when the map remains unchanged after vehicle position updates. This ensures accurate alignment between the vehicle model and the vector road surface in the rendered image. This method effectively solves the problem of vehicle "floating" or misalignment, improving the accuracy of the rendering results. Using vector road surfaces instead of Bitmap images avoids the jagged edges caused by meshing in traditional Bitmap rendering. The use of vector graphics makes road edges smoother and the visual effect more natural. Compared to the complex image processing or point cloud segmentation algorithms in Bitmap rendering, adjusting and rendering using vector road surfaces reduces computation. This not only improves the system's real-time performance but also reduces the demand for computing resources. Dynamically adjusting the vector road surface to adapt to changes in vehicle position better handles situations with low map update frequency. This solution, by combining vehicle pose offset adjustment and vector road surface rendering, significantly improves the accuracy and efficiency of map rendering while reducing computational complexity.

[0076] Figure 7 A schematic diagram of an embodiment of the map rendering apparatus of the present invention is shown. Figure 7 As shown, the device 700 includes: a determination module 710, an adjustment module 720, and a rendering module 730.

[0077] The determination module is used to compare the current vehicle pose data with the previous vehicle pose data when the vehicle position is updated but the map is not updated, and to determine the vehicle's pose offset during the vehicle position update period.

[0078] The adjustment module is used to adjust the vector road surface in the map based on the pose offset;

[0079] The rendering module is used to render the adjusted vector road surface.

[0080] In one alternative approach, the adjustment module is specifically used for:

[0081] Based on pose offset, the vector road surface in the map is translated and / or rotated.

[0082] In an alternative embodiment, the map rendering apparatus of the present invention is further used for:

[0083] The vehicle's anchor point is determined from the acquired prior road environment image. The anchor point represents the vehicle's reference point in the prior road environment image, which corresponds to the prior vehicle pose data in time.

[0084] Based on anchor points, road boundary pixels in prior road environment images are identified;

[0085] Starting from the identified road boundary pixels, a pre-defined exploration algorithm is used to search in the prior road environment image to identify the set of pixels of the road boundary in the prior road environment image;

[0086] A vector road surface is generated based on the set of pixels.

[0087] In an alternative embodiment, the map rendering apparatus of the present invention is further used for:

[0088] Based on the relative positional relationship between each pixel in the pixel set and the anchor point in the pixel coordinate system, the pixels in the pixel set are mapped to the vehicle coordinate system with the anchor point as the origin;

[0089] Curve fitting is performed on the set of pixels after coordinate transformation to generate the road boundary curve;

[0090] A vector road surface is generated based on the road boundary curve.

[0091] In an alternative embodiment, the map rendering apparatus of the present invention is further used for:

[0092] Generate a ray starting from the anchor point;

[0093] For rays, monitor their propagation path in prior road environment images and record the pixels along the path and their neighborhood information during propagation.

[0094] For a given pixel along a road, if the neighborhood information of that pixel meets a preset condition, then that pixel is identified as a road boundary pixel.

[0095] In an alternative embodiment, the map rendering apparatus of the present invention is further used for:

[0096] If the neighboring pixels of a pixel along the line include both passable and impassable pixels, then the pixel along the line is determined as a road boundary pixel.

[0097] In one alternative approach, the rendering module is specifically used for:

[0098] The adjusted vector road surface is then triangulated.

[0099] Render the set of triangles obtained through triangulation.

[0100] This invention addresses the issue of vehicle "floating" or misalignment by adjusting vector road surfaces using pose offset when the map remains unchanged after vehicle position updates. This ensures accurate alignment between the vehicle model and the vector road surface in the rendered image. This method effectively solves the problem of vehicle "floating" or misalignment, improving the accuracy of the rendering results. Using vector road surfaces instead of Bitmap images avoids the jagged edges caused by meshing in traditional Bitmap rendering. The use of vector graphics makes road edges smoother and the visual effect more natural. Compared to the complex image processing or point cloud segmentation algorithms in Bitmap rendering, adjusting and rendering using vector road surfaces reduces computation. This not only improves the system's real-time performance but also reduces the demand for computing resources. Dynamically adjusting the vector road surface to adapt to changes in vehicle position better handles situations with low map update frequency. This solution, by combining vehicle pose offset adjustment and vector road surface rendering, significantly improves the accuracy and efficiency of map rendering while reducing computational complexity.

