Vehicle chassis perspective method, device and equipment, vehicle and storage medium

By using the rotation translation matrix and transparency gradient rendering technology in the vehicle chassis perspective method, the problem that the circumferential image system cannot obtain the vehicle chassis area image is solved, and the visual effect of the chassis image in the panoramic image is improved.

CN118967876APending Publication Date: 2024-11-15ZHEJIANG GEELY HLDG GRP CO LTD +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411094326.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The surround view image system cannot obtain images of the vehicle chassis area, resulting in poor visual effects of the chassis image in panoramic images in scenes with large light changes.

Method used

By determining the rotation translation matrix based on the steering angle and speed of the vehicle, preset transition rules to obtain the vertex coordinates around the vehicle chassis image, intercept the predicted chassis area image and superimpose it into a bird's-eye image, and perform transparency gradient rendering to improve the visual effect.

Benefits of technology

It effectively improves the visual effect of the chassis image in the panoramic image, reduces the brightness difference caused by light changes, and improves the overall quality of the image.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118967876A_ABST
    Figure CN118967876A_ABST
Patent Text Reader

Abstract

The invention provides a vehicle chassis perspective method, device and equipment, a vehicle and a storage medium. Relates to the technical field of auxiliary driving image processing. The method comprises the steps of determining a rotation and translation matrix according to a steering wheel angle and a vehicle speed of a vehicle, determining vertex coordinates of a vehicle chassis image according to a preset transition rule, intercepting a predicted chassis area image from a panoramic image at a previous moment according to the vertex coordinates and the rotation and translation matrix, and superposing the predicted chassis area image to the aerial view image at the current moment to carry out chassis perspective rendering, and carrying out transparency gradient rendering on a part corresponding to a superposed transition area in the predicted chassis area image. According to the method, the transition part in the chassis area image is predicted through transparency gradient rendering, and the visual effect of the chassis image in the panoramic image is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of assisted driving image processing, and in particular to a vehicle chassis perspective method, device, equipment, vehicle and storage medium. Background Art

[0002] With the continuous development of automobile intelligence, surround view imaging systems have been widely used in smart cars, which can provide drivers with real-time images of the vehicle's surroundings, enhance the driver's perception of the vehicle's surroundings, and improve driving safety. However, due to the limitation of the installation position of the on-board surround view camera, the camera cannot obtain images of the bottom area of ​​the vehicle. Therefore, the surround view imaging system has a blind spot under the vehicle chassis and cannot provide complete information about the vehicle's surroundings.

[0003] In the related art, a fixed vehicle chassis area is usually set for the vehicle, and the image of the vehicle chassis at the next position is predicted. When the vehicle arrives at the position, the chassis image acquired in advance is spliced ​​into the corresponding image. However, in scenes with large changes in light, the spliced ​​images will have significant brightness differences, resulting in poor visual effects of the chassis image in the panoramic image. Summary of the invention

[0004] The present application provides a vehicle chassis perspective method, device, equipment, vehicle and storage medium for improving the visual effect of chassis images in panoramic images.

[0005] In a first aspect, the present application provides a vehicle chassis perspective method, comprising:

[0006] Determine a rotation and translation matrix according to the steering wheel angle and the vehicle speed of the vehicle, wherein the rotation and translation matrix is ​​used to represent the conversion relationship between the chassis coordinates at the current moment and the coordinates in the panoramic image at the previous moment;

[0007] According to a preset transition rule, determining vertex coordinates of the vehicle chassis image, wherein the vertex coordinates are coordinates of the vertices after a transition area is superimposed around the vehicle chassis image;

[0008] According to the vertex coordinates and the rotation and translation matrix, a predicted chassis area image is intercepted from the panoramic image at the previous moment;

[0009] The predicted chassis area image is superimposed on the bird's-eye view image at the current moment to perform chassis perspective rendering, wherein a portion of the predicted chassis area image corresponding to the superimposed transition area is rendered with a gradual transparency.

[0010] In a possible implementation, determining the vertex coordinates of the vehicle chassis image according to a preset transition rule includes:

[0011] Determining original vertex coordinates of the vehicle chassis image based on the body parameters and projection ratio of the vehicle;

[0012] Calculating a first transition area width according to the vehicle speed, a preset minimum vehicle speed threshold, and a preset maximum vehicle speed threshold;

[0013] According to the original vertex coordinates, the coordinates of the vertices after the first transition area corresponding to the first transition area width is superimposed around the vehicle chassis image are acquired to obtain the vertex coordinates.

[0014] In a possible implementation, the method further includes:

[0015] If the steering wheel angle indicates that the steering wheel of the vehicle is rotated, determining a second transition region width according to the steering wheel angle;

[0016] Correspondingly, the step of acquiring the coordinates of the vertices after the first transition area corresponding to the width of the first transition area is superimposed around the vehicle chassis image according to the original vertex coordinates to obtain the vertex coordinates includes:

[0017] According to the original vertex coordinates, the coordinates of the vertices after superimposing the second transition area corresponding to the width of the second transition area around the vehicle chassis image and the first transition area corresponding to the width of the first transition area are obtained to obtain the vertex coordinates.

[0018] In a possible implementation manner, the calculating the first transition area width according to the vehicle speed, a preset minimum vehicle speed threshold, and a maximum vehicle speed threshold includes:

[0019] If the vehicle speed is less than the minimum vehicle speed threshold, determining the first transition area width to be a preset minimum transition width;

[0020] If the vehicle speed is greater than or equal to the minimum vehicle speed threshold and less than the maximum vehicle speed threshold, the first transition area width is calculated according to the difference between the maximum vehicle speed threshold and the minimum vehicle speed threshold and the vehicle speed;

[0021] If the vehicle speed is greater than or equal to the maximum vehicle speed threshold, the first transition area width is determined to be a preset maximum transition width.

[0022] In a possible implementation, superimposing the predicted chassis area image onto the bird's-eye view image at the current moment to perform chassis perspective rendering includes:

[0023] Based on the original vertex coordinates of the vehicle chassis image, superimposing the predicted chassis area image onto the area where the vehicle chassis is located in the bird's-eye view image at the current moment to obtain a panoramic image of the vehicle;

[0024] The chassis perspective rendering is performed according to the panoramic image, wherein when rendering, when rendering the portion corresponding to the first transition area in the predicted chassis area image, the transparency value gradually decreases from the inside to the outside.

[0025] In a possible implementation, superimposing the predicted chassis area image onto the bird's-eye view image at the current moment to perform chassis perspective rendering includes:

[0026] Based on the original vertex coordinates of the vehicle chassis image, superimposing the predicted chassis area image onto the area where the vehicle chassis is located in the bird's-eye view image at the current moment to obtain a panoramic image of the vehicle;

[0027] The chassis perspective rendering is performed according to the panoramic image, wherein, when rendering, the portion corresponding to the second transition area in the predicted chassis area image has the highest transparency, and when rendering the portion corresponding to the first transition area in the predicted chassis area image, the transparency value gradually decreases from the inside to the outside.

[0028] In a possible implementation manner, determining the width of the second transition area according to the steering wheel angle includes:

[0029] According to a preset mapping relationship between the turning angle and the transition area width, the second transition area width corresponding to the steering wheel turning angle is queried.

[0030] In a possible implementation manner, determining the rotation and translation matrix according to the steering wheel angle and the vehicle speed of the vehicle includes:

[0031] Determine the vehicle turning radius corresponding to the steering wheel angle at a previous moment according to a calibration relationship between the steering wheel angle and the vehicle turning radius, determine the angle offset according to the vehicle turning radius, and determine the displacement change according to the vehicle speed at a previous moment;

[0032] The rotation and translation matrix is ​​constructed according to the angle offset and the displacement change.

