Lane line fitting method and device, vehicle, storage medium and product

Abstract

The invention relates to a lane line fitting method and device, a vehicle, a storage medium and a product. The method comprises the following steps: acquiring a lane line image acquired by image acquisition equipment; determining the type of a lane line in the lane line image; under the condition that the type is a curve, performing Bezier curve fitting processing on the lane line to obtain a Bezier lane line equation; the Bezier lane line equation is input into a first filter, initial key point coordinates in the Bezier lane line equation are updated through the first filter, first target key point coordinates are determined, and the initial key point coordinates comprise end point coordinates and control point coordinates in the Bezier curve; and determining a target lane line fitting result according to the first target key point coordinates and a Bezier curve equation. According to the invention, the fitting effect of the complex curve in the lane line can be improved, and the calculated amount of the overall lane line fitting is small.

Description

Technical Field

[0001] This disclosure relates to the field of autonomous driving technology, and in particular to a lane line fitting method, apparatus, vehicle, storage medium, and product. Background Technology

[0002] Lane fitting is a crucial functional module in autonomous driving. It involves fitting lane lines into a mathematical model, enabling vehicles to accurately track the lane and drive safely. However, related technologies often suffer from poor fitting results for curves within the lane lines, and lane fitting also requires significant computational resources. Summary of the Invention

[0003] To overcome the problems existing in related technologies, this disclosure provides a lane line fitting method, apparatus, vehicle, storage medium, and product.

[0004] According to a first aspect of the present disclosure, a lane line fitting method is provided, comprising: Acquire lane line images captured by the image acquisition device; Determine the type of lane lines in the lane line image; In the case of a curve, the lane lines are fitted with a Bézier curve to obtain a Bézier lane line equation, which is used to reflect the lane lines fitted according to the Bézier curve. The Bezier lane line equation is input into the first filter, and the initial key point coordinates in the Bezier lane line equation are updated using the first filter to determine the coordinates of the first target key point. The initial key point coordinates include the endpoint coordinates and control point coordinates in the Bezier curve. Based on the coordinates of the first target key point and the Bézier curve equation, the target lane line fitting result is determined.

[0005] Optionally, the update performed by the first filter includes the following steps: The coordinates of the observation points in the lane line are sampled according to the Bessel lane line equation to determine the observation coordinate matrix; Based on the state transition matrix and the second target key point coordinate matrix, a priori key point coordinate matrix is ​​determined. The state transition matrix is ​​used to characterize the motion information of the vehicle from the previous moment to the current moment, and the second target key point coordinate matrix is ​​used to reflect the coordinates of the second target key point determined by the first filter in the previous moment of the current moment. Using the Bézier curve equation and the prior key point coordinate matrix, the coordinates of the observation points in the lane line are calculated to obtain the prior coordinate matrix; The initial keypoint coordinates are updated based on the prior keypoint coordinate matrix, the observed coordinate matrix, the prior coordinate matrix, and the gain of the first filter to determine the coordinates of the first target keypoint.

[0006] Optionally, updating the initial keypoint coordinates based on the prior keypoint coordinates, the observed coordinate matrix, the prior coordinate matrix, and the gain of the first filter to determine the coordinates of the first target keypoint includes: The first intermediate matrix is ​​obtained by performing a difference operation between the observed coordinate matrix and the prior coordinate matrix. The second intermediate matrix is ​​obtained by multiplying the gain and the first intermediate matrix. The coordinates of the first target key point are obtained by summing the second intermediate matrix and the prior key point coordinate matrix, and the coordinates of the first target key point are used to replace the initial key point coordinates.

[0007] Optionally, the motion information includes lateral movement distance and longitudinal movement distance; The step of determining the prior key point coordinate matrix based on the state transition matrix and the second target key point coordinate matrix includes: The prior key point coordinate matrix is ​​determined by multiplying the state transition matrix and the second target key point coordinate matrix.

[0008] Optionally, the step of calculating the coordinates of the observation points in the lane line using the Bézier curve equation and the prior key point coordinate matrix to obtain the prior coordinate matrix includes: An initial observation matrix is ​​determined based on the Bézier curve equation. The initial observation matrix includes a curve parameter matrix and a preset constant matrix. The curve parameter matrix includes curve parameters that can vary within a preset range. By inputting different values ​​of the curve parameters within the preset range into the initial observation matrix, the target observation matrix is ​​obtained; The target observation matrix and the prior key point coordinate matrix are input into the Bézier curve equation to calculate the coordinates of the observation points at the previous time step mapped to the coordinates at the current time step, thus obtaining the prior coordinate matrix.

[0009] Optionally, after the step of inputting the target observation matrix and the prior keypoint coordinate matrix into the Bézier curve equation to calculate the coordinates of the observation points at the previous time step mapped to the coordinates at the current time step, and obtaining the prior coordinate matrix, the method further includes: Based on the state transition matrix, the first noise covariance of the first noise, and the covariance matrix of the previous time step output by the first filter, the prior covariance matrix is ​​determined. The covariance matrix is ​​used to characterize the accuracy of the target key point coordinates output by the first filter. The first noise includes noise in the process of determining the prior key point coordinate matrix. The gain is determined based on the prior covariance matrix, the target observation matrix, and the second noise covariance matrix, wherein the second noise includes the noise of the first filter and / or the noise of the image acquisition device.

[0010] Optionally, determining the type of lane lines in the lane line image includes: Based on the lane lines, a polynomial curve fitting process is performed to obtain the initial polynomial curve equation; The type of lane line is determined based on the initial polynomial curve equation.

[0011] Optionally, determining the type of lane line based on the initial polynomial curve equation includes: The type is determined by comparing the preset coefficients of the first term with the preset threshold in the initial polynomial curve equation.

[0012] Optionally, the method further includes: When the type is a straight road, the initial polynomial curve equation is input into the second filter, the second filter is used to update the initial polynomial curve equation, the target polynomial curve equation is output, and the target lane line fitting result is determined based on the target polynomial curve equation.

