Vehicle dynamic trajectory line construction method and device, equipment and storage medium

Abstract

The application discloses a kind of vehicle dynamic trajectory line construction method, device, equipment and storage medium, its method includes: according to vehicle measurement distance obtains perpendicular distance, and according to key angle and perpendicular distance acquisition and each key angle corresponding preview figure;Each preview figure is handled to obtain each edge map, collect multiple target feature points in each edge map, and construct target feature point set corresponding to each key angle based on multiple target feature points;Current angle is obtained, and current angle feature point set is calculated according to current angle, key angle and target feature point set;Current angle point set is calculated according to current angle feature point set;Current angle feature point set and current angle point set are converted into vertex point set;Dynamic trajectory line is constructed according to vertex point set.The application realizes the dynamic construction of vehicle trajectory line in the process of vehicle driving, not only improves the accuracy of dynamic trajectory line, and improves the smoothness when angle switches.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of vehicle driving technology, and in particular to a vehicle dynamic trajectory line construction method, device, equipment and storage medium. BACKGROUND

[0002] At present, the auxiliary trajectory line in the vehicle image system can reduce the difficulty of driving operation, improve the driving experience of users, and has become an indispensable function. The common auxiliary trajectory line construction and drawing forms include the following two kinds: algorithm simulation and real vehicle line drawing.

[0003] Among them, the trajectory line constructed by algorithm simulation is to simulate the driving path according to the vehicle parameters. The construction process is simple, the drawing style is flexible and various, and the switching smoothness is high. But the disadvantage is that the consistency with the vehicle trajectory is poor, and the error is large.

[0004] Among them, the trajectory line constructed by real vehicle line drawing is to sample the actual driving trajectory, which solves the problem of large algorithm error. But the construction process is complicated, and a large amount of data needs to be processed manually after sampling, which is low in efficiency. The data is stored in the form of pictures, resulting in fixed and single style. If the sampling is less, there will be the problem of poor smoothness when the angle switches. SUMMARY

[0005] The embodiments of the present application provide a vehicle dynamic trajectory line construction method, device, equipment and storage medium, which aims to solve the problem of poor consistency between the auxiliary trajectory line in the vehicle image system and the vehicle trajectory line and poor smoothness when the angle switches in the prior art.

[0006] In order to solve the above problems, in a first aspect, the embodiments of the present application provide a vehicle dynamic trajectory line construction method, which comprises: obtaining a perpendicular distance according to a vehicle measurement distance, and collecting a preview picture corresponding to each key angle according to the key angle and the perpendicular distance; processing each preview picture to obtain each edge picture, collecting a plurality of target feature points in each edge picture, and constructing a target feature point set corresponding to each key angle based on the plurality of target feature points; obtaining a current angle, calculating a current angle feature point set according to the current angle, the key angle and the target feature point set; calculating a current angle point set according to the current angle feature point set; converting the current angle feature point set and the current angle point set into a vertex point set; and constructing a dynamic trajectory line according to the vertex point set.

[0007] Secondly, embodiments of this application provide a vehicle dynamic trajectory line construction device, comprising: a preview image acquisition unit, configured to obtain a vertical distance based on a vehicle measurement distance, and acquire a preview image corresponding to each key angle based on a key angle and the vertical distance; a target feature point set construction unit, configured to process each preview image to obtain each edge image, acquire multiple target feature points in each edge image, and construct a target feature point set corresponding to each key angle based on the multiple target feature points; a current angle feature point set calculation unit, configured to obtain a current angle, and calculate a current angle feature point set based on the current angle, the key angle, and the target feature point set; a current angle point set calculation unit, configured to calculate a current angle point set based on the current angle feature point set; a vertex point set conversion unit, configured to convert the current angle feature point set and the current angle point set into a vertex point set; and a dynamic trajectory line construction unit, configured to construct a dynamic trajectory line based on the vertex point set.

[0008] Thirdly, embodiments of this application provide a computer device, the computer device including a memory and a processor connected to the memory; the memory is used to store a computer program, and the processor is used to run the computer program stored in the memory to perform the method described in the first aspect above.

[0009] Fourthly, embodiments of this application provide a storage medium storing a computer program, the computer program including program instructions, which, when executed by a processor, implement the method described in the first aspect above.

[0010] This invention provides a method, apparatus, device, and storage medium for constructing a vehicle dynamic trajectory line, which realizes the dynamic construction of the vehicle trajectory line during vehicle driving, improving not only the accuracy of the dynamic trajectory line but also the smoothness during angle switching. Attached Figure Description

[0011] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A flowchart illustrating the vehicle dynamic trajectory line construction method provided in an embodiment of the present invention;

[0013] Figure 2 A schematic block diagram of a vehicle dynamic trajectory line construction device provided in an embodiment of the present invention;

[0014] Figure 3A schematic block diagram of a computer device provided for an embodiment of the present invention. Detailed Implementation

[0015] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0016] The directional terms used in this invention, such as "up," "down," "front," "back," "left," "right," "inner," "outer," and "side," are merely for reference to the accompanying drawings. Therefore, the directional terms used are for illustrating and understanding this invention, and not for limiting it. Furthermore, in the drawings, structures that are similar or identical are indicated by the same reference numerals.

[0017] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0018] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0019] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0020] Please see Figure 1 , Figure 1 This is a flowchart illustrating the vehicle dynamic trajectory line construction method provided in an embodiment of the present invention. Figure 1 As shown, this embodiment of the invention provides a method for constructing a vehicle dynamic trajectory line, which includes the following steps S110-S160.

[0021] S110. Obtain the vertical distance based on the vehicle measurement distance, and collect a preview image corresponding to each key angle based on the key angle and the vertical distance.

[0022] In this embodiment, when any type of vehicle dynamic trajectory line construction device is set up, the actual parameters of the vehicle are measured and processed to obtain the distance to calculate the vertical distance, and the preview image corresponding to each key angle is collected according to the key angle and the vertical distance, wherein each key angle has a corresponding preview image.

[0023] In the above embodiments, the vertical distance is obtained by secondary calculation based on the distance calculated from the actual parameters of the vehicle, which effectively ensures consistency with the actual trajectory of the vehicle and effectively improves the accuracy of constructing dynamic trajectory lines.

[0024] In one embodiment, the step of obtaining the vertical distance based on the vehicle measurement distance and acquiring a preview image corresponding to each key angle based on the key angle and the vertical distance includes:

[0025] The maximum distance between the edge lines of the two rearview mirrors of the vehicle is taken as the outer distance of the rearview mirror, and the maximum distance between the edge lines of the two symmetrical tires of the vehicle is taken as the outer distance of the tire.

[0026] The vertical distance is calculated using the distance from the outer edge of the rearview mirror and the distance from the outer edge of the tire.

[0027] The key angle is determined based on the preset rotation angle and the preset rotation angle range;

[0028] The tire trajectory line is calibrated based on the aforementioned key angles;

[0029] The vehicle body edge trajectory line is calibrated based on the tire trajectory line and the vertical distance;

[0030] The image acquisition device is invoked and controlled to acquire images based on the tire trajectory line and the vehicle body edge trajectory line to obtain the preview image.