[0033] In a second aspect, the present application provides a vehicle chassis perspective device, comprising:

[0034] A first determination module, used to determine a rotation and translation matrix according to a steering wheel angle and a vehicle speed of the vehicle, wherein the rotation and translation matrix is ​​used to represent a conversion relationship between chassis coordinates at a current moment and coordinates in a panoramic image at a previous moment;

[0035] A second determination module is used to determine the vertex coordinates of the vehicle chassis image according to a preset transition rule, wherein the vertex coordinates are the coordinates of the vertices after a transition area is superimposed around the vehicle chassis image;

[0036] A first processing module, configured to extract a predicted chassis area image from the panoramic image at a previous moment according to the vertex coordinates and the rotation and translation matrix;

[0037] The second processing module is used to superimpose the predicted chassis area image onto the bird's-eye view image at the current moment to perform chassis perspective rendering, wherein a portion of the predicted chassis area image corresponding to the superimposed transition area is rendered with a transparency gradient.

[0038] In a third aspect, the present application provides a cockpit domain controller, including: a processor, a memory, and a communication interface;

[0039] The memory stores computer-executable instructions;

[0040] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the vehicle chassis perspective method described in any one of the first aspects.

[0041] In a fourth aspect, an embodiment of the present application provides a vehicle, comprising a vehicle body and a cockpit domain controller as described in the third aspect.

[0042] In a fifth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the vehicle chassis perspective method described in any one of the first aspects.

[0043] In a sixth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the vehicle chassis perspective method described in any one of the first aspects.

[0044] The present application provides a vehicle chassis perspective method, device, equipment, vehicle and storage medium. The cockpit domain controller can determine the rotation and translation matrix according to the steering wheel angle and speed of the vehicle. The vertex coordinates of the vehicle chassis image are determined by preset transition rules. Using the determined vertex coordinates and rotation and translation matrix, the predicted chassis area image is cut out from the panoramic image at the previous moment, and it is superimposed on the bird's-eye view image at the current moment. During the rendering process, the transition area part in the predicted chassis area image can be rendered with transparency gradient to achieve chassis perspective. Since the superimposed transition area in the predicted chassis area image can be rendered with transparency gradient, the visual effect of the chassis image in the panoramic image is effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0046] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present application;

[0047] Figure 2 A schematic diagram of the process of the first embodiment of the vehicle chassis perspective method provided by the present application;

[0048] Figure 3 A schematic diagram of vertex coordinate positions provided in an embodiment of the present application;

[0049] Figure 4 A schematic diagram of the process of the second embodiment of the vehicle chassis perspective method provided by the present application;

[0050] Figure 5 A schematic diagram of an example of a rotation and translation matrix provided in an embodiment of the present application;

[0051] Figure 6 A schematic diagram of the vertex coordinate position transformation provided in an embodiment of the present application;

[0052] Figure 7 A schematic diagram of the process of the third embodiment of the vehicle chassis perspective method provided in the present application;

[0053] Figure 8 A schematic diagram of another vertex coordinate position provided in an embodiment of the present application;

[0054] Fig. 9 A schematic diagram of a process for determining a predicted chassis area image provided in an embodiment of the present application;

[0055] Fig.10 A schematic diagram of the process of perspective viewing of a vehicle chassis provided in an embodiment of the present application;

[0056] Fig.11 A schematic diagram of the coordinate positions of the vertices of the special-shaped transparent chassis provided in an embodiment of the present application;

[0057] Fig.12 A schematic diagram of the structure of a vehicle chassis perspective device provided in an embodiment of the present application;

[0058] Fig.13 A schematic diagram of the structure of a cockpit domain controller provided in an embodiment of the present application.

[0059] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0060] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0061] First, let’s explain the terms involved in this application:

[0062] Bird's-eye view image: A bird's-eye view image is an image taken from a high altitude, usually used to provide a wide perspective, similar to what a bird sees when looking down at the ground from the air. In a vehicle, a bird's-eye view image can be achieved by setting up four cameras (or cameras) on the front, rear, left and right sides of the vehicle.

[0063] Vehicle chassis image: refers to an image taken of the blind area below the vehicle chassis area, which is used to show the condition of the vehicle chassis.

[0064] Panoramic image: It is a superposition of the bird's-eye view image and the vehicle chassis image to provide a comprehensive perspective to show the vehicle's surrounding environment and the vehicle chassis condition.

[0065] Rotation-translation matrix: used to describe the position and orientation of an object in three-dimensional space. It combines the rotation matrix and translation vector to simultaneously represent the rotation and displacement of an object.

[0066] With the advancement of smart car technology, surround view imaging systems have become a common configuration of smart cars, with various functions emerging one after another. However, due to the limitations of the installation position of the on-board surround view camera, the surround view imaging system cannot cover the image acquisition of the vehicle chassis area.

[0067] In the related technology, a fixed vehicle chassis area can be set for the vehicle, and the image of the vehicle chassis area during the movement of the vehicle can be predicted. When the vehicle arrives at the corresponding position, the vehicle chassis image acquired in advance can be spliced ​​together with the surrounding image acquired by the surround-view camera to obtain a panoramic image, realize the perspective of the vehicle chassis, and obtain the image of the vehicle chassis area.

[0068] However, when the vehicle chassis image acquired in advance is stitched together with the surrounding images, for scenes with large light changes, the stitched images will have significant brightness differences, resulting in poor visual effects of the chassis image in the panoramic image.

[0069] In response to the above problems, the inventors found that in the process of acquiring the vehicle chassis image, the fixed vehicle chassis area can be dynamically changed, and the visual effect of the chassis image in the panoramic image can be improved by superimposing the transition area and rendering the corresponding part of the transition area with transparency gradient. Specifically, after many experiments, the inventors found that the rotation and translation matrix can be determined according to the steering wheel angle and speed of the vehicle, and the vertex coordinates after the transition area is superimposed around the vehicle chassis image can be obtained by applying the preset transition rules. Based on the vertex coordinates and the rotation and translation matrix, the predicted chassis area image is cut out from the panoramic image of the previous moment, and the predicted chassis area image is superimposed on the bird's-eye view image of the current moment for chassis perspective rendering. During the rendering process, the superimposed transition area in the predicted chassis area image is rendered with transparency gradient, which effectively improves the visual effect of the chassis image in the panoramic image. Based on this, the present application proposes a vehicle chassis perspective method to further enhance the visual effect of the chassis image in the panoramic image.

[0070] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of the present application. Figure 1 , the vehicle can obtain a panoramic image of the previous moment, the panoramic image includes a predicted chassis area image A of the vehicle at the next moment. When the vehicle is at the current moment, it can obtain a bird's-eye view image of the current moment, and overwrite the predicted chassis area image A included in the panoramic image obtained at the previous moment with the bird's-eye view image obtained at the current moment to obtain a panoramic image of the current moment.

[0071] For example, the vehicle can obtain panoramic image 1 at the previous moment (moment A), and panoramic image 1 includes the predicted chassis area image A of the vehicle at the next moment (moment B). When the vehicle is at the current moment (moment B), a bird's-eye view image of moment B can be obtained, and the predicted chassis area image A included in the panoramic image 1 obtained at moment A is overlaid on the bird's-eye view image obtained at moment B to obtain panoramic image 2 at moment B.