[0013] According to a second aspect of the present disclosure, a lane line fitting device is provided, comprising: The acquisition module is configured to acquire lane line images captured by the image acquisition device; The first determining module is configured to determine the type of lane lines in the lane line image; The first fitting module is configured to perform Bézier curve fitting on the lane line when the type is a curve, to obtain the Bézier lane line equation, which is used to reflect the lane line fitted according to the Bézier curve. The first update module is configured to input the Bezier lane line equation into a first filter, use the first filter to update the initial key point coordinates in the Bezier lane line equation, and determine the coordinates of the first target key point. The initial key point coordinates include the endpoint coordinates and control point coordinates in the Bezier curve. The second determining module is configured to determine the target lane line fitting result based on the coordinates of the first target key point and the Bézier curve equation.

[0014] According to a third aspect of the present disclosure, a vehicle is provided, comprising: processor; Memory used to store processor-executable instructions; The processor is configured as follows: Acquire lane line images captured by the image acquisition device; Determine the type of lane lines in the lane line image; In the case of a curve, the lane lines are fitted with a Bézier curve to obtain a Bézier lane line equation, which is used to reflect the lane lines fitted according to the Bézier curve. The Bezier lane line equation is input into the first filter, and the initial key point coordinates in the Bezier lane line equation are updated using the first filter to determine the coordinates of the first target key point. The initial key point coordinates include the endpoint coordinates and control point coordinates in the Bezier curve. Based on the coordinates of the first target key point and the Bézier curve equation, the target lane line fitting result is determined.

[0015] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the steps of the lane line fitting method provided in the first aspect of the present disclosure.

[0016] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the lane line fitting method provided in the first aspect of the present disclosure.

[0017] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects: by first determining the type of lane line, and then performing Bézier curve fitting on the lane line when the type of lane line is determined to be a curve, the Bézier curve fitting process can better fit complex curves, and the Bézier curve fitting process is only performed on curves, which can reduce the overall lane fitting calculation amount.

[0018] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0020] Figure 1 This is a schematic diagram illustrating a region with poor fitting performance according to an exemplary embodiment.

[0021] Figure 2 This is a flowchart illustrating a lane line fitting method according to an exemplary embodiment.

[0022] Figure 3 This is a schematic diagram of a third-order Bézier curve according to an exemplary embodiment.

[0023] Figure 4 This is a flowchart illustrating the updating of the first filter according to an exemplary embodiment.

[0024] Figure 5 This is a flowchart illustrating the determination of the coordinates of a first target key point according to an exemplary embodiment.

[0025] Figure 6 This is a flowchart illustrating the determination of gain according to an exemplary embodiment.

[0026] Figure 7 This is another flowchart illustrating a lane line fitting method according to an exemplary embodiment.

[0027] Figure 8 This is a block diagram illustrating a lane line fitting device according to an exemplary embodiment.

[0028] Figure 9 This is a block diagram illustrating a vehicle according to an exemplary embodiment.

[0029] Figure 10 This is a block diagram of a chip system according to an exemplary embodiment. Detailed Implementation

[0030] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0031] The embodiments described in the following examples of this disclosure are not representative of all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0032] Lane fitting refers to processing lane line images and using mathematical models to fit the shape and position of the lane lines. Lane lines include straight lines and / or curves. Straight lines correspond to straight sections of the road, while curves correspond to curved sections. The goal of fitting is to find the best-fitting curve or straight line that closely approximates the actual lane lines.

[0033] In potential application scenarios, deep learning algorithms, such as semantic segmentation or 3D detection schemes, are used to fit lane lines, obtaining a lane line point set. This set is then post-processed before being output to downstream vehicle control modules to ensure safe driving. Post-processing may include tracking and filtering the lane line point set, smoothing the results of consecutive frames of lane line images to prevent issues such as lane line jitter and abrupt changes.

[0034] In related technologies, cubic curves are used to fit lane lines. However, this method can only fit lane line point sets with relatively low error for straight lanes or curves with small curvature. For complex lanes, such as S-curves or sharp bends, the fitting effect drops sharply, leading to "near-and-far" deviations. "Near-and-far" deviations occur when the fitted lane line points deviate from the actual lane lines; areas exhibiting this deviation are regions of poor fitting. See the example below. Figure 1 The region formed by the set of lane line points within the dashed box represents the area with poor fitting performance. Furthermore, related technologies employ computationally complex fitting algorithms for both straight and curved roads, resulting in high computational costs and low lane line fitting efficiency.

[0035] To address the aforementioned technical problems, this disclosure proposes a lane line fitting method, apparatus, vehicle, storage medium, and product that can improve the fitting effect for complex curves in lane lines, while reducing the overall computational load of lane line fitting.

[0036] Figure 2 This is a flowchart illustrating a lane line fitting method according to an exemplary embodiment, which can be applied to vehicles, such as... Figure 2 As shown, the method includes the following steps.

[0037] Step 210: Obtain the lane line image captured by the image acquisition device.

[0038] Image acquisition devices may include cameras in vehicles and devices equipped with cameras. Lane line images may be images captured by the image acquisition device for the lane lines along which the vehicle is traveling. In a possible implementation, the lane line image may be a lane line image captured by the image acquisition device at the current moment.

[0039] Step 220: Determine the type of lane lines in the lane line image.

[0040] In some embodiments, the type may include straight sections and curves. In possible implementations, the type of lane markings can be determined based on a machine learning model, or based on a polynomial curve fitting result of the lane markings.

[0041] In some embodiments, determining the type of lane lines in a lane line image includes: performing polynomial curve fitting processing on the lane lines to obtain an initial polynomial curve equation; and determining the type of lane lines based on the initial polynomial curve equation.

[0042] In some embodiments, performing polynomial curve fitting processing on the lane lines to obtain an initial polynomial curve may include: performing key point detection on the lane line image to obtain lane line key points; and performing polynomial curve fitting processing on the lane lines based on the lane line key points to obtain the initial polynomial curve equation.

