Transparent chassis implementation method, vehicle body integrated control module and vehicle

Abstract

The embodiment of the invention provides a transparent chassis implementation method, a vehicle body integrated control module and a vehicle, relates to the technical field of vehicle panoramic images, and can display the actual situation under a vehicle chassis and improve the driving safety. Meanwhile, compared with an existing transparent chassis implementation algorithm, the transparent chassis implementation method provided by the invention is relatively simple, and the computing power consumption of a CPU and a GPU can be reduced, so that the resource occupancy rate is reduced, and the real-time frame rate of the panoramic image is improved. The transparent chassis implementation method comprises the following steps: predicting a next frame driving position of a vehicle chassis in a current frame aerial view according to a current frame driving position of the vehicle chassis in the current frame aerial view; determining a next frame of texture image of the vehicle chassis according to the next frame of driving position of the vehicle chassis in the current frame of aerial view; and fusing the next frame of texture image with the next frame of aerial view to obtain the next frame of transparent chassis image.

Description

[Technical field]

[0001] The embodiments of the present application relate to the field of vehicle panoramic imaging technology, and in particular to a method for realizing a transparent chassis, a vehicle body integrated control module, and a vehicle. [Background technology]

[0002] Transparent chassis technology is a technology that uses cameras installed on the bottom of the vehicle to capture and display the ground conditions under the vehicle. The images captured by these cameras are transmitted to the display screen inside the vehicle, allowing the driver to see the actual situation under the vehicle chassis on the screen, as if the chassis is transparent. This technology helps to improve driving safety, especially in complex road conditions, such as when avoiding obstacles on the ground such as manhole covers, potholes, etc., or when driving off-road.

[0003] At present, the implementation algorithms of transparent chassis are mainly the world coordinate point search method and the ORB (ORiented Brief) feature point collection method. These methods are relatively complex in terms of technology, greatly consume the computing power of the CPU and GPU, increase resource utilization, and thus affect the real-time frame rate of panoramic images. [Summary of the invention]

[0004] The embodiments of the present application propose a transparent chassis implementation method, a body integrated control module and a vehicle, which relate to the field of vehicle panoramic imaging technology and can display the actual situation under the vehicle chassis to improve driving safety. At the same time, compared with the existing transparent chassis implementation algorithms, the transparent chassis implementation method provided by the present application is relatively simple, which can reduce the computing power consumption of the CPU and GPU, thereby reducing resource utilization and improving the real-time frame rate of the panoramic image.

[0005] In a first aspect, an embodiment of the present application provides a method for realizing a transparent chassis, the method comprising:

[0006] Predicting the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the current frame driving position of the vehicle chassis in the current frame bird's-eye view;

[0007] Determine a next frame texture image of the vehicle chassis according to a next frame driving position of the vehicle chassis in the current frame bird's-eye view;

[0008] The next frame of texture image is fused with the next frame of bird's-eye view image to obtain the next frame of transparent chassis image.

[0009] In an embodiment of the present application, the driving position of the vehicle chassis in the next frame of the current frame bird's-eye view is predicted based on the current frame driving position of the vehicle chassis in the current frame bird's-eye view; the next frame texture image of the vehicle chassis is determined based on the next frame driving position of the vehicle chassis in the current frame bird's-eye view; and then the next frame texture image is fused with the next frame bird's-eye view to obtain the next frame transparent chassis image. It can be seen that the method provided in this application can display the actual situation under the vehicle chassis and improve driving safety; at the same time, the method provided in this application does not need to accurately locate features on the map through world coordinates, nor does it need to combine focus detection algorithms and binary descriptors, so it is relatively simple, which can reduce the computing power consumption of the CPU and GPU, thereby reducing resource occupancy and improving the real-time frame rate of panoramic images.

[0010] Optionally, predicting the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the current frame driving position of the vehicle chassis in the current frame bird's-eye view includes:

[0011] Obtain the vehicle's steering wheel angle, driving speed, frame rate, and the vehicle chassis' current frame driving position in the current frame bird's-eye view;

[0012] Determine whether the steering wheel angle is 0;

[0013] If the steering wheel angle is 0, it is determined that the vehicle is traveling in a straight line;

[0014] If the vehicle is traveling in a straight line, the next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined according to the driving speed, the frame rate and the current frame driving position of the vehicle chassis in the current frame bird's-eye view.

[0015] In the embodiment of the present application, the steering wheel angle, driving speed, frame rate and the current frame driving position of the vehicle chassis in the current frame bird's-eye view are first obtained, and then the current driving trajectory of the vehicle is determined based on whether the steering wheel angle is 0. If it is a straight line, the next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined based on the above-obtained vehicle driving speed, frame rate and the current frame driving position of the vehicle chassis in the current frame bird's-eye view. It can be seen that in the embodiment of the present application, the steering wheel angle is first used for judgment, and then the corresponding data is obtained for calculation based on the judgment result, thereby reducing the acquisition of useless data and affecting the imaging time of the transparent chassis. Furthermore, when the steering wheel angle is 0, the vehicle is judged to be traveling in a straight line, and then the driving position of the vehicle chassis in the next frame in the current frame bird's-eye view is determined according to the vehicle's driving speed, frame rate and the current frame driving position of the vehicle chassis in the current frame bird's-eye view. A method for determining the next frame driving position of the vehicle chassis in the current frame bird's-eye view when the vehicle is traveling in a straight line is provided. The method only requires three input data, namely, driving speed, frame rate and current frame driving position of the vehicle chassis in the current frame bird's-eye view. The method is simple and can reduce the computing power consumption of the CPU and GPU, thereby reducing resource utilization and improving the real-time frame rate of the panoramic image.

[0016] Optionally, the driving position is represented by pixel coordinates, and determining the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the driving speed, the frame rate, and the current frame driving position of the vehicle chassis in the current frame bird's-eye view includes:

[0017] Determine the current frame pixel coordinates of the vehicle chassis in the current frame bird's-eye view according to the current frame driving position of the vehicle chassis in the current frame bird's-eye view, and determine the time interval between each frame according to the frame rate;

[0018] Determine the travel distance according to the time interval between each frame and the travel speed;

[0019] The horizontal coordinate of the current frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view is used as the horizontal coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view, and the vertical coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view is used as the sum of the vertical coordinate of the current frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view and the driving distance;

[0020] The next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined according to the horizontal coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view and the vertical coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view.