[0072] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0073] Figure 2 This is a flow chart of the first embodiment of the vehicle chassis perspective method provided by this application. Figure 2 , the method may include:

[0074] S201. Determine a rotation and translation matrix according to the steering wheel angle and vehicle speed of the vehicle.

[0075] The execution subject of the embodiment of the present application may be a cockpit domain controller, or a vehicle chassis perspective device set in the cockpit domain controller. The vehicle chassis perspective device may be implemented by software, or by a combination of software and hardware. The vehicle chassis perspective device may be a processor in the cockpit domain controller. For ease of understanding, the following description is made by taking the cockpit domain controller as an example.

[0076] In this step, the cockpit domain controller can determine the angle offset according to the steering wheel angle of the vehicle at the previous moment, and determine the displacement change according to the vehicle speed at the previous moment. According to the determined angle offset and displacement change, a rotation and translation matrix is ​​constructed.

[0077] The previous moment may be a historical moment, and the previous moment may be preset according to the request, that is, the time interval between the previous moment and the current moment is adjustable.

[0078] For example, if the current time is 2022 / 10 / 31 14:00:05.200, the previous time may be a time immediately adjacent to the current time, such as 2022 / 10 / 31 14:00:05.170, where the time interval between the two times is 30 milliseconds (ms).

[0079] For another example, if the current time is 2022 / 10 / 31 14:00:05.200, the previous time can be any time before the current time, such as 2022 / 10 / 31 14:00:05.150, and the time interval between the two times is 50ms.

[0080] Optionally, the vehicle turning radius corresponding to the steering wheel angle at the previous moment can be obtained according to the calibration relationship between the steering wheel angle and the vehicle turning radius. The angle offset is determined according to the vehicle speed at the previous moment, the time interval between the previous moment and the current moment, and the vehicle turning radius.

[0081] Specifically, the displacement change amount may be determined according to the vehicle speed at a previous moment and the time interval between the previous moment and the current moment.

[0082] Furthermore, a 4x4 rotation and translation matrix can be constructed based on the angle offset and displacement change to realize the rotation and translation transformation of the coordinate point in three-dimensional space, convert the coordinate point from one coordinate system to another, and describe its position and posture in space.

[0083] For example, the rotation and translation matrix RT0 may be determined based on the steering wheel angle A0 and the vehicle speed V0 of the vehicle at the previous moment.

[0084] S202: Determine vertex coordinates of the vehicle chassis image according to a preset transition rule.

[0085] In this step, a transition area may be superimposed around the vehicle chassis image according to a preset transition rule to obtain vertex coordinates of the vehicle chassis image, where the vertex coordinates are the coordinates of the vertices after the transition area is superimposed around the vehicle chassis image.

[0086] In an optional implementation, the original vertex coordinates of the vehicle chassis image in the image coordinate system can be determined based on the vehicle body parameters and projection ratio; the first transition area width is calculated based on the vehicle speed at the previous moment, the preset minimum speed threshold and the maximum speed threshold, and the vertex coordinates are obtained based on the original vertex coordinates after the first transition area corresponding to the first transition area width is superimposed around the vehicle chassis image. The coordinates of each point in the original vertex coordinates can be represented by pixel (px) coordinates in the image coordinate system.

[0087] Body parameters refer to the attribute parameters of the vehicle during the production process, such as vehicle width, vehicle length, and the size of the blind spots of the four-way cameras in the front, back, left and right of the vehicle.

[0088] Projection ratio refers to the ratio between the displayed bird's-eye view image and the actual scene after the images taken by four cameras are stitched together.

[0089] For example, the original vertex coordinates (Xi, Yi) of the vehicle chassis image can be determined according to the vehicle width L1, the vehicle length L2, the front blind spot D1 of the front camera, the rear blind spot D2 of the rear camera, the left blind spot D3 of the left camera, the right blind spot D4 of the right camera, and the projection ratio F1, which are the upper left corner coordinates (X1, Y1), the upper right corner coordinates (X2, Y2), the lower left corner coordinates (X3, Y3), and the lower right corner coordinates (X4, Y4), respectively.

[0090] Furthermore, the first transition area width may be calculated based on the relationship between the vehicle speed at the previous moment and a preset minimum vehicle speed threshold and a maximum vehicle speed threshold.

[0091] For example, the preset minimum vehicle speed threshold Vmin may correspond to a preset minimum transition width W11, and the preset maximum vehicle speed threshold Vmax may correspond to a preset maximum transition width W12. According to the vehicle speed V0 at the previous moment being greater than the preset maximum vehicle speed threshold Vmax, the width of the first transition area is determined to be the preset maximum transition width W12 corresponding to the preset maximum vehicle speed threshold Vmax.

[0092] After obtaining the original vertex coordinates and the width of the first transition area, the coordinates of the vertices after superimposing the first transition area corresponding to the width of the first transition area around the vehicle chassis image can be obtained to obtain the vertex coordinates (Xj, Yj), which are the upper left corner coordinates (X5, Y5), the upper right corner coordinates (X6, Y6), the lower left corner coordinates (X7, Y7), and the lower right corner coordinates (X8, Y8), respectively.

[0093] Figure 3 This is a schematic diagram of the vertex coordinate positions provided in the embodiment of the present application. Figure 3 , an image coordinate system is established with the south direction as the Y axis and the east direction as the X axis. The original vertex coordinates (Xi, Yi) corresponding to the vehicle chassis image are point A (X1, Y1), point B (X2, Y2), point C (X3, Y3), and point D (X4, Y4), respectively. The coordinates (Xj, Yj) of the vertices after the first transition area corresponding to the first transition area width W12 is superimposed around the vehicle chassis image are point E (X5, Y5), point F (X6, Y6), point G (X7, Y7), and point H (X8, Y8), respectively.

[0094] It should be noted that when the actual coordinates of the vertex coordinates (Xj, Yj) are calculated by the actual coordinates of the original vertex coordinates (Xi, Yi) and the first transition area width W12, it is necessary to consider the direction of superimposing the first transition area width W12, that is, whether the actual coordinates of the original vertex coordinates (Xi, Yi) are subtracted or added. For example, if the first transition area width W12 is 10, the original vertex coordinates (Xi, Yi) and the vertex coordinates (Xj, Yj) superimposed with the first transition area width W12 can be as shown in Table 1:

[0095] Table 1

[0096]

[0097] S203 , extracting a predicted chassis area image from the panoramic image at the previous moment according to the vertex coordinates and the rotation and translation matrix.

[0098] In this step, the vertex coordinates (Xj, Yj) can be transformed according to the rotation and translation matrix to obtain the coordinate position of the chassis area image at the previous moment in the panoramic image at the current moment (also the next moment of the previous moment), and the predicted chassis area image can be cut out from the panoramic image at the previous moment.

[0099] In an optional implementation, the formula: j ′,y j ′) 4x2 =RT 4x4 *(Xj,Yj) 4x2The coordinate position of the predicted chassis area image at the current moment in the panoramic image at the previous moment is calculated.

[0100] For example, the coordinates of point E (X5, Y5), point F (X6, Y6), point G (X7, Y7), and point H (X8, Y8) can be changed according to the rotation and translation matrix RT0 to obtain the coordinate position of the predicted chassis area image at the current moment in the panoramic image at the previous moment, and the predicted chassis area image can be cut out from the panoramic image at the previous moment.

[0101] S204: superimposing the predicted chassis area image onto the bird's-eye view image at the current moment to perform chassis perspective rendering, wherein a portion of the predicted chassis area image corresponding to the superimposed transition area is rendered with a transparency gradient.