[0101] Figure 8 The diagram shows a structural schematic of an embodiment of the map rendering device of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the map rendering device.

[0102] like Figure 8 As shown, the map rendering device may include: a processor 802, a communications interface 804, a memory 806, and a communications bus 808.

[0103] The processor 802, communication interface 804, and memory 806 communicate with each other via communication bus 808. Communication interface 804 is used to communicate with other network elements such as clients or other servers. Processor 802 executes program 810, specifically performing the relevant steps described above in the map rendering method embodiment.

[0104] Specifically, program 810 may include program code, which includes computer-executable instructions.

[0105] Processor 802 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The map rendering device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0106] Memory 806 is used to store program 810. Memory 806 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0107] Specifically, program 810 can be called by processor 802 to cause the map rendering device to perform the following operations:

[0108] When the vehicle position is updated but the map is not updated, the current vehicle pose data is compared with the previous vehicle pose data to determine the vehicle's pose offset during the vehicle position update period.

[0109] Based on pose offset, the vector road surface in the map is adjusted;

[0110] Render the adjusted vector road surface.

[0111] In an alternative manner, program 810 is invoked by processor 802 to cause the map rendering device to perform the following operations:

[0112] Based on pose offset, the vector road surface in the map is translated and / or rotated.

[0113] In an alternative manner, program 810 is invoked by processor 802 to cause the map rendering device to perform the following operations:

[0114] The vehicle's anchor point is determined from the acquired prior road environment image. The anchor point represents the vehicle's reference point in the prior road environment image, which corresponds to the prior vehicle pose data in time.

[0115] Based on anchor points, road boundary pixels in prior road environment images are identified;

[0116] Starting from the identified road boundary pixels, a pre-defined exploration algorithm is used to search in the prior road environment image to identify the set of pixels of the road boundary in the prior road environment image;

[0117] A vector road surface is generated based on the set of pixels.

[0118] In an alternative manner, program 810 is invoked by processor 802 to cause the map rendering device to perform the following operations:

[0119] Based on the relative positional relationship between each pixel in the pixel set and the anchor point in the pixel coordinate system, the pixels in the pixel set are mapped to the vehicle coordinate system with the anchor point as the origin;

[0120] Curve fitting is performed on the set of pixels after coordinate transformation to generate the road boundary curve;

[0121] A vector road surface is generated based on the road boundary curve.

[0122] In an alternative manner, program 810 is invoked by processor 802 to cause the map rendering device to perform the following operations:

[0123] Generate a ray starting from the anchor point;

[0124] For rays, monitor their propagation path in prior road environment images and record the pixels along the path and their neighborhood information during propagation.

[0125] For a given pixel along a road, if the neighborhood information of that pixel meets a preset condition, then that pixel is identified as a road boundary pixel.

[0126] In an alternative manner, program 810 is invoked by processor 802 to cause the map rendering device to perform the following operations:

[0127] If the neighboring pixels of a pixel along the line include both passable and impassable pixels, then the pixel along the line is determined as a road boundary pixel.

[0128] In an alternative manner, program 810 is invoked by processor 802 to cause the map rendering device to perform the following operations:

[0129] The adjusted vector road surface is then triangulated.

[0130] Render the set of triangles obtained through triangulation.

[0131] This invention addresses the issue of vehicle "floating" or misalignment by adjusting vector road surfaces using pose offset when the map remains unchanged after vehicle position updates. This ensures accurate alignment between the vehicle model and the vector road surface in the rendered image. This method effectively solves the problem of vehicle "floating" or misalignment, improving the accuracy of the rendering results. Using vector road surfaces instead of Bitmap images avoids the jagged edges caused by meshing in traditional Bitmap rendering. The use of vector graphics makes road edges smoother and the visual effect more natural. Compared to the complex image processing or point cloud segmentation algorithms in Bitmap rendering, adjusting and rendering using vector road surfaces reduces computation. This not only improves the system's real-time performance but also reduces the demand for computing resources. Dynamically adjusting the vector road surface to adapt to changes in vehicle position better handles situations with low map update frequency. This solution, by combining vehicle pose offset adjustment and vector road surface rendering, significantly improves the accuracy and efficiency of map rendering while reducing computational complexity.

