A method for calculating a vehicle heading angle in a farmland road surface environment

Abstract

The application discloses a kind of farmland road surface environment under the calculation method of vehicle heading angle.The method includes using camera arranged in the vehicle to be controlled to obtain the current road surface image in front of vehicle driving, determines the current processing road surface point;Obtain the position state of current processing road surface point, the first height value of camera distance ground, the preset parameter of camera and the description information of current processing road surface point in current road surface image;According to position state, first height value, preset parameter and description information, determine the depth estimation value of current road surface point, and determine the current heading angle matched with current processing road surface point according to depth estimation value;According to each current heading angle corresponding to each current processing road surface point, determine the target heading angle matched with current road surface image.The technical scheme of this embodiment obtains more accurate estimated depth information, to improve the accuracy of vehicle driving navigation angle.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of vehicle navigation technology, and in particular to a method for calculating a vehicle heading angle in a farmland road surface environment. BACKGROUND

[0002] In traditional agricultural planting, in some scenarios, agricultural machines need to travel along a navigation line in a field, and the agricultural machines can estimate the depth information of a target point on the navigation line in a shooting mode along a visual axis to obtain heading information.

[0003] Since monocular cameras lack depth information, how to obtain depth information from a sequence of images is currently a research focus. Currently, monocular camera depth estimation methods are divided into two categories: one is based on traditional methods, and the other is based on deep learning methods. The traditional method mainly establishes a dense point cloud through a three-dimensional reconstruction method by shooting around an object to obtain the depth information of a target point. Since the vehicle generally runs along the visual axis direction in a farmland scene, the shooting mode around the object cannot be met, so the method does not work well in this scenario. The deep learning method relies on a large amount of data for network model training, and the data set generally includes monocular images and corresponding depth values. If the training sample is not large enough, the training model will not work well.

[0004] The present application relates to the field of vehicle navigation technology, and in particular to a method for calculating a vehicle heading angle in a farmland road surface environment.

[0005] The present application relates to the field of vehicle navigation technology, and in particular to a method for calculating a vehicle heading angle in a farmland road surface environment. SUMMARY

[0006] The present application provides a method for calculating a vehicle heading angle in a farmland road surface environment to obtain more accurate estimated depth information, thereby improving the accuracy of the navigation angle of the vehicle.

[0007] According to an aspect of the present application, a method for calculating a vehicle heading angle in a farmland road surface environment is provided, which comprises:

[0008] A camera provided on a vehicle to be controlled is used to obtain a current road surface image in front of the vehicle, and a current processing road surface point is determined according to the current road surface image.

[0009] The position state of the current processing road surface point, a first height value of the camera from the ground, preset parameters of the camera, and description information of the current processing road surface point in the current road surface image are obtained.

[0010] determine a depth estimation value of the current road surface point according to the position state, the first height value, the preset parameter and the description information, and determine a current heading angle matched with the current processing road surface point according to the depth estimation value;

[0011] determine a target heading angle matched with the current road surface image according to each current heading angle corresponding to each current processing road surface point.

[0012] According to another aspect of the present application, a vehicle control method is provided, which comprises:

[0013] obtaining a target heading angle corresponding to a current road surface image;

[0014] controlling a vehicle to be controlled to travel by using the target heading angle;

[0015] The method for calculating a vehicle heading angle in a farmland road surface environment according to any embodiment of the present application is used to obtain the target heading angle corresponding to the current road surface image.

[0016] According to another aspect of the present application, a device for calculating a vehicle heading angle in a farmland road surface environment is provided, which comprises:

[0017] a current processing point determination module, configured to obtain a current road surface image in front of a vehicle to be controlled by using a camera arranged on the vehicle, and determine a current processing road surface point according to the current road surface image;

[0018] an information obtaining module, configured to obtain a position state of the current processing road surface point, a first height value of the camera from the ground, a preset parameter of the camera and description information of the current processing road surface point in the current road surface image;

[0019] a current heading angle determination module, configured to determine a depth estimation value of the current road surface point according to the position state, the first height value, the preset parameter and the description information, and determine a current heading angle matched with the current processing road surface point according to the depth estimation value;

[0020] a target heading angle determination module, configured to determine a target heading angle matched with the current road surface image according to each current heading angle corresponding to each current processing road surface point.

[0021] According to another aspect of the present application, a vehicle control device is provided, which comprises:

[0022] each current heading angle obtaining module, configured to obtain a target heading angle corresponding to a current road surface image;

[0023] a vehicle control module, configured to control a vehicle to be controlled to travel by using the target heading angle;

[0024] The target heading angle corresponding to the current road surface image is obtained by using the vehicle heading angle calculation method in any of the embodiments of the present application.