[0102] In this step, the predicted chassis area image can be cut out from the panoramic image at the previous moment and superimposed on the bird's-eye view image at the current moment to perform chassis perspective rendering. Specifically, the portion corresponding to the superimposed transition area in the predicted chassis area image can be rendered with a transparency gradient to ensure that the visual effect of the transition area is smoother and more natural.

[0103] Transparency refers to the degree of transparency of an image or object, and is usually represented by the value of the Alpha channel, which ranges from 0 to 1. A transparency value of 0 represents complete transparency, and a transparency value of 1 represents complete opacity.

[0104] Optionally, the transparency value of the transition area may be preset, and the transparency value gradually transitions from 1 to 0 from the inner side to the outer side.

[0105] In an embodiment of the present application, a rotation and translation matrix can be determined based on the steering wheel angle and speed of the vehicle. The vertex coordinates of the vehicle chassis image are determined by a preset transition rule. Using the determined vertex coordinates and the rotation and translation matrix, the predicted chassis area image can be cut out from the panoramic image of the previous moment and superimposed on the bird's-eye view image of the current moment to achieve chassis perspective rendering. During the rendering process, the transition area portion in the predicted chassis area image is rendered with a transparency gradient. In the above process, by superimposing the transition area and rendering the portion corresponding to the transition area with a transparency gradient, the visual effect of the chassis image in the panoramic image can be improved.

[0106] exist Figure 2 Based on the embodiment shown below, combined with Figure 4 , the above-mentioned vehicle chassis perspective method is further described in detail.

[0107] Figure 4 This is a flow chart of the second embodiment of the vehicle chassis perspective method provided by this application. Figure 4, the method may include:

[0108] S401. Determine the vehicle turning radius corresponding to the steering wheel angle at a previous moment according to a calibration relationship between the steering wheel angle and the vehicle turning radius, determine an angle offset according to the vehicle turning radius, and determine a displacement change according to the vehicle speed at a previous moment.

[0109] In this step, the vehicle turning radius at the previous moment can be determined by the steering wheel angle of the vehicle at the previous moment according to the calibration relationship between the pre-set steering wheel angle and the vehicle turning radius, and the angle offset can be determined by combining the angle offset calculation formula. The displacement change can be determined according to the vehicle speed at the previous moment.

[0110] The calibration relationship refers to the known corresponding relationship between two variables. The corresponding relationship between the steering wheel angle and the vehicle turning radius can be determined through experiments, tests, etc.

[0111] Optionally, the vehicle turning radius corresponding to the steering wheel angle at the previous moment can be obtained based on the calibrated relationship between the steering wheel angle and the vehicle turning radius, and the angular offset of the vehicle at the current moment relative to the previous moment can be predicted based on the angle offset calculation formula.

[0112] The angle offset calculation formula is: Δθ=V*Δt / R.

[0113] Among them, Δθ represents the angle offset, V represents the vehicle speed at the previous moment, Δt represents the time interval between the previous moment and the current moment, and R is the vehicle turning radius corresponding to the previous moment.

[0114] Optionally, the displacement change of the vehicle at the current moment relative to the previous moment can be predicted based on the vehicle speed at the previous moment and the displacement change calculation formula.

[0115] The displacement change calculation formula is: Δs=V*Δt.

[0116] Among them, Δs represents the displacement change.

[0117] For example, based on the calibration relationship between the steering wheel angle A and the vehicle turning radius R, the vehicle turning radius R0 corresponding to the steering wheel angle A0 at the previous moment can be obtained, and the angular offset Δθ of the vehicle at the current moment relative to the previous moment can be predicted based on the angle offset calculation formula; based on the vehicle speed V0 at the previous moment, the displacement change Δs of the vehicle at the current moment relative to the previous moment can be predicted through the displacement change calculation formula.

[0118] S402: construct a rotation and translation matrix according to the angle offset and the displacement change.

[0119] For example, the rotation-translation matrix RT0 may be constructed based on the predicted angular offset Δθ of the vehicle at the current moment relative to the previous moment, and the displacement change Δs of the vehicle at the current moment relative to the previous moment.

[0120] Figure 5 This is a schematic diagram of an example of a rotation and translation matrix provided in an embodiment of the present application. Figure 5 , the 4x4 rotation and translation matrix RT0 can be constructed through the angle offset Δθ and the displacement change Δs. Among them, R11, R12, R13, R21, R22, R23, R31, R32, R33 are the elements of the 3x3 rotation matrix, which respectively represent the angles of rotation of the object around the x, y, and z axes. Tx, Ty, and Tz are the elements of the translation vector, which represent the displacement of the object in the x, y, and z directions.

[0121] In the vehicle body coordinate system, perpendicular to the earth direction, that is, in the Z-axis direction, there is no angle offset and displacement change, so 0 is used instead at R13, R23, R31, R32, and Tz positions.

[0122] It should be understood that if the vehicle steering wheel angle has not changed at the previous moment, the vehicle turning radius R0 corresponding to the steering wheel angle A0 at the previous moment may be empty, that is, the vehicle keeps moving in a straight line, and accordingly, the value of the angle offset Δθ may be 0.

[0123] S403: Determine original vertex coordinates of the vehicle chassis image based on the vehicle body parameters and projection ratio.

[0124] In this step, the actual scene area captured by the four cameras can be determined based on the vehicle body parameters, the actual scene area can be scaled to the image coordinate system through the projection ratio, and the original vertex coordinates of the vehicle chassis image can be determined from the image corresponding to the actual scene area.

[0125] For example, the actual scene area can be determined based on the vehicle width L1, the vehicle length L2, the front blind spot D1 of the front camera, the rear blind spot D2 of the rear camera, the left blind spot D3 of the left camera, and the right blind spot D4 of the right camera. The actual scene area can be scaled to the image coordinate system through the projection ratio F1, and the original vertex coordinates (Xi, Yi) of the vehicle chassis image can be determined from the image corresponding to the actual scene area, which are the upper left corner coordinates (X1, Y1), the upper right corner coordinates (X2, Y2), the lower left corner coordinates (X3, Y3), and the lower right corner coordinates (X4, Y4), respectively.

[0126] S404: Calculate a first transition area width according to the vehicle speed, a preset minimum vehicle speed threshold, and a maximum vehicle speed threshold.

[0127] In this step, the preset minimum vehicle speed threshold may correspond to a preset minimum transition width, and the preset maximum vehicle speed threshold may correspond to a preset maximum transition width. The width of the first transition area may be determined by the relationship between the vehicle speed at the previous moment and the preset minimum vehicle speed threshold and the maximum vehicle speed threshold.

[0128] If the vehicle speed is less than the minimum vehicle speed threshold, the first transition area width is determined to be a preset minimum transition width.

[0129] Optionally, the minimum vehicle speed threshold and the preset minimum transition width can be preset. For example, the minimum vehicle speed threshold Vmin is 10 km / h, and the preset minimum transition width W11 can be 0.

[0130] For example, the minimum preset transition width is W11. If the vehicle speed V0 at the previous moment is less than the preset minimum vehicle speed threshold Vmin, the width of the first transition area is determined to be the preset minimum transition width W11.

[0131] If the vehicle speed is greater than or equal to the minimum vehicle speed threshold and less than the maximum vehicle speed threshold, the first transition area width is calculated according to the difference between the maximum vehicle speed threshold and the minimum vehicle speed threshold and the vehicle speed.