[0043] In a possible implementation, key points can be detected in the lane line image based on an image segmentation algorithm or a detection algorithm. The lane line key points can be specifically set according to actual needs. For example, the lane line key points can be coordinate points obtained at preset distances in the lane line 100 meters in front of the vehicle position. For example, the preset distance can be 1m or 1.5m, etc.

[0044] Polynomial curve fitting can include quadratic polynomial curve fitting, cubic polynomial curve fitting, etc. Different polynomial curve fitting processes yield different initial polynomial curve equations. For example, the initial polynomial curve equation obtained by quadratic polynomial curve fitting is a quadratic polynomial curve equation, and the initial polynomial curve equation obtained by cubic polynomial curve fitting is a cubic polynomial curve equation.

[0045] In some embodiments, determining the type of lane line based on the initial polynomial curve equation includes: determining the type based on a comparison between a preset coefficient of a predetermined term in the initial polynomial curve equation and a preset threshold.

[0046] The preset coefficients of the second term can be determined according to the type of the polynomial curve equation. For example, if the polynomial curve equation is a quadratic polynomial curve equation, the preset coefficients of the second term can be quadratic coefficients; if the polynomial curve equation is a cubic polynomial curve equation, the preset coefficients of the second term can be cubic coefficients.

[0047] The preset threshold can be set according to the actual situation. For example, the preset threshold can be 0.000001. In possible implementations, the preset thresholds for different preset sub-term coefficients can be different. This disclosure does not impose any restrictions on the specific value of the preset threshold.

[0048] In some embodiments, the type is determined based on the comparison between the preset coefficient of the first term in the initial polynomial curve equation and a preset threshold, including: if the preset coefficient of the first term is greater than or equal to the preset threshold, the type is determined to be a curve; if the preset coefficient of the first term is less than the preset threshold, the type is determined to be a straight road.

[0049] Step 230: In the case of a curve, perform Bézier curve fitting on the lane lines to obtain the Bézier lane line equation. The Bézier lane line equation is used to reflect the lane lines fitted according to the Bézier curve.

[0050] Bézier curve fitting is used to fit lane lines based on Bézier curves. Correspondingly, the Bézier lane line equation can reflect the lane lines fitted based on Bézier curves, or it can also be called the fitted lane lines.

[0051] In some embodiments, the Bézier curve used for fitting may include a second-order, third-order, or fourth-order Bézier curve, which is a mathematical curve applied using a two-dimensional graphics application. Correspondingly, the fitted Bézier lane line equation may be a Bézier curve equation that matches the second-order, third-order, or fourth-order Bézier curve. For details on Bézier lane line equations, please refer to the relevant description below, which will not be repeated here.

[0052] In a possible implementation, endpoint coordinates include start-point coordinates and end-point coordinates. Control point coordinates may include the coordinates of control points used to control the shape of the Bézier curve. The number of control points varies depending on the type of Bézier curve; for example, in the case of a second-order Bézier curve, there is one control point; in the case of a third-order Bézier curve, there are two control points; and in the case of a fourth-order Bézier curve, there are three control points.

[0053] In the exemplary application scenario, the Bézier curve fitting process selected in this disclosure is a third-order Bézier curve fitting process. By selecting the third-order Bézier curve fitting process, the third-order Bézier curve has a good fitting effect on curves, and the fitting calculation is small. For example, see Figure 3 , Figure 3 The dashed lines in the diagram are lane lines fitted based on a Bézier curve, also known as fitted lane lines. This Bézier curve is a third-order Bézier curve, where P1 and P4 are the endpoint coordinates, and P2 and P3 are the control point coordinates.

[0054] It is worth noting that the following examples of embodiments of this disclosure all use third-order Bézier curve fitting as an example. However, it is worth noting that obtaining the corresponding initial Bézier curve through Bézier curve fitting of other orders is also within the protection scope of this disclosure.

[0055] For example, taking the Bézier curve equation as a third-order Bézier curve equation, the third-order Bézier curve equation can be the following equation (1): (1) in, Let t be the lane line coordinates, and t be the curve parameter. - These are the coordinates of the key point. t can take values ​​within a preset range, which can be determined according to actual needs. For example, the preset range can be [0,1].

[0056] Understandable, For the curve parameter matrix, For a preset constant matrix, Let be the keypoint coordinate matrix, consisting of the keypoint coordinates, where and These can be endpoint coordinates. and These can be the coordinates of control points.

[0057] In possible implementations It can be a coordinate in the vehicle coordinate system (VCS). Used to reflect the coordinates in the fitted lane lines.

[0058] For example, taking the aforementioned third-order Bézier curve equation (1) as an example, after performing Bézier curve fitting on the lane line, the initial key point coordinates can be obtained. The Bézier lane line equation is obtained by substituting the initial key point coordinates into the key point coordinate matrix of the Bézier curve equation (1). It can be seen that the Bézier lane line equation consists of a curve parameter matrix, a preset constant matrix, and an initial key point coordinate matrix. The initial key point coordinate matrix is ​​used to reflect the initial key point coordinates. The curve parameters in the curve parameter matrix are the independent variables of the Bézier lane line equation, and the dependent variable of the Bézier lane line equation is the lane line coordinates.

[0059] Step 240: Input the Bézier lane line equation into the first filter, and use the first filter to update the initial key point coordinates in the Bézier lane line equation to determine the coordinates of the first target key point. The initial key point coordinates include the endpoint coordinates and control point coordinates in the Bézier curve.

[0060] The first filter can be a Kalman filter matched to the Bessel lane line equations. Specific details regarding the update process of the first filter can be found below. Figure 4 The details and related descriptions will not be repeated here.

[0061] Step 250: Determine the target lane line fitting result based on the coordinates of the first target key point and the Bézier curve equation.

[0062] This embodiment of the disclosure first determines the type of lane line. When the type of lane line is determined to be a curve, the lane line is then subjected to Bézier curve fitting. The Bézier curve fitting process can better fit complex curves, and since the Bézier curve fitting process is only performed on curves, the overall lane fitting calculation amount can be reduced.