[0021] In the embodiment of the present application, the driving position is represented by pixel coordinates, so whether it is the known driving position of the vehicle chassis in the current frame bird's-eye view or the driving position of the vehicle chassis in the next frame in the current frame bird's-eye view that needs to be solved, it can be represented by pixel points. Since the vehicle is traveling in a straight line, the horizontal coordinate of the vehicle chassis remains unchanged, and the horizontal coordinate of the current frame pixel coordinate of the vehicle chassis in the current frame bird's-eye view is directly used as the horizontal coordinate of the next frame pixel coordinate of the vehicle chassis in the current frame bird's-eye view. Since the vehicle is traveling in a straight line, the vertical coordinate of the vehicle chassis will change, and it is necessary to first calculate the displacement distance of the vehicle. The displacement distance is determined according to the time interval between each frame and the driving speed. Therefore, the sum of the vertical coordinate of the current frame pixel coordinate of the vehicle chassis in the current frame bird's-eye view and the driving distance can be used as the vertical coordinate of the next frame pixel coordinate of the vehicle chassis in the current frame bird's-eye view. It can be seen that the embodiment of the present application provides a specific method for determining the driving position of the vehicle chassis in the next frame in the bird's-eye view of the current frame. The coordinates used are two-dimensional pixel point coordinates rather than three-dimensional world coordinates. The amount of calculation is small, which can reduce the computing power consumption of the CPU and GPU, thereby reducing resource utilization and improving the real-time frame rate of the panoramic image.

[0022] Optionally, the method further includes:

[0023] If the steering wheel angle is not 0, it is determined that the vehicle is turning;

[0024] If the vehicle is turning, obtaining the steering ratio and wheelbase of the vehicle;

[0025] The next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined based on the steering wheel angle, the steering ratio, the wheelbase, the frame rate, the driving speed and the current frame driving position of the vehicle chassis in the current frame bird's-eye view.

[0026] In the embodiment of the present application, if the steering wheel angle is not 0, it can be determined that the vehicle is turning. When turning, it is not enough to only know the steering wheel angle, driving speed, frame rate and the current frame driving position of the vehicle chassis in the current frame bird's-eye view. Therefore, it is necessary to further obtain the steering ratio and wheelbase of the vehicle, and then determine the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the steering wheel angle, steering ratio, wheelbase, frame rate, driving speed and the current frame driving position of the vehicle chassis in the current frame bird's-eye view. It can be seen that the embodiment of the present application provides a method for determining the next frame driving position of the vehicle chassis in the current frame bird's-eye view when the vehicle is turning, and the method only requires input data such as the steering wheel angle, steering ratio, wheelbase, frame rate, driving speed and the current frame driving position of the vehicle chassis in the current frame bird's-eye view. The method is simple and can reduce the computing power consumption of the CPU and GPU, thereby reducing resource occupancy and improving the real-time frame rate of the panoramic image.

[0027] Optionally, determining the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the steering wheel angle, the steering ratio, the wheelbase, the frame rate, the driving speed, and the current frame driving position of the vehicle chassis in the current frame bird's-eye view includes:

[0028] determining a wheel angle according to the steering wheel angle and the steering ratio;

[0029] Determining a wheel rotation radius according to the wheel rotation angle and the wheelbase;

[0030] determining a time interval between each frame according to the frame rate;

[0031] Determine the front deflection angle according to the wheel rotation radius, the driving speed and the time interval between each frame;

[0032] Determine the wheel displacement according to the vehicle head deflection angle and the wheel rotation radius, and determine the coordinate rotation matrix according to the vehicle head deflection angle;

[0033] Determine a coordinate translation matrix according to the wheel displacement, the coordinate rotation matrix and the current frame driving position of the vehicle chassis in the current frame bird's-eye view;

[0034] The next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined according to the coordinate rotation matrix, the coordinate translation matrix and the current frame driving position of the vehicle chassis in the current frame bird's-eye view.

[0035] In the embodiment of the present application, the wheel angle is first determined according to the steering wheel angle and the steering ratio, and then the wheel rotation radius is determined according to the wheel angle and the wheelbase, and then the front deflection angle can be determined according to the wheel rotation radius, the driving speed and the time interval between each frame; after knowing the front deflection angle, the coordinate rotation matrix can be directly determined, and the wheel displacement can also be determined according to the front deflection angle and the wheel rotation radius, and then the coordinate translation matrix is ​​determined according to the wheel displacement, the coordinate rotation matrix and the current frame driving position of the vehicle chassis in the current frame bird's-eye view; the coordinate transformation can be realized by the coordinate rotation matrix and the coordinate translation matrix, so that the coordinates of the current frame driving position of the vehicle chassis in the current frame bird's-eye view are transformed into the coordinates of the next frame driving position of the vehicle chassis in the current frame bird's-eye view, that is, the determination of the next frame driving position of the vehicle chassis in the current frame bird's-eye view is realized. It can be seen that the embodiment of the present application provides a specific method for determining the next frame driving position of the vehicle chassis in the current frame bird's-eye view when the vehicle is turning. The method is simple and can reduce the computing power consumption of the CPU and GPU, thereby reducing the resource occupancy rate and improving the real-time frame rate of the panoramic image.

[0036] Optionally, the driving position is represented by Ackerman coordinates, and determining the next frame texture image of the vehicle chassis according to the next frame driving position of the vehicle chassis in the current frame bird's-eye view includes:

[0037] Determine the Ackerman coordinates of the next frame according to the next frame driving position of the vehicle chassis in the current frame bird's-eye view;

[0038] Convert the next frame Ackerman coordinates into texture coordinates;

[0039] The texture of the current frame bird's-eye view is sampled according to the texture coordinates to obtain a next frame texture image of the vehicle chassis.

[0040] In the embodiment of the present application, the driving position is represented by Ackerman coordinates, and the driving position of the vehicle chassis in the next frame in the current frame bird's-eye view can be represented by Ackerman coordinates, and then the Ackerman coordinates are converted into texture coordinates, and the texture sampling of the current frame bird's-eye view is performed according to the texture coordinates to obtain the next frame texture image of the vehicle chassis. It can be seen that the embodiment of the present application provides a method for determining a texture image, and texture sampling can be achieved through coordinate transformation to obtain the next frame texture image of the vehicle chassis. The method is simple and can reduce the computing power consumption of the CPU and GPU, thereby reducing resource occupancy and improving the real-time frame rate of the panoramic image.

[0041] Optionally, converting the next frame Ackerman coordinates into texture coordinates includes:

[0042] Obtaining the width and height of the bird's-eye view of the current frame, and determining the origin of the coordinate axis;

[0043] Determine the abscissa of the texture coordinate according to the ordinate of the Ackerman coordinate of the next frame, the abscissa of the origin of the coordinate axis and the width of the bird's-eye view of the current frame, and determine the ordinate of the texture coordinate according to the abscissa of the Ackerman coordinate of the next frame, the ordinate of the origin of the coordinate axis and the height of the bird's-eye view of the current frame;

[0044] The texture coordinate is determined according to the abscissa and the ordinate of the texture coordinate.

[0045] In the embodiment of the present application, the abscissa of the texture coordinates is determined according to the ordinate of the Ackerman coordinates of the next frame, the abscissa of the origin of the coordinate axis, and the width of the bird's-eye view of the current frame, and the ordinate of the texture coordinates is determined according to the abscissa of the Ackerman coordinates of the next frame, the ordinate of the origin of the coordinate axis, and the height of the bird's-eye view of the current frame, thereby realizing the conversion of the Ackerman coordinates into the texture coordinates. It can be seen that the present application provides a specific method for converting the Ackerman coordinates into the texture coordinates, which has a small amount of calculation, is simple, can reduce the computing power consumption of the CPU and GPU, thereby reducing the resource occupancy rate and improving the real-time frame rate of the panoramic image.