[0132] Similarly, the maximum vehicle speed threshold and the preset maximum transition width can also be preset. For example, the maximum vehicle speed threshold Vmax is 25 km / h, and the preset maximum transition width W12 can be 10 pixels.

[0133] Specifically, the first transition area width calculation formula can be used to obtain the first transition area width corresponding to when the vehicle speed is greater than or equal to the minimum vehicle speed threshold and less than the maximum vehicle speed threshold.

[0134] The calculation formula for the width of the first transition area is:

[0135]

[0136] Where W1 is the width of the first transition region, W max is the preset maximum transition width, W min is the preset minimum transition width, V max is the maximum vehicle speed threshold, V min is the minimum vehicle speed threshold, and V is the vehicle speed at the previous moment.

[0137] If the vehicle speed is greater than or equal to the maximum vehicle speed threshold, the first transition area width is determined to be a preset maximum transition width.

[0138] For example, the maximum preset transition width is W12. If the vehicle speed V0 at the previous moment is greater than the preset maximum vehicle speed threshold Vmax, the width of the first transition area is determined to be the preset maximum transition width W12.

[0139] S405 . According to the original vertex coordinates, the coordinates of the vertices after the first transition area corresponding to the width of the first transition area is superimposed around the vehicle chassis image are obtained to obtain the vertex coordinates.

[0140] For example, if the width of the first transition region is W12, the method for obtaining the vertex coordinates may refer to the method for obtaining the vertex coordinates (Xj, Yj) in S202, which will not be described in detail here.

[0141] S406: According to the vertex coordinates and the rotation and translation matrix, a predicted chassis area image is cut out from the panoramic image at the previous moment.

[0142] In this step, the vertex coordinates may be transformed according to the rotation and translation matrix to obtain the predicted chassis area image at the previous moment, and the predicted chassis area image may be cut out from the panoramic image at the previous moment.

[0143] Figure 6 This is a schematic diagram of the vertex coordinate position transformation provided by the embodiment of the present application. Figure 6 , in the image coordinate system, the vertex coordinates of the panoramic image are respectively O1 point coordinates, O2 point coordinates, O3 point coordinates and O4 point coordinates. After changing the coordinates of point E, point F, point G and point H according to the rotation and translation matrix RT0, the vertex coordinates corresponding to the predicted chassis area image at the previous moment can be obtained, which are respectively I point coordinates, J point coordinates, K point coordinates and L point coordinates, and the predicted chassis area image is cut out from the panoramic image at the previous moment, and the vertex coordinates of the predicted chassis area image are respectively I point coordinates, J point coordinates, K point coordinates and L point coordinates.

[0144] In an optional embodiment, the vertex coordinates of the predicted chassis area image in the image coordinate system can be obtained through the following steps ①②③.

[0145] Step ①: Establish a body coordinate system. Based on the body coordinate system, the rotation and translation matrix RT0 in the body coordinate system is constructed according to the steering wheel angle and vehicle speed of the vehicle at the previous moment. The body coordinate system can use the center of the rear axle of the vehicle as the origin of the coordinates, the X-axis is along the center line of the vehicle pointing to the forward direction of the vehicle, and the Y-axis is at the same level as the X-axis and points to the left side of the driver.

[0146] Step ②: According to the vehicle body coordinate system, the vertex coordinates in the image coordinate system are transformed. The rotation and translation matrix RT0 is used to transform the position of the vertex coordinates after the position transformation to obtain the vertex coordinates of the predicted chassis area image in the vehicle body coordinate system.

[0147] Step ③: Perform position transformation on the vertex coordinates of the predicted chassis area image in the vehicle body coordinate system, restore them to the image coordinate system, and obtain the vertex coordinates of the predicted chassis area image at the previous moment.

[0148] S407 . Based on the original vertex coordinates of the vehicle chassis image, the predicted chassis area image is superimposed on the area where the vehicle chassis is located in the bird's-eye view image at the current moment to obtain a panoramic image of the vehicle.

[0149] In this step, when the vehicle travels to the position corresponding to the current moment, the initial position where the chassis area image needs to be rendered can be determined according to the original vertex coordinates of the vehicle chassis image. Then, the predicted chassis area image obtained at the previous moment can be superimposed on the area where the vehicle chassis is located in the bird's-eye view image at the current moment to generate a panoramic image of the vehicle.

[0150] For example, when the vehicle travels to the position corresponding to the current moment, the initial position of the chassis area image to be rendered can be determined based on the original vertex coordinates of the vehicle chassis image, and the initial position is the boundary position of the area composed of points A, B, C, and D as vertices. Then, the predicted chassis area image obtained at the previous moment, including the image of the area composed of points I, J, K, and L as vertices, can be superimposed on the area where the vehicle chassis is located in the bird's-eye view image at the current moment to generate a panoramic image of the vehicle.

[0151] S408, performing chassis perspective rendering according to the panoramic image, wherein, when rendering, when rendering the portion corresponding to the first transition area in the predicted chassis area image, the transparency value gradually decreases from the inside to the outside.

[0152] In this step, the generated panoramic image may be subjected to chassis perspective rendering. In the rendering process, when rendering the portion corresponding to the first transition area in the predicted chassis area image, the transparency value gradually decreases from the inside to the outside.

[0153] Optionally, the inner side refers to the chassis area image, and the boundary formed by the vertices of the chassis area image when the transition area is not superimposed; the outer side refers to the chassis area image, and the boundary formed by the vertices in the predicted chassis area image obtained after the transition area is superimposed.

[0154] For example, when the generated panoramic image is rendered in chassis perspective, the transparency value of the inner part corresponding to the first transition area is 1, and the transparency value of the outer part corresponding to the first transition area is 0, and the transparency value gradually decreases from 1 inside to 0 outside.

[0155] In an embodiment of the present application, the vehicle turning radius and angle offset corresponding to the steering wheel angle at the previous moment can be determined according to the relationship between the steering wheel angle and the vehicle turning radius, and the displacement change can be determined according to the vehicle speed at the previous moment to construct a rotation and translation matrix. Based on the vehicle parameters and the projection ratio, the original vertex coordinates of the chassis image are determined, the width of the first transition area is calculated, and the superimposed vertex coordinates are obtained. According to the vertex coordinates and the rotation and translation matrix, the predicted chassis area image is intercepted from the panoramic image at the previous moment, and it is superimposed on the vehicle chassis area in the bird's-eye view image at the current moment to obtain a panoramic image. When performing chassis perspective rendering, the transparency value of the first transition area in the predicted chassis area image is gradually reduced from the inside to the outside. In the above process, by rendering the superimposed transition area with a gradual transparency, a smooth transition between different image areas can be achieved, thereby improving the visual effect of the chassis image in the panoramic image.

[0156] During the vehicle chassis perspective, the steering wheel angle of the vehicle may change due to driving needs. Therefore, during the vehicle driving process, if the steering wheel angle indicates that the vehicle's steering wheel rotates, the width of the second transition area can be determined according to the steering wheel angle. Figure 2 Based on the embodiment shown, combined Figure 7 When determining the width of the second transition area based on the steering wheel angle, the above-mentioned vehicle chassis perspective method is further described in detail.

[0157] Figure 7 This is a flow chart of the third embodiment of the vehicle chassis perspective method provided by this application. Figure 7 , the method may include:

[0158] S701. Determine the vehicle turning radius corresponding to the steering wheel angle at a previous moment according to a calibration relationship between the steering wheel angle and the vehicle turning radius, determine an angle offset according to the vehicle turning radius, and determine a displacement change according to the vehicle speed at a previous moment.