[0025] According to another aspect of the present application, a vehicle is provided, comprising:

[0026] at least one processor; and

[0027] a memory connected to the at least one processor in communication; wherein,

[0028] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the vehicle heading angle calculation method in any of the embodiments of the present application, and the vehicle driving control method in any of the embodiments of the present application.

[0029] Alternatively, the vehicle comprises the vehicle heading angle calculation device in any of the embodiments of the present application, and the vehicle driving control device in any of the embodiments of the present application.

[0030] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the vehicle heading angle calculation method in any of the embodiments of the present application, and the vehicle driving control method in any of the embodiments of the present application.

[0031] The technical solution of the embodiments of the present application obtains the current road surface image in front of the vehicle to be controlled by using the camera arranged on the vehicle, and determines the current processing road surface point according to the current road surface image; obtains the position state of the current processing road surface point, the first height value of the camera from the ground, the preset parameters of the camera, and the description information of the current processing road surface point in the current road surface image; determines the depth estimation value of the current processing road surface point according to the position state, the first height value, the preset parameters and the description information, and determines the current heading angle matched with the current processing road surface point according to the depth estimation value; and determines the target heading angle matched with the current road surface image according to each current heading angle corresponding to each current processing road surface point. Since the position state of each current processing road surface point and the parameters of the camera are considered, the problem of poor depth estimation accuracy caused by three-dimensional reconstruction in the prior art, or the problem of poor depth estimation accuracy caused by insufficient model training effect when the scale of training samples is insufficient, is solved, more accurate estimated depth information is obtained, and the navigation angle accuracy of vehicle driving is improved.

[0032] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1a A flowchart illustrating a method for calculating the heading angle of a vehicle in a farmland road environment, provided in Embodiment 1 of the present invention;

[0035] Figure 1b This is a schematic diagram of navigation line pixel coordinates provided in Embodiment 1 of the present invention;

[0036] Figure 1c This is a schematic diagram illustrating the principle of ground point depth estimation for a horizontal road section, provided in Embodiment 1 of the present invention.

[0037] Figure 1d This is a schematic diagram illustrating the principle of ground point depth estimation on an uphill road section, provided in Embodiment 1 of the present invention.

[0038] Figure 1e This is a schematic diagram illustrating the principle of ground point depth estimation on a downhill road section, provided in Embodiment 1 of the present invention.

[0039] Figure 1f This is a first principle diagram for estimating the depth of a suspended point according to Embodiment 1 of the present invention;

[0040] Figure 1g This is a second principle diagram for estimating the depth of a suspended point provided in Embodiment 1 of the present invention;

[0041] Figure 1h This is a third principle diagram for estimating the depth of a suspended point according to Embodiment 1 of the present invention;

[0042] Figure 2a A flowchart illustrating another method for calculating the heading angle of a vehicle in a farmland road environment, as provided in Embodiment 2 of the present invention;

[0043] Figure 2b This is a schematic diagram of a depth estimate converted to a camera coordinate system according to Embodiment 2 of the present invention;

[0044] Figure 2c This is a farmland ground simulation map provided in Embodiment 2 of the present invention;

[0045] Figure 2d A depth estimation method application flowchart is provided for the second embodiment of the present application;

[0046] Figure 3 A flowchart of a vehicle driving control method is provided for the third embodiment of the present application;

[0047] Figure 4 A structural schematic diagram of a vehicle heading angle calculation device under a farmland road surface environment is provided for the fourth embodiment of the present application;

[0048] Figure 5 A structural schematic diagram of a vehicle driving control device is provided for the fifth embodiment of the present application;

[0049] Figure 6 A structural schematic diagram of a vehicle is provided for the vehicle driving control method and the vehicle heading angle calculation method under a farmland road surface environment. DETAILED DESCRIPTION

[0050] In order to make the personnel in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by the person of ordinary skill in the art without creative labor should belong to the scope of protection of the present application.

[0051] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0052] Embodiment one

[0053] Figure 1aA flowchart of a method for calculating a vehicle heading angle in a farmland road surface environment is provided for Embodiment One of the present application. The embodiment can be applied to the case of navigating and driving a vehicle. The method can be executed by a farmland road surface environment vehicle heading angle calculation device, which can be realized in the form of hardware and / or software. The farmland road surface environment vehicle heading angle calculation device can be configured in a vehicle controller of the vehicle. As shown in Figure 1a , the method comprises:

[0054] S110, acquiring a current road surface image in front of the vehicle to be controlled by using a camera arranged on the vehicle, and determining a current processing road surface point according to the current road surface image.

[0055] The vehicle to be controlled can be, for example, a farm machine. The camera can be fixedly arranged on the roof or other position of the vehicle to be controlled. The camera can be, for example, a monocular camera. The camera can be simultaneously configured with an IMU (Inertial Measurement Unit) and a GNSS (Global Navigation Satellite System).