[0063] In a possible implementation, the target lane line fitting result may include a set of lane line coordinates obtained by sampling the coordinates in the lane line based on the coordinates of the first target key point and the Bézier curve equation.

[0064] In some embodiments, determining the target lane line fitting result based on the coordinates of the first target key points and the Bézier curve equation may include: inputting the coordinates of the first target key points into the Bézier curve equation to obtain the first Bézier curve equation, wherein the Bézier curve equation is composed of a curve parameter matrix, a preset constant matrix, and key point coordinates, and the curve parameter matrix includes curve parameters, which are the independent variables of the Bézier curve equation, and the dependent variable of the Bézier curve equation is the lane line coordinates; inputting different values ​​of the curve parameters within a preset range into the first Bézier curve equation to obtain multiple first lane line coordinates, and determining the multiple first lane line coordinates as the target lane line fitting result.

[0065] Inputting the coordinates of the first target key point into the Bézier curve equation, i.e., substituting the coordinates of the first target key point into the key point coordinate matrix, results in the curve parameters being unknowns in the first Bézier curve equation, while the constant matrix and the coordinates of the first target key point are known quantities. By inputting different values ​​of the curve parameters within a preset range into the first Bézier curve equation, the known coordinates of different lane lines can be obtained. This allows us to obtain the target lane line fitting result.

[0066] It is understandable that the process of inputting different values ​​of curve parameters within a preset range into the first Bézier curve equation to obtain multiple first lane line coordinates is, in other words, the process of sampling the coordinates in the lane lines. In a possible implementation, the method further includes: controlling the vehicle based on the target lane line fitting result. Details regarding vehicle control based on the lane line fitting result can be found in related technologies and will not be elaborated here.

[0067] Figure 4 This is a flowchart illustrating the updating of a first filter according to an exemplary embodiment. Figure 4 As shown, the update performed by the first filter includes the following steps 410-440.

[0068] Step 410: Sample the coordinates of the observation points in the lane line according to the Bessel lane line equation to determine the observation coordinate matrix.

[0069] In a possible implementation, the observation point can be a coordinate point within the lane line captured in the lane line image. It is understood that the observation point can be a coordinate point within the lane line captured by the image acquisition device, and the coordinates of the observation point are the values ​​observed by the image acquisition device, i.e., the observed values.

[0070] In some embodiments, the coordinates of the observation point can be coordinates in the vehicle coordinate system. In a possible implementation, the coordinates of the lane lines in the lane line image can be transformed from the image coordinate system to the vehicle coordinate system to obtain the coordinates of the observation point.

[0071] As mentioned earlier, the Bézier lane line equation consists of a curve parameter matrix, a preset constant matrix, and an initial keypoint coordinate matrix. In another possible implementation, sampling the coordinates of observation points in the lane line according to the Bézier lane line equation to determine the observation coordinate matrix may include: inputting different values ​​of the curve parameters within a preset range into the curve parameter matrix of the Bézier lane line equation, sampling the coordinates of observation points in the lane line, and determining the observed lane line coordinates. Different values ​​of the curve parameters within a preset range enable the sampling of the coordinates of observation points in the lane line. The specific method of value selection, i.e., the specific sampling method, can be determined according to actual needs, and this disclosure does not impose any restrictions on it.

[0072] Step 420: Determine the prior key point coordinate matrix based on the state transition matrix and the second target key point coordinate matrix. The state transition matrix is ​​used to characterize the motion information of the vehicle from the previous moment to the current moment, and the second target key point coordinate matrix is ​​used to reflect the coordinates of the second target key points determined by the first filter in the previous moment of the current moment.

[0073] In a possible embodiment, the motion information includes lateral movement distance and longitudinal movement distance. Both the lateral and longitudinal movement distances can be determined based on the vehicle's movement distance and the change in yaw angle in the direction of movement. For example, let the vehicle's movement distance be d, and the yaw angle change be... For example, the vertical movement distance Lateral movement distance The state transition matrix F can be one of the following matrices (2): F= (2) In some embodiments, the lane line state transition equation can be determined based on the Bezier lane line equation at the previous time step and the Bezier lane line equation at the current time step. The Bezier lane line equation at the previous time step is the Bezier curve equation corresponding to the coordinates of the second target key point, and the Bezier lane line equation at the current time step is the Bezier curve equation corresponding to the coordinates of the first target key point.

[0074] For example, with the current time as time t and the previous time as time t-1, the Bessel lane line equation at the current time is equation (1) above, where, The coordinates are ( ), The coordinates are ( ), The coordinates are ( ), The coordinates are ( For example, the equation of the Bessel lane line corresponding to the previous moment is the following equation (3): (3) in, For the previous moment coordinates For the previous moment coordinates For the previous moment coordinates For the previous moment The coordinates.

[0075] Using the coordinate matrix of the first target key point as =[ , , , , , , , [1], the coordinate matrix of the second target key point is ,in,( Let ) be the coordinates of P1 at the previous time step. Let ) be the coordinates of P2 at the previous time step. ) represents the coordinates of P3 at the previous moment. Taking the coordinates of P4 at the previous moment as an example, the lane line state transition equation is the following equation (4): (4) In some embodiments, determining the prior key point coordinate matrix based on the state transition matrix and the second target key point coordinate matrix includes: performing a product operation based on the state transition matrix and the second target key point coordinate matrix to determine the prior key point coordinate matrix.

[0076] For example, the coordinate matrix of the key points of the second target mentioned above is... The prior key point coordinate matrix is Taking the state transition matrix F as an example, the prior key point coordinate matrix can be determined according to the following formula (5). : (5) Step 430: Using the Bézier curve equation and the prior key point coordinate matrix, calculate the coordinates of the observation points in the lane line to obtain the prior coordinate matrix.