[0159] S702: Construct a rotation and translation matrix according to the angle offset and the displacement change.

[0160] For example, the rotation and translation matrix RT1 can be constructed based on the angle offset Δθ and the displacement change Δs. The angle offset Δθ in RT1 is not 0, which means that the vehicle steering wheel angle has changed at the previous moment, and the steering wheel angle A1 at the previous moment has a corresponding vehicle turning radius R1, that is, the vehicle does not maintain a straight line.

[0161] S703: Determine original vertex coordinates of the vehicle chassis image based on the vehicle body parameters and projection ratio.

[0162] S704: Calculate a first transition region width according to the vehicle speed, a preset minimum vehicle speed threshold, and a preset maximum vehicle speed threshold.

[0163] It should be noted that the specific execution process of the above steps S701-S704 can be followed in order, refer to steps S401-S404 in sequence, and will not be repeated here.

[0164] S705: Determine a width of the second transition area according to the steering wheel angle.

[0165] In this step, the width of the second transition area may be determined according to the steering wheel angle at the previous moment.

[0166] Optionally, the second transition area width corresponding to the steering wheel angle may be queried according to a preset mapping relationship between the steering angle and the transition area width to determine the second transition area width.

[0167] The second transition region width, also called the wheel projection masking region, refers to the position where the wheel appears outside the region formed by the original vertices of the vehicle chassis image when the steering wheel angle changes and the wheel rotates accordingly.

[0168] For example, the second transition region width W2 may be determined according to the steering wheel angle A1 at a previous moment.

[0169] S706. According to the original vertex coordinates, obtain the coordinates of the vertices after superimposing the second transition area corresponding to the width of the second transition area around the vehicle chassis image and the first transition area corresponding to the width of the first transition area, to obtain the vertex coordinates.

[0170] In this step, the second transition area corresponding to the width of the second transition area can be superimposed around the vehicle chassis image determined according to the original vertex coordinates, and the first transition area corresponding to the width of the first transition area can be superimposed to obtain the vertex coordinates after superimposing the two transition areas.

[0171] Figure 8 This is a schematic diagram of another vertex coordinate position provided in an embodiment of the present application. Figure 8 , the width of the second transition area is W2, the width of the first transition area is W12, and the original vertex coordinates (Xi, Yi) corresponding to the vehicle chassis image are point A (X1, Y1), point B (X2, Y2), point C (X3, Y3), and point D (X4, Y4), respectively. The second transition area corresponding to the width of the second transition area W2 is first superimposed, and then the first transition area corresponding to the width of the first transition area W12 is superimposed, and the vertex coordinates after superimposing the two transition areas are obtained. They are point E1 (X5, Y5), point F1 (X6, Y6), point G1 (X7, Y7), and point H1 (X8, Y8).

[0172] S707 , extracting a predicted chassis area image from the panoramic image at the previous moment according to the vertex coordinates and the rotation and translation matrix.

[0173] For example, according to the rotation and translation matrix RT1, the coordinates of the vertex points E1 (X5, Y5), F1 (X6, Y6), G1 (X7, Y7), and H1 (X8, Y8) can be transformed to obtain the predicted chassis area image at the previous moment, and the predicted chassis area image can be cut out from the panoramic image at the previous moment.

[0174] S708. Based on the original vertex coordinates of the vehicle chassis image, the predicted chassis area image is superimposed on the area where the vehicle chassis is located in the bird's-eye view image at the current moment to obtain a panoramic image of the vehicle.

[0175] It should be noted that the execution process of step S708 can refer to step S407, which will not be described in detail here.

[0176] S709. Perform chassis perspective rendering according to the panoramic image, wherein, when rendering, the portion corresponding to the second transition area in the predicted chassis area image has the highest transparency, and when rendering the portion corresponding to the first transition area in the predicted chassis area image, the transparency value gradually decreases from the inside to the outside.

[0177] In this step, chassis perspective rendering can be performed based on the panoramic image. In a specific implementation, the highest transparency, i.e., the maximum transparency value, can be used to render the portion corresponding to the second transition area in the predicted chassis area image; and the portion corresponding to the first transition area in the predicted chassis area image can be rendered from the inside to the outside with gradually decreasing transparency values.

[0178] For example, when performing chassis perspective rendering on the generated panoramic image, the highest transparency, that is, the transparency value of 1, can be used to render the portion corresponding to the second transition area in the predicted chassis area image; when rendering the portion corresponding to the first transition area in the predicted chassis area image, the transparency value gradually decreases from 1 on the inner side of the first transition area to 0 on the outer side.

[0179] In an embodiment of the present application, the vertex coordinates of the width of two transition areas superimposed around the vehicle chassis image can be obtained, and the predicted chassis area image can be intercepted from the panoramic image at the previous moment according to the vertex coordinates and the rotation and translation matrix. The predicted chassis area image is superimposed on the area where the vehicle chassis is located in the bird's-eye view image at the current moment to form a panoramic image of the vehicle. When performing chassis perspective rendering, the transparency of the second transition area is the highest, and the transparency of the first transition area gradually decreases from the inside to the outside. In the above process, when performing chassis perspective rendering, the transparency of the second transition area is the highest, and the transparency of the first transition area gradually decreases, which can more naturally achieve a smooth transition between different image areas and improve the visual effect of the chassis image in the panoramic image.

[0180] Fig. 9 This is a schematic diagram of the process of determining the predicted chassis area image provided by the embodiment of the present application. Fig. 9 Through step ①, the width of the projection mask area can be determined, through step ②, the motion matrix can be determined, through step ③, the width of the gradient transition area can be determined, through step ④, the vertex coordinates of the original rectangle can be determined, through step ⑤, the vertex coordinates of the dynamic rectangle can be determined, and through step ⑥, the predicted position of the chassis area can be determined.

[0181] In the specific implementation of step ①, the width of the projection coverage area can be determined by querying the angle-wheel projection mapping table according to the steering wheel angle. The mapping relationship between the preset angle and the transition area width is calibrated in the angle-wheel projection mapping table, and the projection coverage area width is the second transition area width.

[0182] In the specific implementation of step ②, the motion matrix can be determined according to the steering wheel angle and the vehicle speed, wherein the motion matrix is ​​a rotation and translation matrix.

[0183] In the specific implementation of step ③, the width of the gradual transition area can be determined according to the vehicle speed, wherein the width of the gradual transition area is the width of the first transition area.

[0184] In the specific implementation of step ④, the original rectangle vertex coordinates can be determined according to the vehicle body parameters, including vehicle width, vehicle length, and blind spot size. The original rectangle vertex coordinates are the vertex coordinates of the vehicle chassis image without the superimposed transition area.

[0185] In the specific implementation of step ⑤, the vertex coordinates can be obtained by superimposing the projection masking area width around the vehicle chassis image and then superimposing the gradient transition area width according to the original rectangle vertex coordinates (original vertex coordinates). According to the vertex coordinates and the motion matrix (rotation and translation matrix), the dynamic rectangle vertex coordinates can be determined. Among them, the dynamic rectangle vertex coordinates are the vertex coordinates of the predicted chassis area image.

[0186] In the specific implementation of step ⑥, the predicted position of the chassis area can be determined from the panoramic image at the previous moment according to the coordinates of the dynamic rectangle vertices.

[0187] The specific process of determining the predicted chassis area image provided in the embodiment of the present application can refer to the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar and will not be repeated here.