[0056] Optionally, determining the current processing road surface point according to the current road surface image can comprise: acquiring pixel coordinates of a current road surface navigation line and a plurality of pixel points on the current road surface navigation line according to the current road surface image; and sequentially determining each pixel point as the current processing road surface point.

[0057] The navigation line pixel coordinates of the ridge center can be acquired by a visual perception method, as shown by the dashed line in Figure 1b , since most of the extracted pixel points are ground points, the current processing road surface point can be sequentially determined in the extracted pixel points.

[0058] S120, acquiring a position state of the current processing road surface point, a first height value of the camera from the ground, preset parameters of the camera, and description information of the current processing road surface point in the current road surface image.

[0059] The position state of the current processing road surface point can comprise that the current processing road surface point is in a horizontal road segment, the current processing road surface point is in an uphill road segment, or the current processing road surface point is in a downhill road segment.

[0060] The preset parameters of the camera can comprise a focal length value and a first included angle between a camera axis direction of the camera and a vertical direction. For example, as shown in Figure 1c , wherein the range of AO and BO represents the camera viewing angle; OF represents the camera axis Z cThe direction of the camera's optical axis is denoted as OC c The ray projected into the image AB, with the projection point C, and the segment OC representing the focal length f of the camera. OG represents the ray of the camera looking at the ground point G (equivalent to the current processing road point). The first angle is in Figure 1c corresponds to θ c .

[0061] The description information can include an image first height value of the current road image and a first distance value of the current processing road point from the bottom of the current road image; wherein the first height value corresponds to h in Figure 1c and the first distance value corresponds to d p .

[0062] S130, according to the position state, the first height value, the preset parameter and the description information, determining the depth estimation value of the current road point, and determining the current heading angle matched with the current processing road point according to the depth estimation value.

[0063] In an optional embodiment, according to the position state, the first height value, the preset parameter and the description information, determining the depth estimation value of the current road point can include: determining a second angle between the line of sight direction of the camera looking at the current processing road point and the vertical direction according to the focal length value, the first angle, the image first height value and the first distance value; determining the vertical distance between the camera and the current processing road point according to the first height value based on the position state; determining the depth estimation value of the current processing road point according to the second angle and the vertical distance.

[0064] Since the camera and the current processing road point are not in the same horizontal plane, there can be a vertical distance between the camera and the current processing road point.

[0065] Based on the above optional embodiment, according to the focal length value, the first angle, the image first height value and the first distance value, determining the second angle between the line of sight direction of the camera looking at the current processing road point and the vertical direction can include: determining a second distance value between the first mapping point of the current processing road point in the current road image and the second mapping point of the camera optical axis direction in the current road image under the image coordinate system according to the image first height value and the first distance value; determining a third angle between the camera optical axis direction and the line of sight direction of the camera looking at the current processing road point according to the second distance value and the focal length value; determining the sum of the first angle and the third angle as the second angle.

[0066] The second angle corresponds to θ Figure 1c + β in c . Specifically, the second distance value where h represents the image height, d p represents the pixel size from the ground point G = (u, v) to the bottom of the image, i.e. the first distance value, as shown inFigure 1c OC line segment represents the focal length f, i.e. |OC| = f, so the third angle Thus, the second angle

[0067] Based on the above optional implementation, in one case, when the position state is that the current processing road point is on a horizontal road segment, the first height value is directly determined as the vertical distance. Referring to Figure 1c , G corresponds to the current processing road point, and G is located on the horizontal road segment. At this time, the first height value of the camera from the ground, and the vertical distance between the camera and G are the same, both of which are H c .

[0068] Correspondingly, according to the second angle and the vertical distance, determining the depth estimation value of the current processing road point can include: determining the depth estimation value of the current processing road point through D = H c tan (θ c + β); wherein D represents the depth estimation value; H c represents the first height value; θ c + β represents the second angle; θ c represents the first angle; and β represents the third angle.

[0069] Based on the above optional implementation, in another case, when the position state is that the current processing road point is on an uphill road segment, the vertical distance is determined through H c -Dtanθ 上坡 ; wherein θ 上坡 represents the uphill slope angle of the uphill road segment. Referring to Figure 1d , the current processing road point G is located on the uphill road segment, and the uphill slope angle of the uphill road segment is θ 上坡 . At this time, the first height value of the camera from the ground is H c , but the vertical distance between the camera and G is H c -Dtanθ 上坡 .

[0070] Correspondingly, according to the second angle and the vertical distance, determining the depth estimation value of the current processing road point can include: determining the depth estimation value through D = (H c -Dtanθ 上坡 ) tan (θ c + β).

[0071] Based on the above optional implementation, in another case, when the position state is that the current processing road point is on a downhill road segment, the vertical distance is determined through H c +Dtanθ 下坡 ; wherein θ 下坡represents a downhill slope angle of the downhill road section. Refer to Figure 1e , the current processing road surface point G is located on the downhill road section, and the downhill slope angle of the downhill road section is θ 下坡 , at this time, the first height value of the camera from the ground is H c , but the vertical distance between the camera and G is H c + D tan θ 下坡 .