[0046] In a second aspect, an embodiment of the present application provides a transparent chassis implementation device, the device comprising:

[0047] A driving position determination unit, used for predicting the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the current frame driving position of the vehicle chassis in the current frame bird's-eye view;

[0048] A texture image determination unit, configured to determine a next frame texture image of the vehicle chassis according to a next frame driving position of the vehicle chassis in the current frame bird's-eye view;

[0049] The image fusion unit is used to fuse the next frame of texture image with the next frame of bird's-eye view to obtain the next frame of transparent chassis image.

[0050] Optionally, in the aspect of predicting the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the current frame driving position of the vehicle chassis in the current frame bird's-eye view, the driving position determination unit is specifically used to:

[0051] Obtain the vehicle's steering wheel angle, driving speed, frame rate, and the vehicle chassis' current frame driving position in the current frame bird's-eye view;

[0052] Determine whether the steering wheel angle is 0;

[0053] If the steering wheel angle is 0, it is determined that the vehicle is traveling in a straight line;

[0054] If the vehicle is traveling in a straight line, the next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined according to the driving speed, the frame rate and the current frame driving position of the vehicle chassis in the current frame bird's-eye view.

[0055] Optionally, the driving position is represented by pixel coordinates, and in determining the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the driving speed, the frame rate, and the current frame driving position of the vehicle chassis in the current frame bird's-eye view, the driving position determining unit is specifically used to:

[0056] Determine the current frame pixel coordinates of the vehicle chassis in the current frame bird's-eye view according to the current frame driving position of the vehicle chassis in the current frame bird's-eye view, and determine the time interval between each frame according to the frame rate;

[0057] Determine the travel distance according to the time interval between each frame and the travel speed;

[0058] The horizontal coordinate of the current frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view is used as the horizontal coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view, and the vertical coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view is used as the sum of the vertical coordinate of the current frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view and the driving distance;

[0059] The next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined according to the horizontal coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view and the vertical coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view.

[0060] Optionally, the driving position determination unit is further specifically used for:

[0061] If the steering wheel angle is not 0, it is determined that the vehicle is turning;

[0062] If the vehicle is turning, obtaining the steering ratio and wheelbase of the vehicle;

[0063] The next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined based on the steering wheel angle, the steering ratio, the wheelbase, the frame rate, the driving speed and the current frame driving position of the vehicle chassis in the current frame bird's-eye view.

[0064] Optionally, in determining the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the steering wheel angle, the steering ratio, the wheelbase, the frame rate, the driving speed and the current frame driving position of the vehicle chassis in the current frame bird's-eye view, the driving position determining unit is specifically used to:

[0065] determining a wheel angle according to the steering wheel angle and the steering ratio;

[0066] Determining a wheel rotation radius according to the wheel rotation angle and the wheelbase;

[0067] determining a time interval between each frame according to the frame rate;

[0068] Determine the front deflection angle according to the wheel rotation radius, the driving speed and the time interval between each frame;

[0069] Determine the wheel displacement according to the vehicle head deflection angle and the wheel rotation radius, and determine the coordinate rotation matrix according to the vehicle head deflection angle;

[0070] Determine a coordinate translation matrix according to the wheel displacement, the coordinate rotation matrix and the current frame driving position of the vehicle chassis in the current frame bird's-eye view;

[0071] The next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined according to the coordinate rotation matrix, the coordinate translation matrix and the current frame driving position of the vehicle chassis in the current frame bird's-eye view.

[0072] Optionally, the driving position is represented by Ackerman coordinates, and in determining the next frame texture image of the vehicle chassis according to the next frame driving position of the vehicle chassis in the current frame bird's-eye view, the texture image determining unit is specifically used to:

[0073] Determine the Ackerman coordinates of the next frame according to the next frame driving position of the vehicle chassis in the current frame bird's-eye view;

[0074] Convert the next frame Ackerman coordinates into texture coordinates;

[0075] The texture of the current frame bird's-eye view is sampled according to the texture coordinates to obtain a next frame texture image of the vehicle chassis.

[0076] Optionally, in the aspect of converting the Ackerman coordinates of the next frame into texture coordinates, the texture image determination unit is specifically used for:

[0077] Obtaining the width and height of the bird's-eye view of the current frame, and determining the origin of the coordinate axis;

[0078] Determine the abscissa of the texture coordinate according to the ordinate of the Ackerman coordinate of the next frame, the abscissa of the origin of the coordinate axis and the width of the bird's-eye view of the current frame, and determine the ordinate of the texture coordinate according to the abscissa of the Ackerman coordinate of the next frame, the ordinate of the origin of the coordinate axis and the height of the bird's-eye view of the current frame;

[0079] The texture coordinate is determined according to the abscissa and the ordinate of the texture coordinate.

[0080] In a third aspect, an embodiment of the present application provides a body-integrated control module, which comprises a memory for storing computer program instructions and a processor for executing program instructions, wherein when the computer program instructions are executed by the processor, the body-integrated control module is triggered to execute the steps of the method described in any embodiment of the first aspect.

[0081] In a fourth aspect, an embodiment of the present application provides a vehicle, comprising a body integrated control module in an embodiment of the third aspect.

[0082] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store computer instructions, and when the computer is running, the computer enables the computer to execute the steps of the method described in any embodiment of the first aspect.

[0083] It should be understood that the second to fifth aspects of the embodiments of the present application are consistent with the technical solutions of the first aspect of the embodiments of the present application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation methods are similar and will not be repeated here.

Brief Description of the Drawings

[0084] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0085] Figure 1 A schematic diagram of a process for implementing a transparent chassis provided in an embodiment of the present application;

[0086] Figure 2 A simplified schematic diagram of a bird's-eye view of a current frame provided in an embodiment of the present application;

[0087] Figure 3 A schematic diagram of a flow chart of a method for predicting the next frame driving position provided in an embodiment of the present application;

[0088] Figure 4A schematic diagram of a flow chart of another method for predicting the next frame driving position provided in an embodiment of the present application;

[0089] Figure 5 A schematic diagram of a flow chart of another method for predicting the next frame driving position provided in an embodiment of the present application;

[0090] Figure 6 A schematic diagram of a flow chart of another method for predicting the next frame driving position provided in an embodiment of the present application;

[0091] Figure 7 A schematic diagram of a flow chart of a method for determining a next frame of texture image provided in an embodiment of the present application;

[0092] Figure 8 A schematic diagram of a coordinate transformation method provided in an embodiment of the present application;

[0093] Fig. 9 A schematic diagram of the structure of a transparent chassis implementation device provided in an embodiment of the present application;

[0094] Fig.10 A schematic diagram of the structure of a vehicle body integrated control module provided in an embodiment of the present application;

[0095] Fig.11 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. [Specific implementation method]

[0096] In order to better understand the technical solution of this specification, the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0097] It should be clear that the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0098] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit this specification. The singular forms of "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0099] Transparent chassis technology is a technology that uses cameras installed on the bottom of the vehicle to capture and display the ground conditions under the vehicle. The images captured by these cameras are transmitted to the display screen inside the vehicle, allowing the driver to see the actual situation under the vehicle chassis on the screen, as if the chassis is transparent. This technology helps to improve driving safety, especially in complex road conditions, such as when avoiding obstacles on the ground such as manhole covers, potholes, etc., or when driving off-road.