[0188] Fig.10 This is a schematic diagram of the process of viewing the vehicle chassis provided by the embodiment of the present application. Fig.10 In step ①, the bird's-eye view image obtained at the current moment can be cached; in step ②, the predicted chassis area image can be intercepted from the panoramic image cached at the previous moment; in step ③, the intercepted predicted chassis area image can be superimposed on the bird's-eye view image at the current moment to obtain the panoramic image at the current moment; in step ④, the second transition area width and the position (corresponding vertex coordinates) of the predicted chassis area image to be rendered can be determined according to the steering wheel angle; in step ⑤, the rendering position of the predicted chassis area image in the panoramic image at the current moment can be determined; in step ⑥, the panoramic image can be rendered according to the determined rendering position; in step ⑦, after the rendering of the panoramic image at the current moment is completed, the image in the cache at the current moment can be exchanged to the cache at the previous moment, so as to prepare for the panoramic image rendering for the next moment of the current moment.

[0189] In the specific implementation of step ①, the current moment cache and the previous moment cache can be set in the cache of the cockpit domain controller. When the bird's-eye view image of the current moment is obtained, the bird's-eye view image of the current moment can be cached in the current moment cache.

[0190] In the specific implementation of step ②, the predicted chassis area image in the panoramic image at the previous moment can be intercepted from the cache at the previous moment.

[0191] In the specific implementation of step ③, the predicted chassis area image can be superimposed on the bird's-eye view image cached at the current moment to obtain a panoramic image at the current moment.

[0192] In the specific implementation of step ④, the second transition area width corresponding to the width of the wheel exposed at the current moment in the bird's-eye view image can be obtained based on the vehicle body parameters, steering wheel angle, and angle-wheel projection mapping table. When rendering, the superimposed second transition area width is intercepted from the predicted chassis area image for rendering position (corresponding vertex coordinates).

[0193] In an optional embodiment, if the steering wheel angle indicates the steering wheel rotation of the vehicle, and the steering wheel rotation only acts on the front axle of the vehicle, that is, only the front wheels of the vehicle rotate, the second transition area can also be determined based on the wheel center of the front wheel and the outer edge coordinates of the front wheel.

[0194] Fig.11 This is a schematic diagram of the coordinate positions of the vertices of the special-shaped transparent chassis provided in the embodiment of the present application. Fig.11 When only the front wheels of the vehicle rotate, the second transition area width W2 can be determined according to the steering wheel angle and the steering angle-wheel projection mapping table, the left front wheel center point K1, and the left front wheel outer edge M1, as shown in the shaded part. Among them, the left wheel center point K1 and the right front wheel centerline point K2 have the same ordinate in the Y-axis direction, and the ordinate value is Y1, and the left front wheel outer edge M1 and the right front wheel outer edge M2 have the same ordinate in the Y-axis direction, and the ordinate value is Y2.

[0195] In the specific implementation of step ⑤, the rendering area can be determined according to the position of the second transition area (corresponding vertex coordinates) and the panoramic image composed of the bird's-eye view image and the predicted chassis area image. Specifically, the portion corresponding to the second transition area has the highest transparency.

[0196] In the specific implementation of step ⑥, the panoramic image can be rendered according to the determined rendering area to obtain a rendered panoramic image. When rendering, the portion corresponding to the second transition area in the predicted chassis area image has the highest transparency, and when rendering the portion corresponding to the first transition area in the predicted chassis area image, the transparency value gradually decreases from the inside to the outside.

[0197] The specific process of vehicle chassis perspective provided in the embodiment of the present application can refer to the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar and will not be repeated here.

[0198] Fig.12 This is a schematic diagram of the structure of the vehicle chassis perspective device provided in the embodiment of the present application. Fig.12 The vehicle chassis perspective device 10 is applied to a cockpit domain controller, comprising:

[0199] A first determination module 11 is used to determine a rotation and translation matrix according to a steering wheel angle and a vehicle speed of the vehicle, wherein the rotation and translation matrix is ​​used to represent a conversion relationship between chassis coordinates at a current moment and coordinates in a panoramic image at a previous moment;

[0200] A second determination module 12 is used to determine the vertex coordinates of the vehicle chassis image according to a preset transition rule, wherein the vertex coordinates are the coordinates of the vertices after a transition area is superimposed around the vehicle chassis image;

[0201] A first processing module 13 is used to extract a predicted chassis area image from the panoramic image at a previous moment according to the vertex coordinates and the rotation and translation matrix;

[0202] The second processing module 14 is used to superimpose the predicted chassis area image on the bird's-eye view image at the current moment to perform chassis perspective rendering, wherein a portion of the predicted chassis area image corresponding to the superimposed transition area is rendered with a gradual transparency.

[0203] The vehicle chassis perspective device provided in the embodiment of the present application can implement the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.

[0204] In a possible implementation manner, the second determining module 12 is specifically configured to:

[0205] Determining original vertex coordinates of the vehicle chassis image based on the body parameters and projection ratio of the vehicle;

[0206] Calculating a first transition area width according to the vehicle speed, a preset minimum vehicle speed threshold, and a preset maximum vehicle speed threshold;

[0207] According to the original vertex coordinates, the coordinates of the vertices after the first transition area corresponding to the first transition area width is superimposed around the vehicle chassis image are acquired to obtain the vertex coordinates.

[0208] In a possible implementation manner, the second determining module 12 is specifically configured to:

[0209] If the steering wheel angle indicates that the steering wheel of the vehicle is rotated, determining a second transition region width according to the steering wheel angle;

[0210] According to the original vertex coordinates, the coordinates of the vertices after superimposing the second transition area corresponding to the width of the second transition area around the vehicle chassis image and the first transition area of ​​the width of the first transition area are obtained to obtain the vertex coordinates.

[0211] In a possible implementation manner, the second determining module 12 is specifically configured to:

[0212] If the vehicle speed is less than the minimum vehicle speed threshold, determining the first transition area width to be a preset minimum transition width;

[0213] If the vehicle speed is greater than or equal to the minimum vehicle speed threshold and less than the maximum vehicle speed threshold, the first transition area width is calculated according to the difference between the maximum vehicle speed threshold and the minimum vehicle speed threshold and the vehicle speed;

[0214] If the vehicle speed is greater than or equal to the maximum vehicle speed threshold, the first transition area width is determined to be a preset maximum transition width.

[0215] In a possible implementation manner, the second processing module 14 is specifically configured to:

[0216] Based on the original vertex coordinates of the vehicle chassis image, superimposing the predicted chassis area image onto the area where the vehicle chassis is located in the bird's-eye view image at the current moment to obtain a panoramic image of the vehicle;

[0217] The chassis perspective rendering is performed according to the panoramic image, wherein when rendering, when rendering the portion corresponding to the first transition area in the predicted chassis area image, the transparency value gradually decreases from the inside to the outside.

[0218] In a possible implementation manner, the second processing module 14 is specifically configured to:

[0219] Based on the original vertex coordinates of the vehicle chassis image, superimposing the predicted chassis area image onto the area where the vehicle chassis is located in the bird's-eye view image at the current moment to obtain a panoramic image of the vehicle;

[0220] The chassis perspective rendering is performed according to the panoramic image, wherein, when rendering, the portion corresponding to the second transition area in the predicted chassis area image has the highest transparency, and when rendering the portion corresponding to the first transition area in the predicted chassis area image, the transparency value gradually decreases from the inside to the outside.

[0221] In a possible implementation manner, the second determining module 12 is specifically configured to:

[0222] According to a preset mapping relationship between the turning angle and the transition area width, the second transition area width corresponding to the steering wheel turning angle is queried.