[0031] In this embodiment, the maximum distance between the edge line of the left rearview mirror and the edge line of the right rearview mirror is measured as the outer distance of the rearview mirror, and the maximum distance between the edge line of the left front outer tire and the right front outer tire or the maximum distance between the left rear outer tire and the right rear outer tire is measured as the outer distance of the tire.

[0032] The difference between the outer edge of the rearview mirror and the outer edge of the tire is used as the first distance result, and the quotient of the first distance result and the integer 2 is used as the vertical distance, which is the vertical distance between the outermost projection of the vehicle body and the wheel.

[0033] The preset rotation angle is the angle at which the vehicle's steering wheel rotates each time. The preset rotation angle range is the range of steering wheel rotation angles. Specifically, when the preset rotation angle range is fixed, the smaller the value of the preset rotation angle, the more critical angles there are, resulting in smoother and more accurate tire trajectory lines and vehicle body edge lines. The preset rotation angle can be 90°, 180°, etc., and the preset rotation angle range can be [-540°, 540°], etc. If the preset rotation angle range is [-540°, 540°], and the preset rotation angle is 180°, then the critical angles include -540°, -360°, -180°, 0°, 180°, 360°, and 540°.

[0034] The tire trajectory lines are calibrated based on the key angles. If the preset rotation angle range is [-540°, 540°], and the preset rotation angle is 180°, when the vehicle's steering wheel is rotated to each key angle (including -540°, -360°, -180°, 0°, 180°, 360°, and 540°), the tire trajectory lines are calibrated. The vehicle body edge trajectory lines are then calibrated based on the tire trajectory lines and the vertical distance. Generally, the preview image corresponding to each key angle includes four tire trajectory lines and two vehicle body edge trajectory lines. Specifically, the preview image includes the left outer tire trajectory line, left inner tire trajectory line, right inner tire trajectory line, right outer tire trajectory line, left vehicle body edge trajectory line, and right vehicle body edge trajectory line.

[0035] When the vehicle's steering wheel is turned to each key angle to calibrate the tire trajectory line and the vehicle body edge trajectory line, an image acquisition device is invoked and controlled to acquire images based on the tire trajectory line and the vehicle body edge trajectory line to obtain the preview image. That is, each key angle corresponds to one preview image, and each preview image includes the tire trajectory line and the vehicle body edge line.

[0036] In the above embodiments, the vertical distance is obtained by secondary calculation based on the distance calculated from the actual parameters of the vehicle. The key angle is determined by the preset rotation angle and preset rotation angle range of the vehicle. The tire trajectory line and the vehicle body edge trajectory line are calibrated based on the key angle and the vertical distance. An image acquisition device is invoked and controlled to acquire images based on the tire trajectory line and the vehicle body edge trajectory line to obtain the preview image. The preview image is obtained based on the actual parameters of the vehicle, which ensures consistency with the actual trajectory of the vehicle and effectively improves the accuracy of constructing dynamic trajectory lines.

[0037] S120. Process each preview image to obtain each edge image, collect multiple target feature points in each edge image, and construct a target feature point set corresponding to each key angle based on the multiple target feature points.

[0038] In this embodiment, each preview image is processed to obtain each edge image. Since the preview images may be affected by factors such as sunlight, environment and road surface, resulting in unclear tire trajectory lines and vehicle body edge lines or other problems, each processed edge image is less affected by external factors, which is beneficial for subsequent dynamic trajectory line construction operations.

[0039] In one embodiment, processing each preview image to obtain each edge image includes:

[0040] Convert each preview image to grayscale;

[0041] A filtered grayscale image is obtained by removing noise from the grayscale image using bilateral filtering.

[0042] Edge detection processing is performed on the filtered grayscale image based on the Laplacian operator to obtain each edge image.

[0043] In this embodiment, an image processing device is invoked to convert each preview image into a grayscale image (a grayscale image, also known as a gray-scale image, is a representation of a grayscale image by dividing the white and black regions into several levels according to a logarithmic relationship; grayscale has 256 levels. An image represented by grayscale is called a grayscale image), and bilateral filtering is applied. The filter method is a non-linear filtering approach that combines spatial proximity and pixel value similarity in an image, taking into account both spatial information and grayscale similarity to achieve edge-preserving denoising. Noise is removed from the grayscale image to obtain the filtered grayscale image. Then, based on the Laplace operator (a second-order differential operator in n-dimensional Euclidean space, defined as the divergence (▽•f) of the gradient (▽f). The Laplace operator can also be generalized to an elliptic operator defined on a Riemannian manifold, called the Laplace-Beltrammian operator), edge detection (edge ​​detection identifies points with significant brightness changes in a digital image) is performed on the filtered grayscale image to obtain relatively clear edge maps for the tire trajectory lines and the vehicle body edge trajectory lines.

[0044] Through the above embodiments, the preview image is processed to obtain an edge image with clearer boundaries, which makes subsequent operations more accurate, effectively improves the accuracy of constructing dynamic trajectory lines, and effectively improves the smoothness when switching angles.

[0045] In one embodiment, the step of collecting multiple target feature points in each edge map and constructing a target feature point set corresponding to each key angle based on the multiple target feature points includes:

[0046] Obtain the trajectory line in each edge map as at least one target trajectory line;

[0047] A predetermined number of points are collected on each of the at least one target trajectory line as the plurality of target feature points;

[0048] The target feature point set corresponding to each key angle is constructed using the multiple target feature points.

[0049] In this embodiment, the tire trajectory line and the vehicle body edge trajectory line in each edge map are obtained as at least one target trajectory line. A preset number of points on each of the at least one target trajectory line are collected as the plurality of target feature points. The preset number is a positive integer greater than or equal to 2. Preferably, the preset number is 4, that is, the preset number of points on each target trajectory line includes 4 points. Four points are collected on each target trajectory line. The target feature points include a start point, a first control point, a second control point, and an end point. The plurality of target feature points are used to construct the target feature point set corresponding to each key angle. Among them, the target trajectory lines include 4 tire target trajectory lines and 2 vehicle body edge target trajectory lines. Specifically, the target trajectory lines include the left outer tire target trajectory line, the left inner tire target trajectory line, the right inner tire target trajectory line, the right outer tire target trajectory line, the left vehicle body target edge trajectory line, and the right vehicle body target edge trajectory line.

[0050] Through the above embodiments, multiple target feature points are collected on at least one target trajectory line in each edge map, and the multiple target feature points are used to construct the target feature point set corresponding to each key angle. Preferably, four points are collected on each target trajectory line. The four points can roughly determine the trajectory direction of a line. This saves storage space and effectively improves the accuracy of constructing dynamic trajectory lines and the smoothness when switching angles.

[0051] S130. Obtain the current angle, and calculate the current angle feature point set based on the current angle, the key angle, and the target feature point set.

[0052] In this embodiment, the current angle feature point set is calculated using interpolation based on the acquired current angle, the key angle, and the target feature point set. Interpolation is an important method for approximating discrete functions; it allows estimation of the approximate value of a function at other points by considering the function's values ​​at a finite number of points. This effectively improves the accuracy of constructing dynamic trajectory lines and enhances the smoothness of angle switching.