[0077] In some embodiments, the coordinates of observation points in the lane line are calculated using the Bézier curve equation and the prior key point coordinate matrix to obtain the prior coordinate matrix. This includes: determining an initial observation matrix based on the Bézier curve equation, the initial observation matrix including a curve parameter matrix and a preset constant matrix, the curve parameter matrix including curve parameters that can vary within a preset range; inputting different values ​​of the curve parameters within the preset range into the initial observation matrix to obtain the target observation matrix; inputting the target observation matrix and the prior key point coordinate matrix into the Bézier curve equation to calculate the coordinates of the observation points at the previous time step mapped to the current time step to obtain the prior coordinate matrix.

[0078] For example, taking the aforementioned Bézier curve equation as equation (1), the initial observation matrix H can be the following matrix (6): H= (6) Therefore, the initial observation matrix includes the unknown curve parameter t. By inputting different values ​​of the curve parameter within a preset range into the initial observation matrix, the known target observation matrix can be obtained. At this time, the target observation matrix and the prior key point coordinate matrix are input into equation (1), thereby substituting the prior key point coordinate matrix into the key point coordinate matrix. Since the prior key point coordinate matrix is ​​also known, the coordinates of the observation point at the previous moment mapped to the current moment can be calculated, that is, the prior coordinate matrix is ​​calculated.

[0079] In some embodiments, after inputting the target observation matrix and the prior keypoint coordinate matrix into the Bézier curve equation to calculate the coordinates of the observation points from the previous time step to the current time step, and obtaining the prior coordinate matrix, the method further includes: determining the gain of the first filter. Specific details regarding the determination of this gain can be found below. Figure 6 The details and related descriptions will not be repeated here.

[0080] Step 440: Update the initial key point coordinates based on the prior key point coordinate matrix, the observation coordinate matrix, the prior coordinate matrix, and the gain of the first filter to determine the coordinates of the first target key point.

[0081] This embodiment of the disclosure updates the initial keypoint coordinates based on the prior keypoint coordinate matrix, the observed coordinate matrix, the prior coordinate matrix, and the gain of the first filter, thereby determining the coordinates of the first target keypoint. This improves the accuracy of the final first target keypoint coordinates, making the Bézier lane line fitted based on the first target keypoint coordinates closer to the real lane line, and the lane line fitted at adjacent time points is smoother, improving the accuracy and stability of the fitted lane line, and thus improving the accuracy of vehicle control. Furthermore, through steps 410-440 above, this embodiment of the disclosure proposes a first filter adapted to Bézier curves, which is more consistent with the filtering operation in Bézier fitting scenarios, further improving the curve fitting effect.

[0082] Figure 5 This is a flowchart illustrating the determination of the coordinates of a first target key point according to an exemplary embodiment. Figure 5 As shown, the flowchart includes the following steps 510-530.

[0083] Step 510: Perform the difference operation between the observed coordinate matrix and the prior coordinate matrix to obtain the first intermediate matrix.

[0084] Step 520: Perform a product operation based on the gain and the first intermediate matrix to obtain the second intermediate matrix.

[0085] Step 530: Perform a summation operation based on the second intermediate matrix and the prior key point coordinate matrix to obtain the coordinates of the first target key point, and replace the initial key point coordinates with the coordinates of the first target key point.

[0086] For example, the coordinates of the first target keypoint and the initial keypoint coordinates are both in matrix form, based on the aforementioned prior keypoint coordinates. The coordinates of the first target key point are: And taking a gain of K as an example, assuming the observation coordinate matrix is... The prior coordinate matrix is Then the coordinates of the first target key point It can be obtained according to the following formula (7): (7) in, K is the first intermediate matrix. ( - ) is the second intermediate matrix.

[0087] Figure 6 This is a flowchart illustrating the determination of gain according to an exemplary embodiment. Figure 6 As shown, the process includes the following steps 610 and 620.

[0088] Step 610: Determine the prior covariance matrix based on the state transition matrix, the first noise covariance of the first noise, and the covariance matrix of the output of the first filter at the previous time step. The covariance matrix is ​​used to characterize the accuracy of the target key point coordinates output by the first filter. The first noise includes the noise in the process of determining the prior key point coordinates.

[0089] In some embodiments, determining the prior covariance matrix based on the state transition matrix, the first noise covariance of the first noise, and the previous time step covariance matrix of the first filter output includes: performing a product operation on the state transition matrix, the previous time step covariance matrix, and the transpose of the state transition matrix to obtain a third intermediate matrix; and performing a summation operation on the third intermediate matrix and the first noise covariance matrix to determine the prior covariance matrix. In some embodiments, the first noise may be noise generated during the process of determining the coordinates of prior key points, i.e., prediction noise.

[0090] For example, the prior covariance matrix can be determined according to the following formula (8): Q(8) in, The prior covariance matrix, Let be the covariance matrix of the output of the first filter at the previous time step. Here is the state transition matrix. Let Q be the transpose of the state transition matrix, and let Q be the first noise covariance. This is the third intermediate matrix.

[0091] Step 620: Determine the gain based on the prior covariance matrix, the target observation matrix, and the second noise covariance matrix of the second noise. The second noise includes the noise of the first filter and / or the noise of the image acquisition device.

[0092] In a possible embodiment, the noise of the first filter can be a systematic error of the first filter, and the noise of the image acquisition device can be a deviation of the image acquisition device during observation. Details regarding the calculation of noise covariance can be found in related technologies and will not be elaborated here.

[0093] For example, the gain K can be determined according to the following formula (9): (9) in, For the prior covariance matrix, For the target observation matrix, The second noise covariance matrix, is the transpose of the target observation matrix.

[0094] In some embodiments, after determining the gain based on the prior covariance matrix, the target observation matrix, and the second noise covariance matrix of the second noise, the method further includes: determining the posterior covariance matrix based on the prior covariance matrix, the gain, the target observation matrix, and the identity matrix, and updating the posterior covariance matrix to the covariance matrix of the filter output at the current time.