[0072] Correspondingly, according to the second included angle and the vertical distance, determining the depth estimation value of the current processing road surface point can include: determining the depth estimation value through D = (H c + D tan θ 下坡 ) tan (θ c + β).

[0073] Based on the above optional implementation, there can be another case, when the position state is that the current processing road surface point is at a hanging point (the hanging point can be a pixel point obtained after the road surface is covered), according to the actual pixel coordinates of the current processing road surface point in the current road surface image, determining a second height value of the hanging point from the ground; according to the second included angle, the second height value and the first height value, determining a depth estimation value of the hanging point.

[0074] Exemplarily, refer to Figure 1f , Figure 1g , Figure 1h , if the tree height covers the field ridge, the pixel point extracted by the visual perception team is a hanging point, not a real ground point, so there is a case that the current processing road surface point is at a hanging point. At this time, it can be calculated in the following way, which needs to be calculated together with the previous and next two frames. The following takes the camera coordinate system of p m point as an example.

[0075] Refer to Figure 1f , where p point is a hanging point, and its pixel coordinates are known, so the angle β can be solved. If the calculation continues according to D = H c tan (θ c + β), at this time, the calculated depth value is the depth D m of M m . Next, the pixel coordinates of M m corresponding to p m are solved.

[0076] Refer to Figure 1g , continue to calculate in the way of D = H Figure 1f from p point to the back, the depth estimation value (as shown in Figure 1g ) of each point (such as p n and p m ) on the extended line can be solved. Where p n represents the pixel point behind p point, Mn M is a point on the extension line of OM n The depth can be calculated. Where ΔOM m M n M m M n The length is the difference between the depths of the two, OM m The length can be calculated by similar triangles, as follows:

[0077] Since M m corresponding p m pixel value size, so each point calculated, the point y value is considered as p n y value size, its depth is equal to M m , then its pixel coordinates v can be obtained by the following formula Where K represents the camera's intrinsic matrix, Y1 and Z1 are known.

[0078] If the value is not equal to the pixel coordinates v of p n , then the point is not M m corresponding pixel coordinates p m . If equal, the point is M m corresponding pixel coordinates p m . At this time, the camera coordinate system of p m is also known. The y value is |OM m |, z is the length of M m , the x axis size can be obtained by normalizing the coordinate system, Where K represents the camera's intrinsic matrix, p m pixel coordinates u and v are known, Y1 and Z1 are known, that is, X1 size can be solved. The final result is shown in Figure 1h .

[0079] Further, according to the depth estimate value, determine the current heading angle matched with the current processing road point.

[0080] S140, according to each current heading angle corresponding to each current processing road point, determine the target heading angle matched with the current road image.

[0081] In this embodiment, after all the pixel points of the navigation line are processed as current processing road points in turn, each current heading angle can be obtained, and then the target heading angle matched with the current road image is determined according to each current heading angle.

[0082] In an optional embodiment, determining the target heading angle matching the current road surface image according to each current heading angle corresponding to each current processing road surface point can include: excluding from each current heading angle a current heading angle exceeding a preset offset threshold to obtain remaining current heading angles; averaging the remaining current heading angles to determine a current backup heading angle matching the current road surface image; and performing coordinate system conversion on the current backup heading angle to obtain the target heading angle in a geographic coordinate system.

[0083] Specifically, since a large number of pixel points are extracted, the heading angles corresponding to all pixel points meeting the accuracy requirement can be obtained. If the angle information corresponding to a certain pixel point is greatly different from that of the remaining pixel points, the certain pixel point is excluded. Since there are calculation errors and systematic errors, the obtained heading angles are not unique, so the heading angles corresponding to the remaining pixel points are averaged to obtain the final heading information (i.e., the current backup heading angle) corresponding to the current road surface image. If the road ahead is a curve, the curve can be divided into multiple straight lines, and the heading angle of the straight line closest to the front of the vehicle can be calculated, and the remaining points can be calculated when the vehicle travels nearby next time. Finally, the final heading information is converted to a geographic coordinate system, and the conversion relationship is as follows: wherein The target heading angle in the camera coordinate system can be obtained by combining GNSS information. cam The target heading angle in the camera coordinate system is calculated for the above technical solution.