[0053] In one embodiment, obtaining the current angle and calculating the current angle feature point set based on the current angle, the key angle, and the target feature point set includes:

[0054] The current steering angle of the vehicle is obtained as the current angle;

[0055] Obtain two key angles adjacent to the current angle as the first adjacent key angle and the second adjacent key angle;

[0056] Obtain the set of target feature points corresponding to the first adjacent key angle as the first adjacent key angle feature point set;

[0057] Obtain the set of target feature points corresponding to the second adjacent key angle as the second adjacent key angle feature point set;

[0058] The current angle feature point set is calculated based on the current angle, the first adjacent key angle, the first adjacent key angle feature point set, and the second adjacent key angle feature point set.

[0059] In this embodiment, the current steering wheel rotation angle of the vehicle is obtained as the current angle. Based on the current angle, two key angles related to it are obtained as the first adjacent key angle and the second adjacent key angle. The first adjacent key angle is smaller than the second adjacent key angle. Based on the first adjacent key angle, the target feature point set corresponding to it is obtained as the first adjacent key angle feature point set. Based on the second adjacent key angle, the target feature point set corresponding to it is obtained as the second adjacent key angle feature point set.

[0060] The difference between the current angle and the first adjacent key angle is taken as the first angle difference, and the quotient of the first angle difference and the preset rotation angle is taken as the angle ratio. Taking the preset number as an example, that is, when the preset number is equal to 4, the target feature points on each target trajectory line include a start point, a first control point, a second control point, and an end point. The abscissa of the target feature point on the left outer tire trajectory line of the target trajectory line in the first adjacent key angle feature point set is taken as the abscissa of the first adjacent key angle. The abscissa of the target feature point on the left outer tire trajectory line of the target trajectory line in the second adjacent key angle feature point set is taken as the abscissa of the second adjacent key angle. The ordinate of the target feature point on the left outer tire trajectory line of the target trajectory line in the first adjacent key angle feature point set is taken as the ordinate of the first adjacent key angle. The ordinate of the target feature point on the left outer tire trajectory line of the target trajectory line in the second adjacent key angle feature point set is taken as the ordinate of the first adjacent key angle. The calculation process is as follows: the difference between the horizontal coordinate of the second adjacent key angle and the horizontal coordinate of the first adjacent key angle is used as the first horizontal coordinate; the product of the first horizontal coordinate and the angle ratio is used as the second horizontal coordinate; the sum of the second horizontal coordinate and the horizontal coordinate of the first adjacent key angle is used as the horizontal coordinate of the current angle feature point of the left outer tire trajectory line in the current angle feature point set; the difference between the vertical coordinate of the second adjacent key angle and the vertical coordinate of the first adjacent key angle is used as the first vertical coordinate; the product of the first vertical coordinate and the angle ratio is used as the second vertical coordinate; the sum of the second vertical coordinate and the vertical coordinate of the first adjacent key angle is used as the vertical coordinate of the current angle feature point of the left outer tire trajectory line in the current angle feature point set; the horizontal coordinate and the vertical coordinate constitute the current angle feature point; the starting point, the first control point, the second control point, and the ending point on the left outer tire trajectory line are calculated sequentially. Similarly, following the above calculation process, multiple current angle feature points can be calculated for each of the following current angle feature point sets: the left inner tire target trajectory line, the right inner tire target trajectory line, the right outer tire target trajectory line, the left vehicle body target edge trajectory line, and the right vehicle body target edge trajectory line. These can then be used as the current angle feature point set.

[0061] Through the above embodiments, during vehicle operation, the current angle feature point set is calculated based on the current angle, the key angle, and the target feature point set. Since the key angle and the target feature points are calculated based on the actual parameters of the vehicle, the data of the current angle feature point set is accurate. This effectively improves the consistency with the actual trajectory of the vehicle, effectively improves the accuracy of constructing dynamic trajectory lines, and effectively improves the smoothness when switching angles.

[0062] S140. Calculate the current angle point set based on the current angle feature point set.

[0063] In this embodiment, the current angle feature point set is calculated using data such as the target feature point set calibrated with actual parameters, and the current angle point set is calculated using the current angle feature point set. This effectively ensures consistency with the actual vehicle trajectory, effectively improves the accuracy of constructing dynamic trajectory lines, and effectively improves the smoothness during angle switching.

[0064] In one embodiment, calculating the current angle point set based on the current angle feature point set includes:

[0065] Obtain the preset number of current angle feature points belonging to the same current angle trajectory line from the current angle feature point set, and obtain the Bézier curve function;

[0066] The curve function of each current angle trajectory line in the current angle feature point set is obtained by using the acquired current angle feature points and the Bézier curve function.

[0067] Each current angle feature point and factor in the current angle feature point set are input into the curve function for calculation to obtain the target point corresponding to each current angle feature point;

[0068] Construct the current angle point set using the target point;

[0069] The factor is any value within the range [0,1].

[0070] In this embodiment, the general parameter formula of the Bézier curve function (Bézier curve, also known as Bézier curve or Bézier curve, is a mathematical curve used in two-dimensional graphics applications) is as follows: Similarly, taking a preset quantity of 4 as an example, when the preset quantity equals 4, the current angle feature point includes the starting point, the first control point, the second control point, and the ending point on the current angle trajectory line; if the preset quantity equals 4, then n equals the preset quantity - 1, that is, n equals 3, where n represents the order of the Bézier curve function, that is, the Bézier curve function defines a cubic Bézier curve for the four points P0, P1, P2, and P3 in a plane or in three-dimensional space: Where B(t) is the abscissa curve function or ordinate curve function of the current angle trajectory line to which P0, P1, P2 and P3 belong in the current angle feature point set; n represents the order of the Bézier curve function; i∈[0,n]; t is a factor, which is any value in [0,1]; here P0, P1, P2 and P3 are each current angle feature point on the current angle trajectory line in the current angle feature point set: starting point P0, first control point P1, second control point P2 and ending point P3. The current angle trajectory line may include the target trajectory line of the left inner tire, the target trajectory line of the right inner tire, the target trajectory line of the right outer tire, and the target trajectory line of the left side of the vehicle. Multiple current angle feature points are used for the target edge trajectory line of the main body and the target edge trajectory line of the right side of the vehicle body. The x-coordinates and y-coordinates of the starting point P0, the first control point P1, the second control point P2, and the ending point P3 are respectively input into the cubic Bezier curve to obtain the x-coordinate curve function and y-coordinate curve function of the current angle trajectory line. Then, t, which is gradually increased with a preset precision value, is input into the x-coordinate curve function and the y-coordinate curve function to obtain the target point corresponding to each current angle feature point. The preset precision value can be 0.1, 0.01, or 0.001, etc. The current angle point set is constructed using the multiple target points obtained by calculation.

[0071] Through the above embodiments, during vehicle operation, since the key angle and the target feature point are calculated based on the actual parameters of the vehicle, and the current angle feature point set is calculated based on the current angle, the key angle, and the target feature point set, and the current angle point set is calculated using the Bezier curve function, the preset precision value and the preset quantity determine and accurately the smoothness of the dynamic trajectory line. Therefore, the data of the current angle point set is accurate, which effectively improves the consistency with the actual trajectory line of the vehicle. This not only effectively improves the accuracy of constructing the dynamic trajectory line, but also effectively improves the smoothness when switching angles.

[0072] S150. Convert the current angle feature point set and the current angle point set into a vertex point set.