[0223] In a possible implementation manner, the first determining module 11 is specifically configured to:

[0224] Determine the vehicle turning radius corresponding to the steering wheel angle at a previous moment according to a calibration relationship between the steering wheel angle and the vehicle turning radius, determine the angle offset according to the vehicle turning radius, and determine the displacement change according to the vehicle speed at a previous moment;

[0225] The rotation and translation matrix is ​​constructed according to the angle offset and the displacement change.

[0226] The vehicle chassis perspective device provided in the embodiment of the present application can implement the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.

[0227] Fig.13 This is a schematic diagram of the structure of the cockpit domain controller provided in the embodiment of the present application. Fig.13 The cockpit domain controller 20 may include a processor 21, a memory 22 and a communication interface 24. Exemplarily, the processor 21, the memory 22 and the communication interface 24 are interconnected via a bus 23.

[0228] The memory 22 stores computer-executable instructions;

[0229] The processor 21 executes the computer-executable instructions stored in the memory 22, so that the processor 21 executes the vehicle chassis perspective method provided by the above method embodiment.

[0230] The present application also provides a vehicle, including a vehicle body and Fig.12 The cockpit domain controller shown is used to execute the vehicle chassis perspective method in the above method embodiment.

[0231] Accordingly, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the vehicle chassis perspective method provided by any of the above method embodiments.

[0232] Accordingly, an embodiment of the present application may also provide a computer program product, including a computer program, which, when executed by a processor, can implement the vehicle chassis perspective method provided by any of the above method embodiments.

[0233] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0234] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A vehicle chassis perspective method, characterized in that: include: Determining a rotation and translation matrix based on the vehicle's steering wheel angle and speed, wherein the rotation and translation matrix is ​​used to represent a conversion relationship between chassis coordinates at a current moment and coordinates in a panoramic image at a previous moment; Determining vertex coordinates of the vehicle chassis image according to a preset transition rule, wherein the vertex coordinates are coordinates of the vertices after a transition region is superimposed around the vehicle chassis image; Cutting out a predicted chassis area image from the panoramic image at a previous moment according to the vertex coordinates and the rotation and translation matrix; The predicted chassis area image is superimposed on the bird's-eye view image at the current moment to perform chassis perspective rendering, wherein a portion of the predicted chassis area image corresponding to the superimposed transition area is rendered with a transparency gradient.

2. The method according to claim 1, characterized in that Determining the vertex coordinates of the vehicle chassis image according to a preset transition rule includes: Determining original vertex coordinates of the vehicle chassis image based on the vehicle body parameters and projection ratio; Calculating a first transition region width based on the vehicle speed, a preset minimum vehicle speed threshold, and a preset maximum vehicle speed threshold; According to the original vertex coordinates, the coordinates of the vertex after the first transition area corresponding to the width of the first transition area is superimposed around the vehicle chassis image are acquired to obtain the vertex coordinates.

3. The method according to claim 2, characterized in that The method further comprises: If the steering wheel angle indicates that the steering wheel of the vehicle has rotated, determining a second transition region width based on the steering wheel angle; Accordingly, the step of obtaining the coordinates of the vertex after the first transition area corresponding to the width of the first transition area is superimposed around the vehicle chassis image based on the original vertex coordinates to obtain the vertex coordinates includes: According to the original vertex coordinates, the coordinates of the vertex after superimposing the second transition area corresponding to the width of the second transition area around the vehicle chassis image and the first transition area corresponding to the width of the first transition area are obtained to obtain the vertex coordinates.

4. The method according to claim 2, characterized in that The calculating of the first transition region width according to the vehicle speed, a preset minimum vehicle speed threshold, and a preset maximum vehicle speed threshold includes: If the vehicle speed is less than the minimum vehicle speed threshold, determining the first transition area width to be a preset minimum transition width; If the vehicle speed is greater than or equal to the minimum vehicle speed threshold and less than the maximum vehicle speed threshold, calculating the first transition region width according to the difference between the maximum vehicle speed threshold and the minimum vehicle speed threshold, and the vehicle speed; If the vehicle speed is greater than or equal to the maximum vehicle speed threshold, the first transition area width is determined to be a preset maximum transition width.

5. The method according to claim 2 or 4, characterized in that The step of superimposing the predicted chassis area image onto the bird's-eye view image at the current moment to perform chassis perspective rendering includes: Based on the original vertex coordinates of the vehicle chassis image, superimposing the predicted chassis area image onto the area where the vehicle chassis is located in the bird's-eye view image at the current moment to obtain a panoramic image of the vehicle; A chassis perspective rendering is performed according to the panoramic image, wherein, during the rendering, when rendering the portion corresponding to the first transition area in the predicted chassis area image, the transparency value gradually decreases from the inside to the outside.

6. The method according to claim 3, characterized in that The step of superimposing the predicted chassis area image onto the bird's-eye view image at the current moment to perform chassis perspective rendering includes: Based on the original vertex coordinates of the vehicle chassis image, superimposing the predicted chassis area image onto the area where the vehicle chassis is located in the bird's-eye view image at the current moment to obtain a panoramic image of the vehicle; Chassis perspective rendering is performed based on the panoramic image, wherein, during rendering, the portion corresponding to the second transition area in the predicted chassis area image has the highest transparency, and the transparency value gradually decreases from the inside to the outside when rendering the portion corresponding to the first transition area in the predicted chassis area image.

7. The method according to claim 3 or 6, characterized in that The determining of the width of the second transition region according to the steering wheel angle includes: According to a preset mapping relationship between the steering angle and the transition area width, the second transition area width corresponding to the steering wheel angle is queried.

8. The method according to any one of claims 1 to 4, characterized in that Determining the rotation and translation matrix according to the steering wheel angle and vehicle speed of the vehicle includes: Determining the vehicle turning radius corresponding to the steering wheel angle at a previous moment based on a calibration relationship between the steering wheel angle and the vehicle turning radius, determining an angle offset based on the vehicle turning radius, and determining a displacement change based on the vehicle speed at a previous moment; The rotation and translation matrix is ​​constructed according to the angle offset and the displacement change.

9. A vehicle chassis perspective device, characterized in that: include: a first determining module, configured to determine a rotation and translation matrix based on a steering wheel angle and a vehicle speed, wherein the rotation and translation matrix represents a conversion relationship between chassis coordinates at a current moment and coordinates in a panoramic image at a previous moment; a second determining module, configured to determine vertex coordinates of the vehicle chassis image according to a preset transition rule, wherein the vertex coordinates are coordinates of the vertices after a transition region is superimposed around the vehicle chassis image; A first processing module is configured to extract a predicted chassis area image from the panoramic image at a previous moment according to the vertex coordinates and the rotation and translation matrix; The second processing module is used to superimpose the predicted chassis area image on the bird's-eye view image at the current moment to perform chassis perspective rendering, wherein the portion of the predicted chassis area image corresponding to the superimposed transition area is rendered with a transparency gradient.

10. A cockpit domain controller, characterized in that: include: processor, memory, and communication interfaces; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the vehicle chassis perspective method according to any one of claims 1 to 8.

11. A vehicle, characterized in that: include: A vehicle body and a cockpit domain controller as claimed in claim 10.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the vehicle chassis perspective method according to any one of claims 1 to 8.

13. A computer program product, characterized in that The invention comprises a computer program, which is used to implement the vehicle chassis perspective method according to any one of claims 1 to 8 when the computer program is executed by a processor.

Citation Information

Cited By

  • Image processing method and device, equipment, vehicle, chip and storage medium

    CN120765520A