[0132] Figure 9 A structural schematic diagram of an embodiment of the vehicle of the present invention is shown. (As shown) Figure 9 As shown, the vehicle 900 includes: sensors, one or more processors, and a communication interface;

[0133] Sensors are used to capture road environment information and generate road environment images;

[0134] The processor is used to execute the steps in the above-described map rendering method embodiments.

[0135] This invention addresses the issue of vehicle "floating" or misalignment by adjusting vector road surfaces using pose offset when the map remains unchanged after vehicle position updates. This ensures accurate alignment between the vehicle model and the vector road surface in the rendered image. This method effectively solves the problem of vehicle "floating" or misalignment, improving the accuracy of the rendering results. Using vector road surfaces instead of Bitmap images avoids the jagged edges caused by meshing in traditional Bitmap rendering. The use of vector graphics makes road edges smoother and the visual effect more natural. Compared to the complex image processing or point cloud segmentation algorithms in Bitmap rendering, adjusting and rendering using vector road surfaces reduces computation. This not only improves the system's real-time performance but also reduces the demand for computing resources. Dynamically adjusting the vector road surface to adapt to changes in vehicle position better handles situations with low map update frequency. This solution, by combining vehicle pose offset adjustment and vector road surface rendering, significantly improves the accuracy and efficiency of map rendering while reducing computational complexity.

[0136] This invention provides a computer-readable storage medium storing at least one executable instruction that, when executed on a map rendering device / apparatus, causes the map rendering device / apparatus to perform the map rendering method in any of the above method embodiments.

[0137] Specifically, the executable instructions can be used to cause the map rendering device / app to perform the following operations:

[0138] When the vehicle position is updated but the map is not updated, the current vehicle pose data is compared with the previous vehicle pose data to determine the vehicle's pose offset during the vehicle position update period.

[0139] Based on pose offset, the vector road surface in the map is adjusted;

[0140] Render the adjusted vector road surface.

[0141] In an alternative approach, the executable instructions cause the map rendering device / apparatus to perform the following operations:

[0142] Based on pose offset, the vector road surface in the map is translated and / or rotated.

[0143] In an alternative approach, the executable instructions cause the map rendering device / apparatus to perform the following operations:

[0144] The vehicle's anchor point is determined from the acquired prior road environment image. The anchor point represents the vehicle's reference point in the prior road environment image, which corresponds to the prior vehicle pose data in time.

[0145] Based on anchor points, road boundary pixels in prior road environment images are identified;

[0146] Starting from the identified road boundary pixels, a pre-defined exploration algorithm is used to search in the prior road environment image to identify the set of pixels of the road boundary in the prior road environment image;

[0147] A vector road surface is generated based on the set of pixels.

[0148] In an alternative approach, the executable instructions cause the map rendering device / apparatus to perform the following operations:

[0149] Based on the relative positional relationship between each pixel in the pixel set and the anchor point in the pixel coordinate system, the pixels in the pixel set are mapped to the vehicle coordinate system with the anchor point as the origin;

[0150] Curve fitting is performed on the set of pixels after coordinate transformation to generate the road boundary curve;

[0151] A vector road surface is generated based on the road boundary curve.

[0152] In an alternative approach, the executable instructions cause the map rendering device / apparatus to perform the following operations:

[0153] Generate a ray starting from the anchor point;

[0154] For rays, monitor their propagation path in prior road environment images and record the pixels along the path and their neighborhood information during propagation.

[0155] For a given pixel along a road, if the neighborhood information of that pixel meets a preset condition, then that pixel is identified as a road boundary pixel.

[0156] In an alternative approach, the executable instructions cause the map rendering device / apparatus to perform the following operations:

[0157] If the neighboring pixels of a pixel along the line include both passable and impassable pixels, then the pixel along the line is determined as a road boundary pixel.

[0158] In an alternative approach, the executable instructions cause the map rendering device / apparatus to perform the following operations:

[0159] The adjusted vector road surface is then triangulated.

[0160] Render the set of triangles obtained through triangulation.