[0073] In this embodiment, both the current angle feature point set and the current angle point set are screen coordinates. The screen coordinates need to be converted to vertex coordinates. The conversion process is as follows: The width of the vehicle's display screen is taken as the screen width, and the height of the display screen is taken as the screen height. The quotient of the x-coordinate of the current angle feature point set or the current angle point set and an integer 2 is taken as the first vertex x-coordinate. The difference between the first vertex x-coordinate and the screen width is taken as the second vertex x-coordinate. The quotient of the second vertex x-coordinate and the screen width is taken as the vertex x-coordinate. Similarly, the quotient of the y-coordinate of the current angle feature point set or the current angle point set and an integer 2 is taken as the first vertex y-coordinate. The difference between the first vertex y-coordinate and the screen height is taken as the second vertex y-coordinate. The quotient of the second vertex y-coordinate and the screen height is taken as the vertex y-coordinate.

[0074] Through the above embodiments, the vertex point set is obtained by calculating the current angle feature point set and the current angle point set through the specific data of the display screen. Therefore, the data of the vertex point set is accurate, which effectively improves the consistency with the actual trajectory line of the vehicle. This not only effectively improves the accuracy of constructing dynamic trajectory lines, but also effectively improves the smoothness when switching angles.

[0075] S160. Construct a dynamic trajectory line based on the vertex set.

[0076] In this embodiment, the vertex point set is the result set obtained by performing calculations on the current angle feature point set, the current angle point set, the screen width, and the screen height. The current angle feature point set and the current angle point set are the target feature point set on the target trajectory line calibrated by the actual parameters of the vehicle. This indicates that the vertex point set is close to the actual trajectory line, which effectively improves the accuracy of constructing dynamic trajectory lines.

[0077] In one embodiment, constructing a dynamic trajectory line based on the vertex set includes:

[0078] The transparency of the corresponding vertices in the vertex set is calculated based on the factor and the preset transparency range, and the gradient fill color of the dynamic trajectory line is determined based on the transparency.

[0079] The area of ​​the corresponding vertex is calculated based on the factor and the preset line width range, and the line width of the dynamic trajectory line is determined based on the area.

[0080] Configure the effective display range of the warning line in the dynamic trajectory line according to the x-coordinate of the vertex of the current angle trajectory line in the vertex point set.

[0081] In this embodiment, specifically, a shader device is invoked to construct the dynamic trajectory line from the set of vertices. Each factor corresponds to a vertex, and the factor is any value within [0,1]. The preset transparency range is set between a first preset transparency and a second preset transparency, wherein the first preset transparency is greater than or equal to the second preset transparency. The transparency calculation process for each factor-corresponding vertex is as follows: the difference between the first preset transparency and the second preset transparency is used as the first transparency; the product of the first transparency and the factor is used as the second transparency; the sum of the second transparency and the second preset transparency is used as the transparency of each factor-corresponding vertex; and the gradient fill color of the dynamic trajectory line is determined by the transparency of each vertex.

[0082] The shader device is invoked to construct the dynamic trajectory line from the set of vertices. Each factor corresponds to a vertex, and the factor is any value within [0,1]. The preset line width range is set between a first preset line width and a second preset line width, wherein the first preset line width is greater than or equal to the second preset line width. The area calculation process for the vertex corresponding to each factor is as follows: the difference between the first preset line width and the second preset line width is used as the first vertex line width; the product of the first vertex line width and the factor is used as the second vertex line width; the sum of the second vertex line width and the second preset line width is used as the area of ​​the vertex corresponding to each factor; and the line width of the dynamic trajectory line is determined by the area of ​​each vertex.

[0083] The shader device is invoked to construct the dynamic trajectory line from the set of vertices. The current angle trajectory line includes the target trajectory line of the left inner tire, the target trajectory line of the right inner tire, the target trajectory line of the right outer tire, the target edge trajectory line of the left vehicle body, and the target edge trajectory line of the right vehicle body. Based on the x-coordinates of the vertices of the target edge trajectory lines of the left and right vehicle body in the current angle trajectory line in the set of vertices, the effective display range of the warning line in the dynamic trajectory line is configured.

[0084] Through the above embodiments, by calling the shader device, the gradient fill color, line width, and warning line of the dynamic trajectory line are constructed through a series of calculations based on preset data, making the dynamic trajectory line more accurate. This effectively improves the consistency with the actual trajectory line of the vehicle, not only effectively improving the accuracy of constructing the dynamic trajectory line, but also effectively improving the smoothness when switching angles.

[0085] As can be seen, the embodiments of this method achieve the following: during vehicle movement, the vertical distance is obtained based on the measured distance of the vehicle; preview images corresponding to each key angle are acquired based on key angles and the vertical distance; each preview image is processed to obtain each edge image; multiple target feature points are acquired in each edge image; a target feature point set corresponding to each key angle is constructed based on the multiple target feature points; the current angle is obtained; a current angle feature point set is calculated based on the current angle, the key angle, and the target feature point set; a current angle point set is calculated based on the current angle feature point set; the current angle feature point set and the current angle point set are converted into a vertex point set; and a dynamic trajectory line is constructed based on the vertex point set. This invention achieves dynamic construction of vehicle trajectory lines during vehicle movement, which not only improves the accuracy of dynamic trajectory lines but also improves the smoothness during angle switching.

[0086] Please see Figure 2 , Figure 2 This is a schematic block diagram of a vehicle dynamic trajectory line construction device provided in an embodiment of the present invention. Figure 2 As shown, this embodiment of the invention provides a vehicle dynamic trajectory line construction device that implements the method described above. The vehicle dynamic trajectory line construction device operates in terminals such as vehicles and vehicle imaging systems. The vehicle dynamic trajectory line construction device 100 includes a preview image acquisition unit 110, a target feature point set construction unit 120, a current angle feature point set calculation unit 130, a current angle point set calculation unit 140, a vertex point set conversion unit 150, and a dynamic trajectory line construction unit 160.

[0087] The preview image acquisition unit 110 obtains the vertical distance based on the vehicle measurement distance, and acquires a preview image corresponding to each key angle based on the key angle and the vertical distance.

[0088] In this embodiment, when any type of vehicle dynamic trajectory line construction device is set up, the actual parameters of the vehicle are measured and processed to obtain the distance to calculate the vertical distance, and the preview image corresponding to each key angle is collected according to the key angle and the vertical distance, wherein each key angle has a corresponding preview image.

[0089] In the above embodiments, the vertical distance is obtained by secondary calculation based on the distance calculated from the actual parameters of the vehicle, which effectively ensures consistency with the actual trajectory of the vehicle and effectively improves the accuracy of constructing dynamic trajectory lines.

[0090] In one embodiment, the step of obtaining the vertical distance based on the vehicle measurement distance and acquiring a preview image corresponding to each key angle based on the key angle and the vertical distance includes:

[0091] The maximum distance between the edge lines of the two rearview mirrors of the vehicle is taken as the outer distance of the rearview mirror, and the maximum distance between the edge lines of the two symmetrical tires of the vehicle is taken as the outer distance of the tire.

[0092] The vertical distance is calculated using the distance from the outer edge of the rearview mirror and the distance from the outer edge of the tire.

[0093] The key angle is determined based on the preset rotation angle and the preset rotation angle range;

[0094] The tire trajectory line is calibrated based on the aforementioned key angles;

[0095] The vehicle body edge trajectory line is calibrated based on the tire trajectory line and the vertical distance;

[0096] The image acquisition device is invoked and controlled to acquire images based on the tire trajectory line and the vehicle body edge trajectory line to obtain the preview image.