[0095] For example, the posterior covariance matrix can be determined according to the following formula (10). : =(IK ) (10) Where I is the identity matrix and K is the gain. For the target observation matrix, Let be the prior covariance matrix.

[0096] Figure 7 This is another flowchart illustrating a lane line fitting method according to an exemplary embodiment. See also Figure 7 The process includes steps 710-760.

[0097] Step 710: Obtain the lane line image captured by the image acquisition device.

[0098] Step 720: Perform polynomial curve fitting based on the lane lines to obtain the initial polynomial curve equation.

[0099] Step 730: Determine the type of lane line based on the initial polynomial curve equation.

[0100] Step 740: In the case of a curve, perform Bézier curve fitting on the lane lines to obtain the Bézier lane line equation.

[0101] Step 750: Input the Bezier lane line equation into the first filter, and use the first filter to update the initial key point coordinates in the Bezier lane line equation to determine the coordinates of the first target key point. The initial key point coordinates include the endpoint coordinates and control point coordinates in the Bezier curve.

[0102] Step 760: Determine the target lane line fitting result based on the coordinates of the first target key point and the Bézier curve equation.

[0103] Step 770: In the case of a straight road, the initial polynomial curve equation is input into the second filter, the initial polynomial curve equation is updated using the second filter, the target polynomial curve equation is output, and the target lane line fitting result is determined based on the target polynomial curve equation.

[0104] For specific details regarding steps 710-760, please refer to the aforementioned [link / reference]. Figure 2 The details and related descriptions will not be repeated here.

[0105] In a possible implementation, the initial polynomial curve equation may be a cubic polynomial curve equation, and the second filter may be a Kalman filter matched with the cubic polynomial curve equation. The second filter may employ a Kalman filter matched with a cubic polynomial curve equation from the related art, and this disclosure does not impose any limitations thereon.

[0106] In some embodiments, the target polynomial curve equation can be determined as the target lane line fitting result, and the vehicle can be controlled based on the target lane line fitting result.

[0107] This embodiment first uses a polynomial curve for initial fitting, then, when the lane line is determined to be a straight road, directly inputs the initially fitted polynomial curve equation into a second filter; and when the lane line is determined to be a curve, it is processed using a Bézier curve fitting. Since polynomial curves are simple in form and suitable for most straight road scenarios, using polynomial curves to fit straight roads ensures a good fitting effect and reduces the computational load. Simultaneously, using Bézier curve fitting to fit curves can better fit complex curves, such as S-curves and sharp bends, resulting in smoother curves with smaller errors, compensating for the "heading-up" phenomenon of polynomial curve fitting. Furthermore, this embodiment combines two fitting methods to further reduce the overall computational load of lane line fitting while ensuring good lane line fitting effects for both straight roads and complex curves, and improves the perceived quality of lane lines.

[0108] Figure 8 This is a block diagram illustrating a lane line fitting device 800 according to an exemplary embodiment. (Refer to...) Figure 8 The device 800 includes: The acquisition module 810 is configured to acquire lane line images captured by the image acquisition device; The first determining module 820 is configured to determine the type of lane lines in the lane line image; The first fitting module 830 is configured to perform Bézier curve fitting on the lane line when the type is a curve, to obtain a Bézier lane line equation, which is used to reflect the lane line fitted according to the Bézier curve. The first update module 840 is configured to input the Bezier lane line equation into a first filter, use the first filter to update the initial key point coordinates in the Bezier lane line equation, and determine the first target key point coordinates. The initial key point coordinates include the endpoint coordinates and control point coordinates in the Bezier curve. The second determining module 850 is configured to determine the target lane line fitting result based on the coordinates of the first target key point and the Bézier curve equation.

[0109] Optionally, the first update module 840 is further configured to: The coordinates of the observation points in the lane line are sampled according to the Bessel lane line equation to determine the observation coordinate matrix; Based on the state transition matrix and the second target key point coordinate matrix, a priori key point coordinate matrix is ​​determined. The state transition matrix is ​​used to characterize the motion information of the vehicle from the previous moment to the current moment, and the second target key point coordinate matrix is ​​used to reflect the coordinates of the second target key point determined by the first filter in the previous moment of the current moment. Using the Bézier curve equation and the prior key point coordinate matrix, the coordinates of the observation points in the lane line are calculated to obtain the prior coordinate matrix; The initial keypoint coordinates are updated based on the prior keypoint coordinate matrix, the observed coordinate matrix, the prior coordinate matrix, and the gain of the first filter to determine the coordinates of the first target keypoint.

[0110] Optionally, the first update module 840 is further configured to: The first intermediate matrix is ​​obtained by performing a difference operation between the observed coordinate matrix and the prior coordinate matrix. The second intermediate matrix is ​​obtained by multiplying the gain and the first intermediate matrix. The coordinates of the first target key point are obtained by summing the second intermediate matrix and the prior key point coordinate matrix, and the coordinates of the first target key point are used to replace the initial key point coordinates.

[0111] Optionally, the motion information includes lateral movement distance and longitudinal movement distance; the first update module 840 is further configured to: The prior key point coordinate matrix is ​​determined by multiplying the state transition matrix and the second target key point coordinate matrix.

[0112] Optionally, the first update module 840 is further configured to: An initial observation matrix is ​​determined based on the Bézier curve equation. The initial observation matrix includes a curve parameter matrix and a preset constant matrix. The curve parameter matrix includes curve parameters that can vary within a preset range. By inputting different values ​​of the curve parameters within the preset range into the initial observation matrix, the target observation matrix is ​​obtained; The target observation matrix and the prior key point coordinate matrix are input into the Bézier curve equation to calculate the coordinates of the observation points at the previous time step mapped to the coordinates at the current time step, thus obtaining the prior coordinate matrix.