[0084] The technical solution of the embodiment of the application obtains the current road surface image in front of the vehicle by using the camera arranged on the vehicle to be controlled, and determines the current processing road surface point according to the current road surface image. The position state of the current processing road surface point, the first height value of the camera from the ground, the preset parameters of the camera, and the description information of the current processing road surface point in the current road surface image are obtained. The depth estimation value of the current road surface point is determined according to the position state, the first height value, the preset parameters, and the description information, and the current heading angle matching the current processing road surface point is determined according to the depth estimation value. The target heading angle matching the current road surface image is determined according to each current heading angle corresponding to each current processing road surface point. Since the position state of each current processing road surface point and the parameters of the camera are considered, the problem that the depth estimation accuracy is poor due to the dependence on three-dimensional reconstruction to cause the camera to shoot along the optical axis in the prior art is solved, or the problem that the depth estimation accuracy is poor due to the dependence on the scale of the training sample to cause the model training effect to be poor when the scale is insufficient, and more accurate estimated depth information is obtained, thereby improving the navigation angle accuracy of the vehicle driving.

[0085] Embodiment two

[0086] Figure 2aThe flowchart of another method for calculating the vehicle heading angle in the farmland road surface environment is provided for the second embodiment of the present application. The embodiment refines the current heading angle matched with the current processing road surface point according to the depth estimation value on the basis of the above-mentioned embodiment. As shown in Figure 2a , the method comprises:

[0087] In S210, the current road surface image in front of the vehicle is acquired by using the camera arranged on the vehicle to be controlled, and the current processing road surface point is determined according to the current road surface image.

[0088] In S220, the position state of the current processing road surface point, the first height value of the camera from the ground, the preset parameters of the camera and the description information of the current processing road surface point in the current road surface image are acquired; the preset parameters of the camera further include the installation pitch angle and the intrinsic matrix.

[0089] In S230, the depth estimation value of the current road surface point is determined according to the position state, the first height value, the preset parameters and the description information.

[0090] In S240, the depth estimation value is converted in the coordinate system according to the installation pitch angle, the intrinsic matrix, the depth estimation value, the first height value and the actual pixel coordinates of the current processing road surface point, the estimated three-dimensional coordinates of the depth estimation value in the camera coordinate system are obtained, and the X-axis coordinate value and the Z-axis coordinate value are acquired from the estimated three-dimensional coordinates.

[0091] In an optional implementation, the depth estimation value is converted in the coordinate system according to the installation pitch angle, the intrinsic matrix, the depth estimation value and the first height value, so as to obtain the estimated three-dimensional coordinates of the depth estimation value in the camera coordinate system, which can include: the Z-axis coordinate is obtained through Z1=Dcosγ+H c sinγ; wherein D represents the depth estimation value, γ represents the installation pitch angle, and Hc represents the first height value; the Y-axis coordinate is obtained through Y1=H c cosγ-Dsinγ; the X-axis coordinate is obtained through ; wherein K represents the intrinsic matrix; u 实际 , v 实际 represent the actual pixel coordinates of the current processing road surface point.

[0092] Since the camera can not be in a completely parallel relationship with the ground, there is a certain angle (as shown in Figure 2b ), so it is necessary to convert the depth value to the camera coordinate system to calculate the coordinates of the point in the camera coordinate system. The specific calculation method is as shown in Figure 2b . Wherein OZY represents the original camera coordinate system, and OZ1Y1 represents the camera coordinate system when the camera has an installation angle. Z1=D cosγ+H c sinγ, Y1=H ccosγ-D sinγ, and because the camera coordinate system normalized coordinates and pixel coordinates exist the following relationship, So the actual pixel coordinates can be input to get the camera coordinate system X1 / Z1 ratio constant, that is, the size of X1.

[0093] S250, the ratio of the X-axis coordinate value and the Z-axis coordinate value is determined as the current heading angle matched with the current processing road surface point.

[0094] Based on the optional implementation of S240, the current heading angle can be obtained by the ratio of X1 and Z1.

[0095] It should be noted that before determining the current heading angle matched with the current processing road surface point, the current processing road surface point can also be determined by the estimated pixel coordinates of the current processing road surface point in the pixel coordinate system; wherein X1, Y1 and Z1 represent the estimated three-dimensional coordinates, u 估计 , v 估计 represent the estimated pixel coordinates; K represents the intrinsic matrix of the camera; the estimated pixel coordinates are compared with the actual pixel coordinates of the current processing road surface point to determine whether the estimated pixel coordinates of the current processing road surface point meet the accuracy requirement; the matched current heading angle is determined for the current processing road surface point meeting the accuracy requirement. For example, the accuracy requirement can refer to that the error between the estimated pixel coordinates and the actual pixel coordinates does not exceed a set number of pixels (such as 2 pixels).

[0096] Since the depth estimate value of the current processing ground point is obtained based on the first height value of the camera from the ground. Because the ground of the farmland environment is irregular, as shown in Figure 2c , but the y-axis coordinates of the total point are consistent with the first height value, as shown by point B in Figure 2c . Then under the premise of D=H c tan(θ c +β), only the depth estimate value of point B is calculated correctly, and the depth estimate values of the remaining points all have certain errors. The projection of the camera coordinate system obtained by formula (4) to the pixel coordinate system is compared with the input target point. If they completely coincide, it indicates that the accuracy is reliable, otherwise it is considered that the calculated depth and the estimated y-axis coordinates have errors.