[0097] In this embodiment, the maximum distance between the edge line of the left rearview mirror and the edge line of the right rearview mirror is measured as the outer distance of the rearview mirror, and the maximum distance between the edge line of the left front outer tire and the right front outer tire or the maximum distance between the left rear outer tire and the right rear outer tire is measured as the outer distance of the tire.

[0098] The difference between the outer edge of the rearview mirror and the outer edge of the tire is used as the first distance result, and the quotient of the first distance result and the integer 2 is used as the vertical distance, which is the vertical distance between the outermost projection of the vehicle body and the wheel.

[0099] The preset rotation angle is the angle at which the vehicle's steering wheel rotates each time. The preset rotation angle range is the range of steering wheel rotation angles. Specifically, when the preset rotation angle range is fixed, the smaller the value of the preset rotation angle, the more critical angles there are, resulting in smoother and more accurate tire trajectory lines and vehicle body edge lines. The preset rotation angle can be 90°, 180°, etc., and the preset rotation angle range can be [-540°, 540°], etc. If the preset rotation angle range is [-540°, 540°], and the preset rotation angle is 180°, then the critical angles include -540°, -360°, -180°, 0°, 180°, 360°, and 540°.

[0100] The tire trajectory lines are calibrated based on the key angles. If the preset rotation angle range is [-540°, 540°], and the preset rotation angle is 180°, when the vehicle's steering wheel is rotated to each key angle (including -540°, -360°, -180°, 0°, 180°, 360°, and 540°), the tire trajectory lines are calibrated. The vehicle body edge trajectory lines are then calibrated based on the tire trajectory lines and the vertical distance. Generally, the preview image corresponding to each key angle includes four tire trajectory lines and two vehicle body edge trajectory lines. Specifically, the preview image includes the left outer tire trajectory line, left inner tire trajectory line, right inner tire trajectory line, right outer tire trajectory line, left vehicle body edge trajectory line, and right vehicle body edge trajectory line.

[0101] When the vehicle's steering wheel is turned to each key angle to calibrate the tire trajectory line and the vehicle body edge trajectory line, an image acquisition device is invoked and controlled to acquire images based on the tire trajectory line and the vehicle body edge trajectory line to obtain the preview image. That is, each key angle corresponds to one preview image, and each preview image includes the tire trajectory line and the vehicle body edge line.

[0102] In the above embodiments, the vertical distance is obtained by secondary calculation based on the distance calculated from the actual parameters of the vehicle. The key angle is determined by the preset rotation angle and preset rotation angle range of the vehicle. The tire trajectory line and the vehicle body edge trajectory line are calibrated based on the key angle and the vertical distance. An image acquisition device is invoked and controlled to acquire images based on the tire trajectory line and the vehicle body edge trajectory line to obtain the preview image. The preview image is obtained based on the actual parameters of the vehicle, which ensures consistency with the actual trajectory of the vehicle and effectively improves the accuracy of constructing dynamic trajectory lines.

[0103] The target feature point set construction unit 120 processes each preview image to obtain each edge image, collects multiple target feature points in each edge image, and constructs a target feature point set corresponding to each key angle based on the multiple target feature points.

[0104] In this embodiment, each preview image is processed to obtain each edge image. Since the preview images may be affected by factors such as sunlight, environment and road surface, resulting in unclear tire trajectory lines and vehicle body edge lines or other problems, each processed edge image is less affected by external factors, which is beneficial for subsequent dynamic trajectory line construction operations.

[0105] In one embodiment, processing each preview image to obtain each edge image includes:

[0106] Convert each preview image to grayscale;

[0107] A filtered grayscale image is obtained by removing noise from the grayscale image using bilateral filtering.

[0108] Edge detection processing is performed on the filtered grayscale image based on the Laplacian operator to obtain each edge image.

[0109] In this embodiment, an image processing device is invoked to convert each preview image into a grayscale image (a grayscale image, also known as a gray-scale image, is a representation of a grayscale image by dividing the white and black regions into several levels according to a logarithmic relationship; grayscale has 256 levels. An image represented by grayscale is called a grayscale image), and bilateral filtering is applied. The filter method is a non-linear filtering approach that combines spatial proximity and pixel value similarity in an image, taking into account both spatial information and grayscale similarity to achieve edge-preserving denoising. Noise is removed from the grayscale image to obtain the filtered grayscale image. Then, based on the Laplace operator (a second-order differential operator in n-dimensional Euclidean space, defined as the divergence (▽•f) of the gradient (▽f). The Laplace operator can also be generalized to an elliptic operator defined on a Riemannian manifold, called the Laplace-Beltrammian operator), edge detection (edge ​​detection identifies points with significant brightness changes in a digital image) is performed on the filtered grayscale image to obtain relatively clear edge maps for the tire trajectory lines and the vehicle body edge trajectory lines.

[0110] Through the above embodiments, the preview image is processed to obtain an edge image with clearer boundaries, which makes subsequent operations more accurate, effectively improves the accuracy of constructing dynamic trajectory lines, and effectively improves the smoothness when switching angles.

[0111] In one embodiment, the step of collecting multiple target feature points in each edge map and constructing a target feature point set corresponding to each key angle based on the multiple target feature points includes:

[0112] Obtain the trajectory line in each edge map as at least one target trajectory line;

[0113] A predetermined number of points are collected on each of the at least one target trajectory line as the plurality of target feature points;

[0114] The target feature point set corresponding to each key angle is constructed using the multiple target feature points.

[0115] In this embodiment, the tire trajectory line and the vehicle body edge trajectory line in each edge map are obtained as at least one target trajectory line. A preset number of points on each of the at least one target trajectory line are collected as the plurality of target feature points. The preset number is a positive integer greater than or equal to 2. Preferably, the preset number is 4, that is, the preset number of points on each target trajectory line includes 4 points. Four points are collected on each target trajectory line. The target feature points include a start point, a first control point, a second control point, and an end point. The plurality of target feature points are used to construct the target feature point set corresponding to each key angle. Among them, the target trajectory lines include 4 tire target trajectory lines and 2 vehicle body edge target trajectory lines. Specifically, the target trajectory lines include the left outer tire target trajectory line, the left inner tire target trajectory line, the right inner tire target trajectory line, the right outer tire target trajectory line, the left vehicle body target edge trajectory line, and the right vehicle body target edge trajectory line.

[0116] Through the above embodiments, multiple target feature points are collected on at least one target trajectory line in each edge map, and the multiple target feature points are used to construct the target feature point set corresponding to each key angle. Preferably, four points are collected on each target trajectory line. The four points can roughly determine the trajectory direction of a line. This saves storage space and effectively improves the accuracy of constructing dynamic trajectory lines and the smoothness when switching angles.

[0117] The current angle feature point set calculation unit 130 obtains the current angle and calculates the current angle feature point set based on the current angle, the key angle, and the target feature point set.

[0118] In this embodiment, the current angle feature point set is calculated using interpolation based on the acquired current angle, the key angle, and the target feature point set. Interpolation is an important method for approximating discrete functions; it allows estimation of the approximate value of a function at other points by considering the function's values ​​at a finite number of points. This effectively improves the accuracy of constructing dynamic trajectory lines and enhances the smoothness of angle switching.