[0100] At present, the implementation algorithms of transparent chassis are mainly the world coordinate point search method and the ORB (ORiented Brief) feature point collection method. These methods are relatively complex in terms of technology, greatly consume the computing power of the CPU and GPU, increase resource utilization, and thus affect the real-time frame rate of panoramic images.

[0101] In view of this, an embodiment of the present application provides a method for realizing a transparent chassis, in which the driving position of the vehicle chassis in the next frame of the current frame bird's-eye view is predicted based on the current frame driving position of the vehicle chassis in the current frame bird's-eye view; the next frame texture image of the vehicle chassis is determined based on the next frame driving position of the vehicle chassis in the current frame bird's-eye view; and then the next frame texture image is fused with the next frame bird's-eye view to obtain the next frame transparent chassis image. It can be seen that the method provided in the present application can display the actual situation under the vehicle chassis and improve driving safety; at the same time, the method provided in the present application does not need to accurately locate features on the map through world coordinates, nor does it need to combine focus detection algorithms and binary descriptors, so it is relatively simple, which can reduce the computing power consumption of the CPU and GPU, thereby reducing resource occupancy and improving the real-time frame rate of panoramic images.

[0102] The technical solution protected by the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0103] See also Figure 1 , is a flow chart of a method for implementing a transparent chassis provided in an embodiment of the present application. The flow of the method is described as follows:

[0104] Step 101: predicting the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the current frame driving position of the vehicle chassis in the current frame bird's-eye view.

[0105] A bird's-eye view is a map or image drawn from a high place looking down, usually used to show the overall layout and structure of buildings, cities, landscapes, etc. This perspective can help people better understand spatial relationships and geographical distribution. The bird's-eye view in this application refers to a vehicle image drawn from a high place looking down.

[0106] In the embodiment of the present application, the vehicle chassis can be approximated as a rectangle, and the current frame driving position of the vehicle chassis in the current frame bird's-eye view or the next frame driving position of the vehicle chassis in the current frame bird's-eye view can establish a coordinate system and be represented by coordinates, and its driving position can be represented by one point or multiple points. For example, the driving position is represented by the position of one of the most edge points, and then the positions of the other three most edge points are obtained based on the total length and total width of the vehicle body. For example, it can also be represented by the positions of four tires, and the positions of the four tires can be given directly, or the position of one of the tires can be given, and the other three can be obtained through the wheelbase and track.

[0107] For example, Figure 2 As shown, Figure 2 A simplified schematic diagram of a current frame bird's-eye view provided for an embodiment of the present application. In the figure, the vehicle chassis is represented by a rectangle. At the moment corresponding to the current frame, the current frame driving position of the vehicle chassis is in the center of the current frame bird's-eye view. After a time interval to the next frame, the vehicle drives to another position, and the angle between the vehicle chassis and the original driving position is θ. Both the initial position (the current frame driving position of the vehicle chassis in the current frame bird's-eye view) and the position after driving (the next frame driving position of the vehicle chassis in the current frame bird's-eye view) are represented in the current frame.

[0108] Step 102: Determine a next frame texture image of the vehicle chassis according to the next frame driving position of the vehicle chassis in the current frame bird's-eye view.

[0109] Among them, texture images are images used to represent the surface details of objects, and are often used in computer graphics, game development, architectural design and other fields. Texture images can increase the realism and visual effects of objects and make virtual scenes more realistic.

[0110] Exemplarily, the area covered by the vehicle chassis can be determined based on the next frame driving position of the vehicle chassis in the current frame bird's-eye view, and then the image of the area is cut out in the current bird's-eye view to obtain the next frame texture image of the vehicle chassis.

[0111] Step 103: Fusing the next frame of texture image with the next frame of bird's-eye view image to obtain the next frame of transparent chassis image.

[0112] Exemplarily, the next frame of the bird's-eye view can be acquired through the vehicle's camera module, and then the next frame of the texture image can be dragged onto the next frame of the bird's-eye view, its size and position can be adjusted, and then the layer blending mode can be used to blend the texture image.

[0113] Exemplarily, point rendering can also be performed through OpenGL, as follows: create and bind a buffer object FBO, bind texture texture, and render the current frame bird's-eye view into FBO. Create and bind a buffer object FBO1, bind texture texture1, use the current frame bird's-eye view texture as the texture of the input shader, find out the coordinate position of the chassis of the next frame through matrix transformation, render the texture point to FBO1, and obtain the transparent chassis image texture1 of the next frame. Bind FBO, use texture and texture1 as texture inputs to the shader, perform edge fusion algorithm transition on the two texture objects, render to FBO, and overwrite the previous texture texture. Render the current texture to the screen to obtain the target frame's surround transparent chassis image.

[0114] Exemplarily, the time interval between the current frame and the next frame can be determined according to the program execution time corresponding to the method. If the program execution time is faster, the number of executions per second is greater, that is, the frame rate is higher. Since the embodiment of the present application is simpler than the existing world coordinate point finding method and ORB feature point acquisition method, the execution time is faster, thereby improving the frame rate.

[0115] In an embodiment of the present application, the driving position of the vehicle chassis in the next frame of the current frame bird's-eye view is predicted based on the current frame driving position of the vehicle chassis in the current frame bird's-eye view; the next frame texture image of the vehicle chassis is determined based on the next frame driving position of the vehicle chassis in the current frame bird's-eye view; and then the next frame texture image is fused with the next frame bird's-eye view to obtain the next frame transparent chassis image. It can be seen that the method provided in this application can display the actual situation under the vehicle chassis and improve driving safety; at the same time, the method provided in this application does not need to accurately locate features on the map through world coordinates, nor does it need to combine focus detection algorithms and binary descriptors, so it is relatively simple, which can reduce the computing power consumption of the CPU and GPU, thereby reducing resource occupancy and improving the real-time frame rate of panoramic images.

[0116] In terms of predicting the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the current frame driving position of the vehicle chassis in the current frame bird's-eye view, the present application provides a method for predicting the next frame driving position. Figure 3 , is a flow chart of a method for predicting the next frame driving position provided in an embodiment of the present application. The flow of the method is described as follows:

[0117] Step 1011: Obtain the steering wheel angle, driving speed, frame rate and current frame driving position of the vehicle chassis in the current frame bird's-eye view;

[0118] Step 1012: Determine whether the steering wheel angle is 0;

[0119] Step 1013: If the steering wheel angle is 0, it is determined that the vehicle is traveling in a straight line;

[0120] Step 1014: If the vehicle is traveling in a straight line, the next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined based on the driving speed, the frame rate and the current frame driving position of the vehicle chassis in the current frame bird's-eye view.