[0113] Optionally, the device 800 further includes: The third determining module is configured to determine the prior covariance matrix based on the state transition matrix, the first noise covariance of the first noise, and the covariance matrix of the previous time step output by the first filter. The covariance matrix is ​​used to characterize the accuracy of the target key point coordinates output by the first filter. The first noise includes noise in the process of determining the prior key point coordinate matrix. The fourth determining module is configured to determine the gain based on the prior covariance matrix, the target observation matrix, and the second noise covariance matrix of the second noise, wherein the second noise includes the noise of the first filter and / or the noise of the image acquisition device.

[0114] Optionally, the first determining module 820 is further configured to: Based on the lane lines, a polynomial curve fitting process is performed to obtain the initial polynomial curve equation; The type of lane line is determined based on the initial polynomial curve equation.

[0115] Optionally, the first determining module 820 is further configured to: The type is determined by comparing the preset coefficients of the first term with the preset threshold in the initial polynomial curve equation.

[0116] Optionally, the device 800 further includes: The second update module is configured to, when the type is a straight road, input the initial polynomial curve equation into a second filter, update the initial polynomial curve equation using the second filter, output a target polynomial curve equation, and determine the target lane line fitting result based on the target polynomial curve equation.

[0117] The apparatus of this disclosure first determines the type of lane line, and when the type of lane line is determined to be a curve, it then performs Bézier curve fitting processing on the lane line. The Bézier curve fitting processing can better fit complex curves, and the Bézier curve fitting processing is only performed on curves, which can reduce the overall lane fitting calculation.

[0118] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0119] This disclosure also provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the steps of the lane line fitting method provided in this disclosure.

[0120] Figure 9 This is a block diagram illustrating a vehicle 900 according to an exemplary embodiment. For example, vehicle 900 can be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicle. Vehicle 900 can be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0121] Reference Figure 9 The vehicle 900 may include various subsystems, such as an infotainment system 910, a perception system 920, a decision control system 930, a drive system 940, and a computing platform 950. The vehicle 900 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and component of the vehicle 900 can be interconnected via wired or wireless means.

[0122] In some embodiments, the infotainment system 910 may include a communication system, an entertainment system, and a navigation system, etc.

[0123] The perception system 920 may include several sensors for sensing information about the environment surrounding the vehicle 900. For example, the perception system 920 may include a global positioning system (which may be GPS, BeiDou, or other positioning systems), an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and a camera device.

[0124] The decision control system 930 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0125] The drive system 940 may include components that provide powered motion to the vehicle 900. In one embodiment, the drive system 940 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of internal combustion engines, electric motors, and compressed air engines. The engine is capable of converting energy provided by the energy source into mechanical energy.

[0126] Some or all of the functions of the vehicle 900 are controlled by a computing platform 950. The computing platform 950 may include at least one first processor 951 and a memory 952, the first processor 951 being able to execute instructions 953 stored in the memory 952.

[0127] The first processor 951 can be any conventional processor, such as a commercially available CPU. The processor may also include a graphics processing unit (GPU), a field-programmable gate array (FPGA), a system-on-a-chip (SoC), an application-specific integrated circuit (ASIC), or a combination thereof.

[0128] The memory 952 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0129] In addition to instruction 953, memory 952 can also store data, such as road maps, route information, vehicle position, direction, speed, and other data. The data stored in memory 952 can be used by computing platform 950.

[0130] In this embodiment of the disclosure, the first processor 951 may execute instructions 953 to complete all or part of the steps of the lane line fitting method described above.

[0131] Some embodiments of this disclosure also provide a chip system, such as Figure 10As shown, the chip system includes at least one second processor 1001 and at least one interface circuit 1002. The second processor 1001 and the interface circuit 1002 are interconnected via lines. For example, the interface circuit 1002 can be used to receive signals from other devices (e.g., the memory of an electronic device). As another example, the interface circuit 1002 can be used to send signals to other devices (e.g., the second processor 1001). Exemplarily, the interface circuit 1002 can read instructions stored in memory and send those instructions to the second processor 1001. When the instructions are executed by the second processor 1001, the lane line fitting device can perform the steps in the above embodiments. Of course, the chip system may also include other discrete devices, and some embodiments of this disclosure do not specifically limit this.

[0132] In some embodiments of this disclosure, the interface circuit 1002 can acquire data, program instructions, and / or information from the internal storage area of ​​the chip system; it can also acquire data, program instructions, and / or information from outside the chip system.

[0133] Optionally, the chip system may also include memory for storing necessary computer programs and data.

[0134] Those skilled in the art will also understand that the various illustrative logical blocks and steps listed in the embodiments of this application can be implemented by electronic hardware, computer software, or a combination of both. Whether such functionality is implemented through hardware or software depends on the specific application and the overall system design requirements. Those skilled in the art can implement the described functionality using various methods for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of this application.

[0135] Furthermore, the term “exemplary” is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as “exemplary” is not necessarily to be construed as advantageous compared to other aspects or designs. Rather, the use of the term “exemplary” is intended to present the concept in a concrete manner. As used herein, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or clear from the context, “X applies A or B” is intended to mean any of the natural inclusive arrangements. That is, “X applies A or B” satisfies any of the foregoing instances if X applies A; X applies B; or both X applies A and B. Additionally, unless otherwise specified or clear from the context to refer to the singular form, the articles “a” and “an” as used in this application and the appended claims are generally understood to mean “one or more.”

[0136] Similarly, although this disclosure has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding this specification and the accompanying drawings. This disclosure includes all such modifications and variations and is limited only by the scope of the claims. In particular, with respect to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise indicated, the terminology used to describe such components is intended to correspond to any component (functionally equivalent) that performs the specific function of the described component, even if structurally not equivalent to the disclosed structure. Furthermore, although specific features of this disclosure may have been disclosed with respect to only one of several implementations, such features may be combined with one or more other features of other implementations, as may be desired and advantageous to any given or particular application. Moreover, with regard to the terms “comprising,” “owning,” “having,” “having,” or variations thereof as used in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term “including.”