[0119] In one embodiment, obtaining the current angle and calculating the current angle feature point set based on the current angle, the key angle, and the target feature point set includes:

[0120] The current steering angle of the vehicle is obtained as the current angle;

[0121] Obtain two key angles adjacent to the current angle as the first adjacent key angle and the second adjacent key angle;

[0122] Obtain the set of target feature points corresponding to the first adjacent key angle as the first adjacent key angle feature point set;

[0123] Obtain the set of target feature points corresponding to the second adjacent key angle as the second adjacent key angle feature point set;

[0124] The current angle feature point set is calculated based on the current angle, the first adjacent key angle, the first adjacent key angle feature point set, and the second adjacent key angle feature point set.

[0125] In this embodiment, the current steering wheel rotation angle of the vehicle is obtained as the current angle. Based on the current angle, two key angles related to it are obtained as the first adjacent key angle and the second adjacent key angle. The first adjacent key angle is smaller than the second adjacent key angle. Based on the first adjacent key angle, the target feature point set corresponding to it is obtained as the first adjacent key angle feature point set. Based on the second adjacent key angle, the target feature point set corresponding to it is obtained as the second adjacent key angle feature point set.

[0126] The difference between the current angle and the first adjacent key angle is taken as the first angle difference, and the quotient of the first angle difference and the preset rotation angle is taken as the angle ratio. Taking the preset number as an example, that is, when the preset number is equal to 4, the target feature points on each target trajectory line include a start point, a first control point, a second control point, and an end point. The abscissa of the target feature point on the left outer tire trajectory line of the target trajectory line in the first adjacent key angle feature point set is taken as the abscissa of the first adjacent key angle. The abscissa of the target feature point on the left outer tire trajectory line of the target trajectory line in the second adjacent key angle feature point set is taken as the abscissa of the second adjacent key angle. The ordinate of the target feature point on the left outer tire trajectory line of the target trajectory line in the first adjacent key angle feature point set is taken as the ordinate of the first adjacent key angle. The ordinate of the target feature point on the left outer tire trajectory line of the target trajectory line in the second adjacent key angle feature point set is taken as the ordinate of the first adjacent key angle. The calculation process is as follows: the difference between the horizontal coordinate of the second adjacent key angle and the horizontal coordinate of the first adjacent key angle is used as the first horizontal coordinate; the product of the first horizontal coordinate and the angle ratio is used as the second horizontal coordinate; the sum of the second horizontal coordinate and the horizontal coordinate of the first adjacent key angle is used as the horizontal coordinate of the current angle feature point of the left outer tire trajectory line in the current angle feature point set; the difference between the vertical coordinate of the second adjacent key angle and the vertical coordinate of the first adjacent key angle is used as the first vertical coordinate; the product of the first vertical coordinate and the angle ratio is used as the second vertical coordinate; the sum of the second vertical coordinate and the vertical coordinate of the first adjacent key angle is used as the vertical coordinate of the current angle feature point of the left outer tire trajectory line in the current angle feature point set; the horizontal coordinate and the vertical coordinate constitute the current angle feature point; the starting point, the first control point, the second control point, and the ending point on the left outer tire trajectory line are calculated sequentially. Similarly, following the above calculation process, multiple current angle feature points can be calculated for each of the following current angle feature point sets: the left inner tire target trajectory line, the right inner tire target trajectory line, the right outer tire target trajectory line, the left vehicle body target edge trajectory line, and the right vehicle body target edge trajectory line. These can then be used as the current angle feature point set.

[0127] Through the above embodiments, during vehicle operation, the current angle feature point set is calculated based on the current angle, the key angle, and the target feature point set. Since the key angle and the target feature points are calculated based on the actual parameters of the vehicle, the data of the current angle feature point set is accurate. This effectively improves the consistency with the actual trajectory of the vehicle, effectively improves the accuracy of constructing dynamic trajectory lines, and effectively improves the smoothness when switching angles.

[0128] The current angle point set calculation unit 140 calculates the current angle point set based on the current angle feature point set.

[0129] In this embodiment, the current angle feature point set is calculated using data such as the target feature point set calibrated with actual parameters, and the current angle point set is calculated using the current angle feature point set. This effectively ensures consistency with the actual vehicle trajectory, effectively improves the accuracy of constructing dynamic trajectory lines, and effectively improves the smoothness during angle switching.

[0130] In one embodiment, calculating the current angle point set based on the current angle feature point set includes:

[0131] Obtain the preset number of current angle feature points belonging to the same current angle trajectory line from the current angle feature point set, and obtain the Bézier curve function;

[0132] The curve function of each current angle trajectory line in the current angle feature point set is obtained by using the acquired current angle feature points and the Bézier curve function.

[0133] Each current angle feature point and factor in the current angle feature point set are input into the curve function for calculation to obtain the target point corresponding to each current angle feature point;

[0134] Construct the current angle point set using the target point;

[0135] The factor is any value within the range [0,1].

[0136] In this embodiment, the general parameter formula of the Bézier curve function (Bézier curve, also known as Bézier curve or Bézier curve, is a mathematical curve used in two-dimensional graphics applications) is as follows: Similarly, taking a preset quantity of 4 as an example, when the preset quantity equals 4, the current angle feature point includes the starting point, the first control point, the second control point, and the ending point on the current angle trajectory line; if the preset quantity equals 4, then n equals the preset quantity - 1, that is, n equals 3, where n represents the order of the Bézier curve function, that is, the Bézier curve function defines a cubic Bézier curve for the four points P0, P1, P2, and P3 in a plane or in three-dimensional space: Where B(t) is the abscissa curve function or ordinate curve function of the current angle trajectory line to which P0, P1, P2 and P3 belong in the current angle feature point set; n represents the order of the Bézier curve function; i∈[0,n]; t is a factor, which is any value in [0,1]; here P0, P1, P2 and P3 are each current angle feature point on the current angle trajectory line in the current angle feature point set: starting point P0, first control point P1, second control point P2 and ending point P3. The current angle trajectory line may include the target trajectory line of the left inner tire, the target trajectory line of the right inner tire, the target trajectory line of the right outer tire, and the target trajectory line of the left side of the vehicle. Multiple current angle feature points are used for the target edge trajectory line of the main body and the target edge trajectory line of the right side of the vehicle body. The x-coordinates and y-coordinates of the starting point P0, the first control point P1, the second control point P2, and the ending point P3 are respectively input into the cubic Bezier curve to obtain the x-coordinate curve function and y-coordinate curve function of the current angle trajectory line. Then, t, which is gradually increased with a preset precision value, is input into the x-coordinate curve function and the y-coordinate curve function to obtain the target point corresponding to each current angle feature point. The preset precision value can be 0.1, 0.01, or 0.001, etc. The current angle point set is constructed using the multiple target points obtained by calculation.

[0137] Through the above embodiments, during vehicle operation, since the key angle and the target feature point are calculated based on the actual parameters of the vehicle, and the current angle feature point set is calculated based on the current angle, the key angle, and the target feature point set, and the current angle point set is calculated using the Bezier curve function, the preset precision value and the preset quantity determine and accurately the smoothness of the dynamic trajectory line. Therefore, the data of the current angle point set is accurate, which effectively improves the consistency with the actual trajectory line of the vehicle. This not only effectively improves the accuracy of constructing the dynamic trajectory line, but also effectively improves the smoothness when switching angles.