[0097] In order to make the skilled in the art better understand the depth estimation method of the present application, Figure 2dA depth estimation method application flowchart is provided. For the current processing road surface point, the pixel coordinates and the camera internal parameters are used to obtain the coordinates of the camera normalized coordinate system, the depth estimation is performed, the accuracy of the depth estimation result is further verified, the heading angle information of the current processing road surface point meeting the accuracy requirement can be saved, if the accuracy requirement is not met, the next current processing road surface point can be calculated, and the operation of obtaining the coordinates of the camera normalized coordinate system through the pixel coordinates and the camera internal parameters is returned to execute until the current road surface point is completely processed.

[0098] S260, determine the target heading angle matched with the current road surface image according to each current heading angle corresponding to each current processing road surface point.

[0099] The technical scheme of the embodiment of the application obtains the current road surface image in front of the vehicle by using the camera arranged on the vehicle to be controlled, and determines the current processing road surface point according to the current road surface image; obtains the position state of the current processing road surface point, the first height value of the camera from the ground, the preset parameters of the camera, and the description information of the current processing road surface point in the current road surface image, the preset parameters of the camera further include the installation pitch angle and the internal parameter matrix; determines the depth estimation value of the current road surface point according to the position state, the first height value, the preset parameters and the description information; performs coordinate system conversion on the depth estimation value according to the installation pitch angle, the internal parameter matrix, the depth estimation value, the first height value and the actual pixel coordinates of the current processing road surface point, obtains the estimated three-dimensional coordinates of the depth estimation value under the camera coordinate system, and obtains the X-axis coordinate value and the Z-axis coordinate value from the estimated three-dimensional coordinates; determines the ratio of the X-axis coordinate value and the Z-axis coordinate value as the current heading angle matched with the current processing road surface point; and determines the target heading angle matched with the current road surface image according to each current heading angle corresponding to each current processing road surface point. The technical means solves the problems that the prior art depends on three-dimensional reconstruction to cause poor depth estimation accuracy caused by shooting along the optical axis, or depends on the training sample size to cause poor model training effect caused by insufficient scale, and obtains more accurate estimated depth information, thereby improving the navigation angle accuracy of vehicle driving.

[0100] Embodiment three

[0101] Figure 3 A flowchart of a vehicle driving control method is provided for the third embodiment of the application. The embodiment is implemented on the basis of the method for calculating the vehicle heading angle in the farmland road surface environment of each of the above embodiments, and can be applied to the case of navigating and driving the vehicle. The method can be executed by a vehicle driving control device, which can be realized in the form of hardware and / or software, and can be configured in the vehicle controller of the vehicle. As shown in the figure, the method comprises: Figure 3

[0102] ​S310, acquire a target heading angle corresponding to the current road surface image.

[0103] S320, control the vehicle to be controlled to travel by using the target heading angle.

[0104] The technical scheme of the embodiment is based on the vehicle heading angle calculation method in the farmland road surface environment of each of the above embodiments, and the target heading angle corresponding to the current road surface image is acquired. The technical means of controlling the vehicle to be controlled to travel by using the target heading angle is used to acquire higher precision estimated depth information, and the more accurate heading information is calculated based on the high-precision estimated depth information to improve the navigation accuracy of the vehicle.

[0105] Embodiment four

[0106] Figure 4 A structural schematic diagram of a vehicle heading angle calculation device in a farmland road surface environment provided by the fourth embodiment of the application. As shown in the figure, the device comprises a current processing point determination module 410, an information acquisition module 420, a current heading angle determination module 430 and a target heading angle determination module 440. Figure 4

[0107] Among them:

[0108] The current processing point determination module 410 is used to acquire the current road surface image in front of the vehicle to be controlled by using the camera arranged on the vehicle, and to determine the current processing road surface point according to the current road surface image.

[0109] The information acquisition module 420 is used to acquire the position state of the current processing road surface point, the first height value of the camera from the ground, the preset parameters of the camera and the description information of the current processing road surface point in the current road surface image.

[0110] The current heading angle determination module 430 is used to determine the depth estimation value of the current road surface point according to the position state, the first height value, the preset parameters and the description information, and to determine the current heading angle matched with the current processing road surface point according to the depth estimation value.

[0111] The target heading angle determination module 440 is used to determine the target heading angle matched with the current road surface image according to each current heading angle corresponding to each current processing road surface point.