[0161] This invention addresses the issue of vehicle "floating" or misalignment by adjusting vector road surfaces using pose offset when the map remains unchanged after vehicle position updates. This ensures accurate alignment between the vehicle model and the vector road surface in the rendered image. This method effectively solves the problem of vehicle "floating" or misalignment, improving the accuracy of the rendering results. Using vector road surfaces instead of Bitmap images avoids the jagged edges caused by meshing in traditional Bitmap rendering. The use of vector graphics makes road edges smoother and the visual effect more natural. Compared to the complex image processing or point cloud segmentation algorithms in Bitmap rendering, adjusting and rendering using vector road surfaces reduces computation. This not only improves the system's real-time performance but also reduces the demand for computing resources. Dynamically adjusting the vector road surface to adapt to changes in vehicle position better handles situations with low map update frequency. This solution, by combining vehicle pose offset adjustment and vector road surface rendering, significantly improves the accuracy and efficiency of map rendering while reducing computational complexity.

[0162] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Furthermore, the embodiments of this invention are not directed to any particular programming language.

[0163] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. Similarly, for the sake of brevity and to aid in understanding one or more aspects of the invention, in the description of exemplary embodiments of the invention above, various features of the embodiments are sometimes grouped together in a single embodiment, figure, or description thereof. The claims, which follow the detailed description, are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0164] Those skilled in the art will understand that the modules in the device of the embodiment can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiment can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components, except that at least some of such features and / or processes or units are mutually exclusive.

[0165] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A map rendering method, characterized in that, The method includes: When the vehicle position is updated but the map is not updated, the current vehicle pose data is compared with the previous vehicle pose data to determine the vehicle's pose offset during the vehicle position update period. Based on the pose offset, the vector road surface in the map is adjusted; Render the adjusted vector road surface.

2. The method according to claim 1, characterized in that, The adjustment of the vector road surface in the map based on the pose offset includes: Based on the pose offset, the vector road surface in the map is translated and / or rotated.

3. The method according to claim 1 or 2, characterized in that, The vector road surface is extracted in the following way: The vehicle's anchor point is determined from the acquired prior road environment image, the anchor point representing the vehicle's reference point in the prior road environment image, the prior road environment image corresponding to the prior vehicle pose data in time; Based on the anchor points, road boundary pixels in the prior road environment image are identified; Starting from the identified road boundary pixels, a preset exploration algorithm is used to search in the prior road environment image to identify the set of pixels of the road boundary in the prior road environment image; The vector road surface is generated based on the set of pixels.

4. The method according to claim 3, characterized in that, The process of generating the vector road surface based on the set of pixels includes: Based on the relative positional relationship between each pixel in the pixel set and the anchor point in the pixel coordinate system, the pixels in the pixel set are mapped to the vehicle coordinate system with the anchor point as the origin; Curve fitting is performed on the set of pixels after coordinate transformation to generate the road boundary curve; The vector road surface is generated based on the road boundary curve.

5. The method according to claim 3, characterized in that, The step of identifying road boundary pixels in the prior road environment image based on the anchor points includes: A ray is generated starting from the anchor point; For the ray, its propagation path in the prior road environment image is monitored, and the pixels along the path and their neighborhood information are recorded during the propagation process. For a given pixel along a road, if the neighborhood information of that pixel meets a preset condition, then that pixel is identified as a road boundary pixel.

6. The method according to claim 5, characterized in that, If the neighborhood information of the pixel along the line meets the preset conditions, then the pixel along the line is determined as a road boundary pixel, including: If the neighboring pixels of a pixel along the line include both passable and impassable pixels, then the pixel along the line is determined as a road boundary pixel.

7. The method according to claim 1, characterized in that, The rendering of the adjusted vector road surface includes: The adjusted vector road surface is then triangulated. Render the set of triangles obtained through triangulation.

8. A map rendering device, characterized in that, The device includes: The determination module is used to compare the current vehicle pose data with the previous vehicle pose data when the vehicle position is updated but the map is not updated, and to determine the vehicle's pose offset during the vehicle position update period. An adjustment module is used to adjust the vector road surface in the map based on the pose offset; The rendering module is used to render the adjusted vector road surface.

9. A map rendering device, characterized in that, include: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction that causes the processor to perform the operation of the map rendering method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The storage medium stores at least one executable instruction, which, when executed on a map rendering device / apparatus, causes the map rendering device / apparatus to perform the map rendering method as described in any one of claims 1-7.

Images