[0138] Vertex point set conversion unit 150 converts the current angle feature point set and the current angle point set into vertex point sets.

[0139] In this embodiment, both the current angle feature point set and the current angle point set are screen coordinates. The screen coordinates need to be converted to vertex coordinates. The conversion process is as follows: The width of the vehicle's display screen is taken as the screen width, and the height of the display screen is taken as the screen height. The quotient of the x-coordinate of the current angle feature point set or the current angle point set and an integer 2 is taken as the first vertex x-coordinate. The difference between the first vertex x-coordinate and the screen width is taken as the second vertex x-coordinate. The quotient of the second vertex x-coordinate and the screen width is taken as the vertex x-coordinate. Similarly, the quotient of the y-coordinate of the current angle feature point set or the current angle point set and an integer 2 is taken as the first vertex y-coordinate. The difference between the first vertex y-coordinate and the screen height is taken as the second vertex y-coordinate. The quotient of the second vertex y-coordinate and the screen height is taken as the vertex y-coordinate.

[0140] Through the above embodiments, the vertex point set is obtained by calculating the current angle feature point set and the current angle point set through the specific data of the display screen. Therefore, the data of the vertex point set is accurate, which effectively improves the consistency with the actual trajectory line of the vehicle. This not only effectively improves the accuracy of constructing dynamic trajectory lines, but also effectively improves the smoothness when switching angles.

[0141] The dynamic trajectory line construction unit 160 constructs a dynamic trajectory line based on the vertex point set.

[0142] In this embodiment, the vertex point set is the result set obtained by performing calculations on the current angle feature point set, the current angle point set, the screen width, and the screen height. The current angle feature point set and the current angle point set are the target feature point set on the target trajectory line calibrated by the actual parameters of the vehicle. This indicates that the vertex point set is close to the actual trajectory line, which effectively improves the accuracy of constructing dynamic trajectory lines.

[0143] In one embodiment, constructing a dynamic trajectory line based on the vertex set includes:

[0144] The transparency of the corresponding vertices in the vertex set is calculated based on the factor and the preset transparency range, and the gradient fill color of the dynamic trajectory line is determined based on the transparency.

[0145] The area of ​​the corresponding vertex is calculated based on the factor and the preset line width range, and the line width of the dynamic trajectory line is determined based on the area.

[0146] Configure the effective display range of the warning line in the dynamic trajectory line according to the x-coordinate of the vertex of the current angle trajectory line in the vertex point set.

[0147] In this embodiment, specifically, a shader device is invoked to construct the dynamic trajectory line from the set of vertices. Each factor corresponds to a vertex, and the factor is any value within [0,1]. The preset transparency range is set between a first preset transparency and a second preset transparency, wherein the first preset transparency is greater than or equal to the second preset transparency. The transparency calculation process for each factor-corresponding vertex is as follows: the difference between the first preset transparency and the second preset transparency is used as the first transparency; the product of the first transparency and the factor is used as the second transparency; the sum of the second transparency and the second preset transparency is used as the transparency of each factor-corresponding vertex; and the gradient fill color of the dynamic trajectory line is determined by the transparency of each vertex.

[0148] The shader device is invoked to construct the dynamic trajectory line from the set of vertices. Each factor corresponds to a vertex, and the factor is any value within [0,1]. The preset line width range is set between a first preset line width and a second preset line width, wherein the first preset line width is greater than or equal to the second preset line width. The area calculation process for the vertex corresponding to each factor is as follows: the difference between the first preset line width and the second preset line width is used as the first vertex line width; the product of the first vertex line width and the factor is used as the second vertex line width; the sum of the second vertex line width and the second preset line width is used as the area of ​​the vertex corresponding to each factor; and the line width of the dynamic trajectory line is determined by the area of ​​each vertex.

[0149] The shader device is invoked to construct the dynamic trajectory line from the set of vertices. The current angle trajectory line includes the target trajectory line of the left inner tire, the target trajectory line of the right inner tire, the target trajectory line of the right outer tire, the target edge trajectory line of the left vehicle body, and the target edge trajectory line of the right vehicle body. Based on the x-coordinates of the vertices of the target edge trajectory lines of the left and right vehicle body in the current angle trajectory line in the set of vertices, the effective display range of the warning line in the dynamic trajectory line is configured.

[0150] Through the above embodiments, by calling the shader device, the gradient fill color, line width, and warning line of the dynamic trajectory line are constructed through a series of calculations based on preset data, making the dynamic trajectory line more accurate. This effectively improves the consistency with the actual trajectory line of the vehicle, not only effectively improving the accuracy of constructing the dynamic trajectory line, but also effectively improving the smoothness when switching angles.

[0151] As can be seen, the embodiments of this device achieve the following during vehicle operation: obtaining the vertical distance based on the measured distance of the vehicle; acquiring preview images corresponding to each key angle based on key angles and the vertical distance; processing each preview image to obtain each edge image; acquiring multiple target feature points in each edge image; constructing a target feature point set corresponding to each key angle based on the multiple target feature points; obtaining the current angle; calculating the current angle feature point set based on the current angle, the key angle, and the target feature point set; calculating the current angle point set based on the current angle feature point set; converting the current angle feature point set and the current angle point set into a vertex point set; and constructing a dynamic trajectory line based on the vertex point set. This invention achieves dynamic construction of the vehicle trajectory line during vehicle operation, which not only improves the accuracy of the dynamic trajectory line but also improves the smoothness during angle switching.

[0152] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned device and each unit can be referred to the corresponding description in the foregoing method embodiments. For the sake of convenience and brevity, it will not be repeated here.

[0153] The above-described device can be implemented as a computer program, and the computer program can be implemented in, for example... Figure 3 It runs on the computer device shown.

[0154] Please see Figure 3 , Figure 3 This is a schematic block diagram of a computer device 500 provided as an embodiment of this application. The computer device 500 includes terminal devices such as computers and servers. Figure 3 As shown, the device 500 includes a processor 502, a memory, and a network interface 503 connected via a system bus 501. The memory may include a non-volatile storage medium 504 and internal memory 505.

[0155] The non-volatile storage medium 504 can store an operating system 5041 and a computer program 5042. When the computer program 5042 stored in the non-volatile storage medium is executed by the processor 502, it can implement the vehicle dynamic trajectory construction method described above. The processor 502 provides computing and control capabilities to support the operation of the entire device 500. The internal memory 505 provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor 502, it enables the processor 502 to execute the vehicle dynamic trajectory construction method described above. The network interface 503 is used for network communication. Those skilled in the art will understand that the structure shown in the figures is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the device to which the present invention is applied. Specific devices may include more or fewer components than shown in the figures, or combinations of certain components, or different component arrangements.

[0156] The processor 502 is used to run a computer program stored in the memory to perform the following steps:

[0157] The vertical distance is obtained based on the vehicle's measured distance, and preview images corresponding to each key angle are acquired based on the key angle and the vertical distance. Each preview image is processed to obtain each edge image, and multiple target feature points are acquired in each edge image. A target feature point set corresponding to each key angle is constructed based on the multiple target feature points. The current angle is obtained, and the current angle feature point set is calculated based on the current angle, the key angle, and the target feature point set. The current angle point set is calculated based on the current angle feature point set. The current angle feature point set and the current angle point set are converted into a vertex point set. A dynamic trajectory line is constructed based on the vertex point set.