[0121] The steering wheel angle refers to the angle at which the driver turns the steering wheel. The steering wheel angle, driving speed, and frame rate can be obtained through the vehicle sensor or read through the OBD port on the vehicle. In general vehicle-mounted panoramic images, the vehicle is located in the center of the bird's-eye view. Therefore, if a point of the vehicle is taken to represent the current frame driving position setting of the vehicle chassis in the current frame bird's-eye view, the point can be the center point of the vehicle, the center point of the tire of the car, or the center point of the line connecting the two rear wheels. The remaining points of the vehicle chassis can be represented according to the coordinates of the point.

[0122] In the embodiment of the present application, the steering wheel angle, driving speed, frame rate and the current frame driving position of the vehicle chassis in the current frame bird's-eye view are first obtained, and then the current driving trajectory of the vehicle is determined based on whether the steering wheel angle is 0. If it is a straight line, the next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined based on the above-obtained vehicle driving speed, frame rate and the current frame driving position of the vehicle chassis in the current frame bird's-eye view. It can be seen that in the embodiment of the present application, the steering wheel angle is first used for judgment, and then the corresponding data is obtained for calculation based on the judgment result, thereby reducing the acquisition of useless data and affecting the imaging time of the transparent chassis. Furthermore, when the steering wheel angle is 0, the vehicle is judged to be traveling in a straight line, and then the driving position of the vehicle chassis in the next frame in the current frame bird's-eye view is determined according to the vehicle's driving speed, frame rate and the current frame driving position of the vehicle chassis in the current frame bird's-eye view. A method for determining the next frame driving position of the vehicle chassis in the current frame bird's-eye view when the vehicle is traveling in a straight line is provided. The method only requires three input data, namely, driving speed, frame rate and current frame driving position of the vehicle chassis in the current frame bird's-eye view. The method is simple and can reduce the computing power consumption of the CPU and GPU, thereby reducing resource utilization and improving the real-time frame rate of the panoramic image.

[0123] See also Figure 4 , which is a flow chart of another method for predicting the next frame driving position provided by an embodiment of the present application. After executing step 1012, steps 1016 to 1017 may also be executed:

[0124] Step 1015: If the steering wheel angle is not 0, it is determined that the vehicle is turning;

[0125] Step 1016: If the vehicle is turning, obtaining the steering ratio and wheelbase of the vehicle;

[0126] Step 1017: Determine the next frame driving position of the vehicle chassis in the current frame bird's-eye view based on the steering wheel angle, the steering ratio, the wheelbase, the frame rate, the driving speed and the current frame driving position of the vehicle chassis in the current frame bird's-eye view.

[0127] Among them, the steering ratio refers to the proportional relationship between the steering wheel angle and the front wheel angle, which is one of the key parameters to measure the sensitivity and responsiveness of the vehicle's steering system. The wheelbase refers to the distance between the center points of the front and rear axles of the vehicle, which is one of the important parameters to measure the size and performance of the vehicle.

[0128] In the embodiment of the present application, if the steering wheel angle is not 0, it can be determined that the vehicle is turning. When turning, it is not enough to only know the steering wheel angle, driving speed, frame rate and the current frame driving position of the vehicle chassis in the current frame bird's-eye view. Therefore, it is necessary to further obtain the steering ratio and wheelbase of the vehicle, and then determine the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the steering wheel angle, steering ratio, wheelbase, frame rate, driving speed and the current frame driving position of the vehicle chassis in the current frame bird's-eye view. It can be seen that the embodiment of the present application provides a method for determining the next frame driving position of the vehicle chassis in the current frame bird's-eye view when the vehicle is turning, and the method only requires input data such as the steering wheel angle, steering ratio, wheelbase, frame rate, driving speed and the current frame driving position of the vehicle chassis in the current frame bird's-eye view. The method is simple and can reduce the computing power consumption of the CPU and GPU, thereby reducing resource occupancy and improving the real-time frame rate of the panoramic image.

[0129] In terms of determining the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the driving speed, the frame rate and the current frame driving position of the vehicle chassis in the current frame bird's-eye view, the present application provides another method for predicting the next frame driving position, wherein the driving position is represented by pixel coordinates. Figure 5 , is a flow chart of another method for predicting the next frame driving position provided by an embodiment of the present application. The flow chart of the method is described as follows:

[0130] Step 1014a: determining the current frame pixel coordinates of the vehicle chassis in the current frame bird's-eye view according to the current frame driving position of the vehicle chassis in the current frame bird's-eye view, and determining the time interval between each frame according to the frame rate;

[0131] Step 1014b: determining the travel distance according to the time interval between each frame and the travel speed;

[0132] Step 1014c: using the horizontal coordinate of the current frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view as the horizontal coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view, and using the sum of the vertical coordinate of the current frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view and the driving distance as the vertical coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view;

[0133] Step 1014d: Determine the next frame driving position of the vehicle chassis in the current frame bird's-eye view based on the horizontal coordinate of the next frame pixel point coordinates of the vehicle chassis in the current frame bird's-eye view and the vertical coordinate of the next frame pixel point coordinates of the vehicle chassis in the current frame bird's-eye view.

[0134] Exemplarily, the current frame driving position of the vehicle chassis in the current frame bird's-eye view is represented by pixel coordinates N0=(x0, y0), and the frame rate is f, then the time interval between each frame is t=1 / f, and the driving distance is s=vt=v / f, where v is the driving speed. The next frame driving position of the vehicle chassis in the current frame bird's-eye view is represented by pixel coordinates N1=(x1, y1), then x1=x0, y1=y0+v / f. It should be noted that the direction of the speed can be determined according to the current gear position. If it is the forward gear (D gear), v is a positive value, if it is the reverse gear (R gear), v is a negative value, and if it is the parking gear (P gear) or neutral gear (N gear), v=0.

[0135] In the embodiment of the present application, the driving position is represented by pixel coordinates, so whether it is the known driving position of the vehicle chassis in the current frame bird's-eye view or the driving position of the vehicle chassis in the next frame in the current frame bird's-eye view that needs to be solved, it can be represented by pixel points. Since the vehicle is traveling in a straight line, the horizontal coordinate of the vehicle chassis remains unchanged, and the horizontal coordinate of the current frame pixel coordinate of the vehicle chassis in the current frame bird's-eye view is directly used as the horizontal coordinate of the next frame pixel coordinate of the vehicle chassis in the current frame bird's-eye view. Since the vehicle is traveling in a straight line, the vertical coordinate of the vehicle chassis will change, and it is necessary to first calculate the displacement distance of the vehicle. The displacement distance is determined according to the time interval between each frame and the driving speed. Therefore, the sum of the vertical coordinate of the current frame pixel coordinate of the vehicle chassis in the current frame bird's-eye view and the driving distance can be used as the vertical coordinate of the next frame pixel coordinate of the vehicle chassis in the current frame bird's-eye view. It can be seen that the embodiment of the present application provides a specific method for determining the driving position of the vehicle chassis in the next frame in the bird's-eye view of the current frame. The coordinates used are two-dimensional pixel point coordinates rather than three-dimensional world coordinates. The amount of calculation is small, which can reduce the computing power consumption of the CPU and GPU, thereby reducing resource utilization and improving the real-time frame rate of the panoramic image.