[0137] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

[0138] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A lane line fitting method, characterized in that, include: Acquire lane line images captured by the image acquisition device; Determine the type of lane lines in the lane line image; In the case of a curve, the lane lines are fitted with a Bézier curve to obtain a Bézier lane line equation, which is used to reflect the lane lines fitted according to the Bézier curve. The Bezier lane line equation is input into the first filter, and the initial key point coordinates in the Bezier lane line equation are updated using the first filter to determine the coordinates of the first target key point. The initial key point coordinates include the endpoint coordinates and control point coordinates in the Bezier curve. Based on the coordinates of the first target key point and the Bézier curve equation, the target lane line fitting result is determined.

2. The method according to claim 1, characterized in that, The update performed by the first filter includes the following steps: The coordinates of the observation points in the lane line are sampled according to the Bessel lane line equation to determine the observation coordinate matrix; Based on the state transition matrix and the second target key point coordinate matrix, a priori key point coordinate matrix is ​​determined. The state transition matrix is ​​used to characterize the motion information of the vehicle from the previous moment to the current moment, and the second target key point coordinate matrix is ​​used to reflect the coordinates of the second target key point determined by the first filter in the previous moment of the current moment. Using the Bézier curve equation and the prior key point coordinate matrix, the coordinates of the observation points in the lane line are calculated to obtain the prior coordinate matrix; The initial keypoint coordinates are updated based on the prior keypoint coordinate matrix, the observed coordinate matrix, the prior coordinate matrix, and the gain of the first filter to determine the coordinates of the first target keypoint.

3. The method according to claim 2, characterized in that, The step of updating the initial keypoint coordinates based on the prior keypoint coordinates, the observed coordinate matrix, the prior coordinate matrix, and the gain of the first filter to determine the coordinates of the first target keypoint includes: The first intermediate matrix is ​​obtained by performing a difference operation between the observed coordinate matrix and the prior coordinate matrix. The second intermediate matrix is ​​obtained by multiplying the gain and the first intermediate matrix. The coordinates of the first target key point are obtained by summing the second intermediate matrix and the prior key point coordinate matrix, and the coordinates of the first target key point are used to replace the initial key point coordinates.

4. The method according to claim 2, characterized in that, The motion information includes lateral movement distance and longitudinal movement distance; The step of determining the prior key point coordinate matrix based on the state transition matrix and the second target key point coordinate matrix includes: The prior key point coordinate matrix is ​​determined by multiplying the state transition matrix and the second target key point coordinate matrix.

5. The method according to claim 2, characterized in that, The process of calculating the coordinates of observation points in the lane line using the Bézier curve equation and the prior key point coordinate matrix to obtain the prior coordinate matrix includes: An initial observation matrix is ​​determined based on the Bézier curve equation. The initial observation matrix includes a curve parameter matrix and a preset constant matrix. The curve parameter matrix includes curve parameters that can vary within a preset range. By inputting different values ​​of the curve parameters within the preset range into the initial observation matrix, the target observation matrix is ​​obtained; The target observation matrix and the prior key point coordinate matrix are input into the Bézier curve equation to calculate the coordinates of the observation points at the previous time step mapped to the coordinates at the current time step, thus obtaining the prior coordinate matrix.

6. The method according to claim 5, characterized in that, After the step of inputting the target observation matrix and the prior keypoint coordinate matrix into the Bézier curve equation to calculate the coordinates of the observation points at the previous time step mapped to the coordinates at the current time step, and obtaining the prior coordinate matrix, the method further includes: Based on the state transition matrix, the first noise covariance of the first noise, and the covariance matrix of the previous time step output by the first filter, the prior covariance matrix is ​​determined. The covariance matrix is ​​used to characterize the accuracy of the target key point coordinates output by the first filter. The first noise includes noise in the process of determining the prior key point coordinate matrix. The gain is determined based on the prior covariance matrix, the target observation matrix, and the second noise covariance matrix, wherein the second noise includes the noise of the first filter and / or the noise of the image acquisition device.

7. The method according to claim 1, characterized in that, Determining the type of lane lines in the lane line image includes: Based on the lane lines, a polynomial curve fitting process is performed to obtain the initial polynomial curve equation; The type of lane line is determined based on the initial polynomial curve equation.

8. The method according to claim 7, characterized in that, Determining the type of lane line based on the initial polynomial curve equation includes: The type is determined by comparing the preset coefficients of the first term with the preset threshold in the initial polynomial curve equation.

9. The method according to claim 7 or 8, characterized in that, The method further includes: When the type is a straight road, the initial polynomial curve equation is input into the second filter, the second filter is used to update the initial polynomial curve equation, the target polynomial curve equation is output, and the target lane line fitting result is determined based on the target polynomial curve equation.

10. A lane line fitting device, characterized in that, include: The acquisition module is configured to acquire lane line images captured by the image acquisition device; The first determining module is configured to determine the type of lane lines in the lane line image; The first fitting module is configured to perform Bézier curve fitting on the lane line when the type is a curve, to obtain the Bézier lane line equation, which is used to reflect the lane line fitted according to the Bézier curve. The first update module is configured to input the Bezier lane line equation into a first filter, use the first filter to update the initial key point coordinates in the Bezier lane line equation, and determine the coordinates of the first target key point. The initial key point coordinates include the endpoint coordinates and control point coordinates in the Bezier curve. The second determining module is configured to determine the target lane line fitting result based on the coordinates of the first target key point and the Bézier curve equation.

11. A vehicle, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured as follows: Acquire lane line images captured by the image acquisition device; Determine the type of lane lines in the lane line image; In the case of a curve, the lane lines are fitted with a Bézier curve to obtain a Bézier lane line equation, which is used to reflect the lane lines fitted according to the Bézier curve. The Bezier lane line equation is input into the first filter, and the initial key point coordinates in the Bezier lane line equation are updated using the first filter to determine the coordinates of the first target key point. The initial key point coordinates include the endpoint coordinates and control point coordinates in the Bezier curve. Based on the coordinates of the first target key point and the Bézier curve equation, the target lane line fitting result is determined.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method described in any one of claims 1 to 9.

13. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1 to 9.

Images