[0158] It should be understood that, in the embodiments of this application, the processor 502 may be a central processing unit (CPU), but it may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0159] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a storage medium, which can be a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0160] Therefore, embodiments of this application also provide a storage medium. This storage medium can be a computer-readable storage medium, including non-volatile computer-readable storage media. The storage medium stores a computer program that, when executed by a processor, performs the following steps:

[0161] The vertical distance is obtained based on the vehicle's measured distance, and preview images corresponding to each key angle are acquired based on the key angle and the vertical distance. Each preview image is processed to obtain each edge image, and multiple target feature points are acquired in each edge image. A target feature point set corresponding to each key angle is constructed based on the multiple target feature points. The current angle is obtained, and the current angle feature point set is calculated based on the current angle, the key angle, and the target feature point set. The current angle point set is calculated based on the current angle feature point set. The current angle feature point set and the current angle point set are converted into a vertex point set. A dynamic trajectory line is constructed based on the vertex point set.

[0162] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0163] In the several embodiments provided in this application, it should be understood that the disclosed apparatus, devices, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, and the division of units is only a logical functional division; in actual implementation, there may be other division methods. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the apparatus, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0164] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for constructing a vehicle dynamic trajectory line, characterized in that, include: The vertical distance is obtained based on the vehicle's measured distance, and a preview image corresponding to each key angle is acquired based on the key angle and the vertical distance. Each preview image is processed to obtain each edge image. Multiple target feature points are collected in each edge image. Based on the multiple target feature points, a target feature point set corresponding to each key angle is constructed. Obtain the current angle, and calculate the current angle feature point set based on the current angle, the key angle, and the target feature point set; The current angle point set is calculated based on the current angle feature point set; Convert the current angle feature point set and the current angle point set into a vertex point set; Construct a dynamic trajectory line based on the vertex set; The process of obtaining the vertical distance based on the vehicle's measured distance, and acquiring a preview image corresponding to each key angle based on the key angle and the vertical distance, includes: The maximum distance between the edge lines of the two rearview mirrors of the vehicle is taken as the outer distance of the rearview mirror, and the maximum distance between the edge lines of the two symmetrical tires of the vehicle is taken as the outer distance of the tire. The vertical distance is calculated using the distance from the outer edge of the rearview mirror and the distance from the outer edge of the tire. The key angle is determined based on the preset rotation angle and the preset rotation angle range; The tire trajectory line is calibrated based on the aforementioned key angles; The vehicle body edge trajectory line is calibrated based on the tire trajectory line and the vertical distance; The image acquisition device is invoked and controlled to acquire images based on the tire trajectory line and the vehicle body edge trajectory line to obtain the preview image; The preset rotation angle is 90° or 180°, and the preset rotation angle range is [-540°, 540°].

2. The method according to claim 1, characterized in that, The process of collecting multiple target feature points from each edge map and constructing a target feature point set corresponding to each key angle based on these multiple target feature points includes: Obtain the trajectory line in each edge map as at least one target trajectory line; A predetermined number of points are collected on each of the at least one target trajectory line as the plurality of target feature points; The target feature point set corresponding to each key angle is constructed using the multiple target feature points.

3. The method according to claim 2, characterized in that, The step of calculating the current angle point set based on the current angle feature point set includes: Obtain the preset number of current angle feature points belonging to the same current angle trajectory line from the current angle feature point set, and obtain the Bézier curve function; The curve function of each current angle trajectory line in the current angle feature point set is obtained by using the acquired current angle feature points and the Bézier curve function. Each current angle feature point and factor in the current angle feature point set are input into the curve function for calculation to obtain the target point corresponding to each current angle feature point; Construct the current angle point set using the target point; The factor is any value within the range [0,1].

4. The method according to claim 3, characterized in that, The step of constructing a dynamic trajectory line based on the vertex set includes: The transparency of the corresponding vertices in the vertex set is calculated based on the factor and the preset transparency range, and the gradient fill color of the dynamic trajectory line is determined based on the transparency. The area of ​​the corresponding vertex is calculated based on the factor and the preset line width range, and the line width of the dynamic trajectory line is determined based on the area. Configure the effective display range of the warning line in the dynamic trajectory line according to the x-coordinate of the vertex of the current angle trajectory line in the vertex point set.

5. The method according to claim 1, characterized in that, The process of processing each preview image to obtain each edge image includes: Convert each preview image to grayscale; A filtered grayscale image is obtained by removing noise from the grayscale image using bilateral filtering. Edge detection processing is performed on the filtered grayscale image based on the Laplacian operator to obtain each edge image.

6. The method according to claim 1, characterized in that, The step of obtaining the current angle, and calculating the current angle feature point set based on the current angle, the key angle, and the target feature point set, includes: The current steering angle of the vehicle is obtained as the current angle; Obtain two key angles adjacent to the current angle as the first adjacent key angle and the second adjacent key angle; Obtain the set of target feature points corresponding to the first adjacent key angle as the first adjacent key angle feature point set; Obtain the set of target feature points corresponding to the second adjacent key angle as the second adjacent key angle feature point set; The current angle feature point set is calculated based on the current angle, the first adjacent key angle, the first adjacent key angle feature point set, and the second adjacent key angle feature point set.

7. A vehicle dynamic trajectory line construction device, characterized in that, include: The preview image acquisition unit is used to obtain the vertical distance based on the vehicle measurement distance, and to acquire a preview image corresponding to each key angle based on the key angle and the vertical distance. The target feature point set construction unit is used to process each preview image to obtain each edge image, collect multiple target feature points in each edge image, and construct a target feature point set corresponding to each key angle based on the multiple target feature points; The current angle feature point set calculation unit is used to obtain the current angle and calculate the current angle feature point set based on the current angle, the key angle, and the target feature point set. The current angle point set calculation unit is used to calculate the current angle point set based on the current angle feature point set. A vertex point set conversion unit is used to convert the current angle feature point set and the current angle point set into a vertex point set; A dynamic trajectory line construction unit is used to construct a dynamic trajectory line based on the vertex set. The process of obtaining the vertical distance based on the vehicle's measured distance, and acquiring a preview image corresponding to each key angle based on the key angle and the vertical distance, includes: The maximum distance between the edge lines of the two rearview mirrors of the vehicle is taken as the outer distance of the rearview mirror, and the maximum distance between the edge lines of the two symmetrical tires of the vehicle is taken as the outer distance of the tire. The vertical distance is calculated using the distance from the outer edge of the rearview mirror and the distance from the outer edge of the tire. The key angle is determined based on the preset rotation angle and the preset rotation angle range; The tire trajectory line is calibrated based on the aforementioned key angles; The vehicle body edge trajectory line is calibrated based on the tire trajectory line and the vertical distance; The image acquisition device is invoked and controlled to acquire images based on the tire trajectory line and the vehicle body edge trajectory line to obtain the preview image; The preset rotation angle is 90° or 180°, and the preset rotation angle range is [-540°, 540°].

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the vehicle dynamic trajectory line construction method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores a computer program, which includes program instructions that, when executed by a processor, cause the processor to perform the vehicle dynamic trajectory line construction method as described in any one of claims 1 to 6.

Images