[0136] In terms of determining the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the steering wheel angle, the steering ratio, the wheelbase, the frame rate, the driving speed and the current frame driving position of the vehicle chassis in the current frame bird's-eye view, the present application provides another method for predicting the next frame driving position. Figure 6 , is a flow chart of another method for predicting the next frame driving position provided by an embodiment of the present application. The flow chart of the method is described as follows:

[0137] Step 1017a: determining a wheel angle according to the steering wheel angle and the steering ratio;

[0138] Step 1017b: determining a wheel rotation radius according to the wheel rotation angle and the wheelbase;

[0139] Step 1017c: determining the time interval between each frame according to the frame rate;

[0140] Step 1017d: determining the vehicle head deflection angle according to the wheel rotation radius, the driving speed and the time interval between each frame;

[0141] Step 1017e: determining the wheel displacement according to the vehicle head deflection angle and the wheel rotation radius, and determining the coordinate rotation matrix according to the vehicle head deflection angle;

[0142] Step 1017f: determining a coordinate translation matrix according to the wheel displacement, the coordinate rotation matrix and the current frame driving position of the vehicle chassis in the current frame bird's-eye view;

[0143] Step 1017g: Determine the next frame driving position of the vehicle chassis in the current frame bird's-eye view based on the coordinate rotation matrix, the coordinate translation matrix and the current frame driving position of the vehicle chassis in the current frame bird's-eye view.

[0144] Exemplarily, the steering wheel angle is represented by α, the steering ratio is represented by i, the wheel angle is represented by β, then β = α / i. The wheelbase is represented by L, the wheel rotation radius is represented by R, then R = L / tan(β). The front deviation angle is represented by θ, then θ = v / fR, f is the frame rate. The wheel displacement includes horizontal displacement ΔHx and vertical displacement ΔHy, horizontal displacement ΔHx = R·sinθ, vertical displacement ΔHy = R–R·cosθ, displacement vector ΔH = (ΔHx, ΔHy) = (R·sinθ, R–R·cosθ).

[0145] Exemplarily, the coordinate rotation matrix is ​​represented by Pr, and the coordinate translation matrix is ​​represented by Pt, Pr = [cosθ, -sinθ, sinθ, cosθ], Pt = H + ΔH - H * Pr, where ΔH = [Rsinθ, R - Rcosθ], H is the pixel coordinates corresponding to the current frame driving position of the vehicle chassis in the current frame bird's-eye view. It should be noted that the sign of θ is determined according to the gear position. If it is D gear, θ is positive, and if it is R gear, θ is negative.

[0146] Exemplarily, F1=F0*Pr+Pt, wherein F0 is the coordinate corresponding to the current frame driving position of the vehicle chassis in the current frame bird's-eye view, and F1 is the coordinate corresponding to the next frame driving position of the vehicle chassis in the current frame bird's-eye view.

[0147] In the embodiment of the present application, the wheel angle is first determined according to the steering wheel angle and the steering ratio, and then the wheel rotation radius is determined according to the wheel angle and the wheelbase, and then the front deflection angle can be determined according to the wheel rotation radius, the driving speed and the time interval between each frame; after knowing the front deflection angle, the coordinate rotation matrix can be directly determined, and the wheel displacement can also be determined according to the front deflection angle and the wheel rotation radius, and then the coordinate translation matrix is ​​determined according to the wheel displacement, the coordinate rotation matrix and the current frame driving position of the vehicle chassis in the current frame bird's-eye view; the coordinate transformation can be realized by the coordinate rotation matrix and the coordinate translation matrix, so that the coordinates of the current frame driving position of the vehicle chassis in the current frame bird's-eye view are transformed into the coordinates of the next frame driving position of the vehicle chassis in the current frame bird's-eye view, that is, the determination of the next frame driving position of the vehicle chassis in the current frame bird's-eye view is realized. It can be seen that the embodiment of the present application provides a specific method for determining the next frame driving position of the vehicle chassis in the current frame bird's-eye view when the vehicle is turning. The method is simple and can reduce the computing power consumption of the CPU and GPU, thereby reducing the resource occupancy rate and improving the real-time frame rate of the panoramic image.

[0148] In the aspect of determining the next frame texture image of the vehicle chassis according to the next frame driving position of the vehicle chassis in the current frame bird's-eye view, the present application provides a method for determining the next frame texture image, wherein the driving position is represented by Ackerman coordinates. Figure 7 , is a flow chart of a method for determining a next frame texture image provided by an embodiment of the present application. The flow of the method is described as follows:

[0149] Step 1021: determining the Ackerman coordinates of the next frame according to the driving position of the vehicle chassis in the next frame in the bird's-eye view of the current frame;

[0150] Step 1022: converting the next frame Ackerman coordinates into texture coordinates;

[0151] Step 1023: Perform texture sampling on the current frame bird's-eye view according to the texture coordinates to obtain a next frame texture image of the vehicle chassis.

[0152] Among them, the Ackermann Coordinate System is not a standard coordinate system, but a concept related to Ackermann steering geometry, which is mainly used to describe the position and motion relationship of various components of the vehicle during the steering process. In the Ackermann coordinate system, the center of mass of the vehicle or a fixed reference point is usually selected as the origin of the coordinate system. The X-axis is along the longitudinal direction of the vehicle, and the positive direction points to the front of the vehicle. The Y-axis is along the lateral direction of the vehicle, and the positive direction points to the left side of the vehicle. The Z-axis is perpendicular to the ground, and the positive direction points to the sky.

[0153] Among them, texture coordinates are the key parameters used to map texture images to the surface of 3D models. Texture coordinates can be used to precisely control how the texture image is covered on each vertex of the model, thereby achieving detailed surface effects. Texture coordinates (also called UV coordinates) are points in a two-dimensional coordinate system, usually represented by (u, v). Among them: u is the horizontal coordinate, usually in the range of [0, 1]; v is the vertical coordinate, usually in the range of [0, 1].