[0112] ​The technical scheme of the embodiment of the present application acquires the current road surface image in front of the vehicle driving through the camera arranged on the vehicle to be controlled, and determines the current processing road surface point according to the current road surface image; acquires the position state of the current processing road surface point, the first height value of the camera from the ground, the preset parameter of the camera and the description information of the current processing road surface point in the current road surface image; determines the depth estimation value of the current processing road surface point according to the position state, the first height value, the preset parameter and the description information, and determines the current heading angle matched with the current processing road surface point according to the depth estimation value. Since the position state of each current processing road surface point and the parameter of the camera are considered, the problem that the depth estimation precision is poor due to the three-dimensional reconstruction in the prior art or the problem that the depth estimation precision is poor due to the poor model training effect caused by the insufficient training sample size is solved, higher-precision estimated depth information is obtained, and the navigation angle precision of the vehicle driving is improved.

[0113] Optionally, the current processing point determination module 410 can be specifically used for:

[0114] According to the current road surface image, the pixel coordinates of the current road surface navigation line and a plurality of pixel points on the current road surface navigation line are acquired;

[0115] The pixel points are sequentially determined as current processing road surface points.

[0116] Optionally, the preset parameter includes a focal length value of the camera and a first included angle between the camera visual axis direction and the vertical direction;

[0117] The description information includes an image first height value of the current road surface image and a first distance value of the current processing road surface point from the bottom of the current road surface image;

[0118] The current heading angle determination module 430 can include:

[0119] The second included angle determination submodule is configured to determine a second included angle between the visual line direction of the camera to the current processing road surface point and the vertical direction according to the focal length value, the first included angle, the image first height value and the first distance value;

[0120] The vertical distance determination submodule is configured to determine the vertical distance between the camera and the current processing road surface point according to the first height value based on the position state;

[0121] The depth estimation value determination submodule is configured to determine the depth estimation value of the current processing road surface point according to the second included angle and the vertical distance.

[0122] Optionally, the second included angle determination submodule can be specifically used for:

[0123] determining a second distance value between the first mapping point of the current road surface image and the second mapping point of the current road surface image according to the image first height value and the first distance value, the second mapping point being a point of intersection between a line of sight of the camera and a line of sight of the camera looking at the current processing road surface point;

[0124] determining a third included angle between the line of sight of the camera and the line of sight of the camera looking at the current processing road surface point according to the second distance value and the focal length value;

[0125] determining the second included angle as a sum of the first included angle and the third included angle.

[0126] Optionally, the vertical distance determining sub-module can comprise a first vertical distance determining unit, configured to:

[0127] when the position state is that the current processing road surface point is on a horizontal road section, directly determining the first height value as the vertical distance;

[0128] Correspondingly, the depth estimation value determining sub-module can comprise a first depth estimation value determining unit, configured to:

[0129] determining the depth estimation value of the current processing road surface point through D=H c tan(θ c +β); wherein D represents the depth estimation value; H c represents the first height value; θ c +β represents the second included angle; θ c represents the first included angle; and β represents the third included angle.

[0130] Optionally, the vertical distance determining sub-module can further comprise a second vertical distance determining unit, configured to:

[0131] when the position state is that the current processing road surface point is on an uphill road section, determining the vertical distance through H c -D tan θ 上坡 ; wherein θ 上坡 represents an uphill slope angle of the uphill road section.

[0132] Correspondingly, the depth estimation value determining sub-module can further comprise a second depth estimation value determining unit, configured to:

[0133] determining the depth estimation value through D=(H c -D tan θ 上坡 ) tan(θ c +β).

[0134] Optionally, the vertical distance determining sub-module can further comprise a third vertical distance determining unit, configured to:

[0135] when the position state is that the current processing road surface point is on a downhill road section, determining the depth estimation value by H c + D tan θ 下坡 determining the vertical distance, wherein θ 下坡 represents a downhill slope angle of the downhill road section;

[0136] Correspondingly, the depth estimation value determination sub-module can further include a third depth estimation value determination unit, configured to:

[0137] determining the depth estimation value by D = (H c + D tan θ 下坡 ) tan (θ c + β).

[0138] Optionally, the depth estimation value determination sub-module can further include a fourth depth estimation value determination unit, configured to:

[0139] when the position state is that the current processing road surface point is on a suspended point, determining a second height value of the suspended point from the ground according to the actual pixel coordinates of the current processing road surface point in the current road surface image; wherein the suspended point is a pixel point obtained after the road surface is covered;

[0140] determining a depth estimation value of the suspended point according to the second included angle, the second height value and the first height value.

[0141] Optionally, the preset parameters of the camera further include an installation pitch angle and an intrinsic matrix;

[0142] The current heading angle determination module 430 can further include:

[0143] An estimated three-dimensional coordinate acquisition sub-module, configured to perform coordinate system conversion on the depth estimation value according to the installation pitch angle, the intrinsic matrix, the depth estimation value, the first height value and the actual pixel coordinates of the current processing road surface point, to obtain an estimated three-dimensional coordinate of the depth estimation value in a camera coordinate system, and acquire an X-axis coordinate value and a Z-axis coordinate value from the estimated three-dimensional coordinate;

[0144] A current heading angle determination sub-module, configured to determine a ratio of the X-axis coordinate value and the Z-axis coordinate value as a current heading angle matched with the current processing road surface point.