[0154] In the embodiment of the present application, the driving position is represented by Ackerman coordinates, and the driving position of the vehicle chassis in the next frame in the current frame bird's-eye view can be represented by Ackerman coordinates, and then the Ackerman coordinates are converted into texture coordinates, and the texture sampling of the current frame bird's-eye view is performed according to the texture coordinates to obtain the next frame texture image of the vehicle chassis. It can be seen that the embodiment of the present application provides a method for determining a texture image, and texture sampling can be achieved through coordinate transformation to obtain the next frame texture image of the vehicle chassis. The method is simple and can reduce the computing power consumption of the CPU and GPU, thereby reducing resource occupancy and improving the real-time frame rate of the panoramic image.

[0155] In terms of converting the Ackerman coordinates of the next frame into texture coordinates, the present application provides a coordinate conversion method. Figure 8 , is a flow chart of a coordinate transformation method provided in an embodiment of the present application. The flow chart of the method is described as follows:

[0156] Step 1022a: Obtain the width and height of the current frame bird's-eye view, and determine the origin of the coordinate axis;

[0157] Step 1022b: determining the abscissa of the texture coordinate according to the ordinate of the Ackerman coordinate of the next frame, the abscissa of the origin of the coordinate axis and the width of the bird's-eye view of the current frame, and determining the ordinate of the texture coordinate according to the abscissa of the Ackerman coordinate of the next frame, the ordinate of the origin of the coordinate axis and the height of the bird's-eye view of the current frame;

[0158] Step 1022c: Determine the texture coordinate according to the abscissa and ordinate of the texture coordinate.

[0159] For example, assuming that the origin coordinates are set to the pixel coordinates of the rear wheel axle center point O = (x2, y2), the bird's-eye view width is width, and the height is height. The texture coordinate conversion formula is: F2 = ((x2-F1.y) / width, (height-y2+F1.x) / height), where F1.x and F1.y are the horizontal and vertical coordinates of the Ackerman coordinates of the next frame, and F1 is the texture coordinate.

[0160] In the embodiment of the present application, the abscissa of the texture coordinates is determined according to the ordinate of the Ackerman coordinates of the next frame, the abscissa of the origin of the coordinate axis, and the width of the bird's-eye view of the current frame, and the ordinate of the texture coordinates is determined according to the abscissa of the Ackerman coordinates of the next frame, the ordinate of the origin of the coordinate axis, and the height of the bird's-eye view of the current frame, thereby realizing the conversion of the Ackerman coordinates into the texture coordinates. It can be seen that the present application provides a specific method for converting the Ackerman coordinates into the texture coordinates, which has a small amount of calculation, is simple, can reduce the computing power consumption of the CPU and GPU, thereby reducing the resource occupancy rate and improving the real-time frame rate of the panoramic image.

[0161] See also Fig. 9 Based on the same inventive concept, the embodiment of the present application further provides a transparent chassis implementation device, the device comprising:

[0162] A driving position determination unit 201, configured to predict a next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the current frame driving position of the vehicle chassis in the current frame bird's-eye view;

[0163] A texture image determining unit 202, configured to determine a next frame texture image of the vehicle chassis according to a next frame driving position of the vehicle chassis in the current frame bird's-eye view;

[0164] The image fusion unit 203 is used to fuse the next frame of texture image with the next frame of bird's-eye view image to obtain the next frame of transparent chassis image.

[0165] Optionally, in the aspect of predicting the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the current frame driving position of the vehicle chassis in the current frame bird's-eye view, the driving position determining unit 201 is specifically used for:

[0166] Obtain the vehicle's steering wheel angle, driving speed, frame rate, and the vehicle chassis' current frame driving position in the current frame bird's-eye view;

[0167] Determine whether the steering wheel angle is 0;

[0168] If the steering wheel angle is 0, it is determined that the vehicle is traveling in a straight line;

[0169] If the vehicle is traveling in a straight line, the next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined according to the driving speed, the frame rate and the current frame driving position of the vehicle chassis in the current frame bird's-eye view.

[0170] Optionally, the driving position is represented by pixel coordinates, and in determining the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the driving speed, the frame rate, and the current frame driving position of the vehicle chassis in the current frame bird's-eye view, the driving position determining unit 201 is specifically used to:

[0171] Determine the current frame pixel coordinates of the vehicle chassis in the current frame bird's-eye view according to the current frame driving position of the vehicle chassis in the current frame bird's-eye view, and determine the time interval between each frame according to the frame rate;

[0172] Determine the travel distance according to the time interval between each frame and the travel speed;

[0173] The horizontal coordinate of the current frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view is used as the horizontal coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view, and the vertical coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view is used as the sum of the vertical coordinate of the current frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view and the driving distance;

[0174] The next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined according to the horizontal coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view and the vertical coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view.

[0175] Optionally, the driving position determining unit 201 is further specifically configured to:

[0176] If the steering wheel angle is not 0, it is determined that the vehicle is turning;

[0177] If the vehicle is turning, obtaining the steering ratio and wheelbase of the vehicle;

[0178] The next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined based on the steering wheel angle, the steering ratio, the wheelbase, the frame rate, the driving speed and the current frame driving position of the vehicle chassis in the current frame bird's-eye view.

[0179] Optionally, in determining the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the steering wheel angle, the steering ratio, the wheelbase, the frame rate, the driving speed, and the current frame driving position of the vehicle chassis in the current frame bird's-eye view, the driving position determining unit 201 is specifically used to:

[0180] determining a wheel angle according to the steering wheel angle and the steering ratio;

[0181] Determining a wheel rotation radius according to the wheel rotation angle and the wheelbase;

[0182] determining a time interval between each frame according to the frame rate;

[0183] Determine the front deflection angle according to the wheel rotation radius, the driving speed and the time interval between each frame;

[0184] Determine the wheel displacement according to the vehicle head deflection angle and the wheel rotation radius, and determine the coordinate rotation matrix according to the vehicle head deflection angle;

[0185] Determine a coordinate translation matrix according to the wheel displacement, the coordinate rotation matrix and the current frame driving position of the vehicle chassis in the current frame bird's-eye view;

[0186] The next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined according to the coordinate rotation matrix, the coordinate translation matrix and the current frame driving position of the vehicle chassis in the current frame bird's-eye view.

[0187] Optionally, the driving position is represented by Ackerman coordinates. In determining the next frame texture image of the vehicle chassis according to the next frame driving position of the vehicle chassis in the current frame bird's-eye view, the texture image determination 202 unit is specifically used for:

[0188] Determine the Ackerman coordinates of the next frame according to the next frame driving position of the vehicle chassis in the current frame bird's-eye view;

[0189] Convert the next frame Ackerman coordinates into texture coordinates;

[0190] The texture of the current frame bird's-eye view is sampled according to the texture coordinates to obtain a next frame texture image of the vehicle chassis.

[0191] Optionally, in the aspect of converting the next frame Ackerman coordinates into texture coordinates, the texture image determining unit 202 is specifically used for:

[0192] Obtaining the width and height of the bird's-eye view of the current frame, and determining the origin of the coordinate axis;

[0193] Determine the abscissa of the texture coordinate according to the ordinate of the Ackerman coordinate of the next frame, the abscissa of the origin of the coordinate axis and the width of the bird's-eye view of the current frame, and determine the ordinate of the texture coordinate according to the abscissa of the Ackerman coordinate of the next frame, the ordinate of the origin of the coordinate axis and the height of the bird's-eye view of the current frame;

[0194] The texture coordinate is determined according to the abscissa and the ordinate of the texture coordinate.

[0195] See also Fig.10 Based on the same inventive concept, the embodiment of the present application further provides a vehicle body integrated control module, the vehicle body integrated control module includes at least one processor 301, the processor 301 is used to execute a computer program stored in a memory, and implement the embodiment of the present application as provided in Figure 1 , Figure 2-8 Schematic diagram of the steps of the vehicle control method shown.

[0196] Optionally, the processor 301 may specifically be a central processing unit, a specific ASIC, or one or more integrated circuits for controlling program execution.

[0197] Optionally, the vehicle body integrated control module may further include a memory 302 connected to at least one processor 301, and the memory 302 may include ROM, RAM, and disk storage. The memory 302 is used to store data required by the processor 301 when it is running, that is, it stores instructions that can be executed by at least one processor 301. At least one processor 301 executes the instructions stored in the memory 302 to execute the instructions shown in FIG. Figure 1 , Figure 2-8 The method shown. Wherein, the number of the memory 302 is one or more. Wherein, the number of the memory 302 is one or more.

[0198] See also Fig.11 Based on the same inventive concept, the present application also provides a vehicle, comprising Fig.10 The body integrated control module shown. For example, the vehicle can be a pure electric vehicle, an extended-range vehicle, or a plug-in hybrid vehicle.

[0199] The present application also provides a computer storage medium, wherein the computer storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer executes Figure 1 , Figure 2-8 method.

[0200] The above description is only a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this specification should be included in the scope of protection of this specification.

Claims

1. A method for realizing a transparent chassis, characterized in that: The method comprises: Predicting the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the current frame driving position of the vehicle chassis in the current frame bird's-eye view; Determine a next frame texture image of the vehicle chassis according to a next frame driving position of the vehicle chassis in the current frame bird's-eye view; The next frame of texture image is fused with the next frame of bird's-eye view image to obtain the next frame of transparent chassis image.

2. The method according to claim 1, characterized in that: The method of predicting the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the current frame driving position of the vehicle chassis in the current frame bird's-eye view comprises: Obtain the vehicle's steering wheel angle, driving speed, frame rate, and the vehicle chassis' current frame driving position in the current frame bird's-eye view; Determine whether the steering wheel angle is 0; If the steering wheel angle is 0, it is determined that the vehicle is traveling in a straight line; If the vehicle is traveling in a straight line, the next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined according to the driving speed, the frame rate and the current frame driving position of the vehicle chassis in the current frame bird's-eye view.

3. The method according to claim 2, characterized in that The driving position is represented by pixel coordinates, and the method of determining the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the driving speed, the frame rate, and the current frame driving position of the vehicle chassis in the current frame bird's-eye view includes: Determine the current frame pixel coordinates of the vehicle chassis in the current frame bird's-eye view according to the current frame driving position of the vehicle chassis in the current frame bird's-eye view, and determine the time interval between each frame according to the frame rate; Determine the travel distance according to the time interval between each frame and the travel speed; The horizontal coordinate of the current frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view is used as the horizontal coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view, and the vertical coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view is used as the sum of the vertical coordinate of the current frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view and the driving distance; The next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined according to the horizontal coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view and the vertical coordinate of the next frame pixel point coordinate of the vehicle chassis in the current frame bird's-eye view.

4. The method according to claim 2, characterized in that: The method further comprises: If the steering wheel angle is not 0, it is determined that the vehicle is turning; If the vehicle is turning, obtaining the steering ratio and wheelbase of the vehicle; The next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined based on the steering wheel angle, the steering ratio, the wheelbase, the frame rate, the driving speed and the current frame driving position of the vehicle chassis in the current frame bird's-eye view.

5. The method according to claim 4, characterized in that The method of determining the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the steering wheel angle, the steering ratio, the wheelbase, the frame rate, the driving speed, and the current frame driving position of the vehicle chassis in the current frame bird's-eye view comprises: determining a wheel angle according to the steering wheel angle and the steering ratio; Determining a wheel rotation radius according to the wheel rotation angle and the wheelbase; determining a time interval between each frame according to the frame rate; Determine the front deflection angle according to the wheel rotation radius, the driving speed and the time interval between each frame; Determine the wheel displacement according to the vehicle head deflection angle and the wheel rotation radius, and determine the coordinate rotation matrix according to the vehicle head deflection angle; Determine a coordinate translation matrix according to the wheel displacement, the coordinate rotation matrix and the current frame driving position of the vehicle chassis in the current frame bird's-eye view; The next frame driving position of the vehicle chassis in the current frame bird's-eye view is determined according to the coordinate rotation matrix, the coordinate translation matrix and the current frame driving position of the vehicle chassis in the current frame bird's-eye view.

6. The method according to any one of claims 1 to 5, characterized in that: The driving position is represented by Ackerman coordinates, and determining the next frame texture image of the vehicle chassis according to the next frame driving position of the vehicle chassis in the current frame bird's-eye view includes: Determine the Ackerman coordinates of the next frame according to the next frame driving position of the vehicle chassis in the current frame bird's-eye view; Convert the next frame Ackerman coordinates into texture coordinates; The texture of the current frame bird's-eye view is sampled according to the texture coordinates to obtain a next frame texture image of the vehicle chassis.

7. The method according to claim 6, characterized in that The converting the next frame Ackerman coordinates into texture coordinates comprises: Obtaining the width and height of the bird's-eye view of the current frame, and determining the origin of the coordinate axis; Determine the abscissa of the texture coordinate according to the ordinate of the Ackerman coordinate of the next frame, the abscissa of the origin of the coordinate axis and the width of the bird's-eye view of the current frame, and determine the ordinate of the texture coordinate according to the abscissa of the Ackerman coordinate of the next frame, the ordinate of the origin of the coordinate axis and the height of the bird's-eye view of the current frame; The texture coordinate is determined according to the abscissa and the ordinate of the texture coordinate.

8. A transparent chassis realization device, characterized in that: The device comprises: A driving position determination unit, used for predicting the next frame driving position of the vehicle chassis in the current frame bird's-eye view according to the current frame driving position of the vehicle chassis in the current frame bird's-eye view; A texture image determination unit, configured to determine a next frame texture image of the vehicle chassis according to a next frame driving position of the vehicle chassis in the current frame bird's-eye view; The image fusion unit is used to fuse the next frame of texture image with the next frame of bird's-eye view to obtain the next frame of transparent chassis image.

9. A vehicle body integrated control module, characterized in that: The body integrated control module includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein when the computer program instructions are executed by the processor, the body integrated control module is triggered to execute the steps of the method as described in any one of claims 1-7.

10. A vehicle, characterized in that: The vehicle includes the body integrated control module of claim 9.

Images