[0145] Optionally, the estimated three-dimensional coordinate acquisition sub-module can be specifically configured to:

[0146] obtain the Z-axis coordinate by Z1 = D cos γ + H c sin γ; wherein D represents the depth estimation value, γ represents the installation pitch angle, and Hc represents a first height value;

[0147] by Y1=H c cosγ-D sinγ to obtain the Y-axis coordinate;

[0148] by to obtain the X-axis coordinate; wherein, K represents an intrinsic matrix; u 实际 , v 实际 represents the actual pixel coordinate of the current processing road surface point.

[0149] Optionally, the precision requirement judgment module is configured to, before determining the current heading angle matched with the current processing road surface point:

[0150] by to obtain the estimated pixel coordinate of the current processing road surface point in the pixel coordinate system; wherein, X1, Y1 and Z1 represent the estimated three-dimensional coordinate, u 估计 , v 估计 represents the estimated pixel coordinate; K represents an intrinsic matrix;

[0151] comparing the estimated pixel coordinate with the actual pixel coordinate of the current processing road surface point, to determine whether the estimated pixel coordinate of the current processing road surface point meets the precision requirement;

[0152] determining the matched current heading angle for the current processing road surface point meeting the precision requirement.

[0153] Optionally, the target heading angle determination module 440 can be specifically configured to:

[0154] excluding the current heading angle exceeding the preset offset threshold from the current heading angles to obtain the remaining current heading angles;

[0155] averaging the remaining current heading angles to determine the current backup heading angle matched with the current road surface image;

[0156] performing coordinate system conversion on the current backup heading angle to obtain the target heading angle in the geographic coordinate system.

[0157] The vehicle heading angle calculation device in the farmland road surface environment provided by the embodiment of the application can execute the vehicle heading angle calculation method in the farmland road surface environment provided by any embodiment of the application, and has the corresponding function modules and beneficial effects of the execution method.

[0158] Embodiment five

[0159] Figure 5 Fig. 1 is a structural schematic diagram of a vehicle driving control device provided by the embodiment five of the application. As shown in Fig. 1, the vehicle driving control device comprises a vehicle driving control device 100. Figure 5As shown, the device comprises a target heading angle acquisition module 510 and a vehicle control module 520.

[0160] Wherein:

[0161] The target heading angle acquisition module 510 is configured to acquire a target heading angle corresponding to a current road surface image.

[0162] The vehicle control module 520 is configured to control a to-be-controlled vehicle to travel by using the target heading angle.

[0163] The technical scheme of the embodiment is based on the calculation method of the vehicle heading angle in the farmland road surface environment of the above-mentioned embodiments, and the target heading angle corresponding to the current road surface image is acquired. The technical means of controlling the to-be-controlled vehicle to travel by using the target heading angle is used to acquire higher-precision estimated depth information, and the more accurate heading information is calculated based on the high-precision estimated depth information to improve the navigation accuracy of the vehicle travel.

[0164] The vehicle travel control device provided in the embodiments of the present application can execute the vehicle travel control method provided in any of the embodiments of the present application, and has the function modules and beneficial effects corresponding to the execution method.

[0165] Embodiment six

[0166] Figure 6 A structural schematic diagram of a vehicle 600 that can be used to implement the embodiments of the present application is shown. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described herein and / or claimed.

[0167] As shown in the figure, Figure 6 The vehicle 600 comprises at least one processor 601 and a memory, such as a read-only memory (ROM) 602, a random access memory (RAM) 603, etc., which is communicatively connected to the at least one processor 601, wherein the memory stores a computer program executable by the at least one processor. The processor 601 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 602 or the computer program loaded from the storage unit 608 into the random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the vehicle 600 can also be stored. The processor 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0168] A plurality of components in the vehicle 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the vehicle 600 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0169] The processor 601 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 601 performs various methods and processes described above, such as the method for calculating a vehicle heading angle in a farmland road surface environment and the vehicle travel control method.

[0170] In some embodiments, the method for calculating a vehicle heading angle in a farmland road surface environment and the vehicle travel control method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed onto the vehicle 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded onto the RAM 603 and executed by the processor 601, one or more steps of the method for calculating a vehicle heading angle in a farmland road surface environment and the vehicle travel control method described above can be performed. Alternatively, in other embodiments, the processor 601 can be configured to perform the method for calculating a vehicle heading angle in a farmland road surface environment and the vehicle travel control method by any other appropriate means, such as by means of firmware.

[0171] The vehicle of the present embodiments can also be integrated with a device for calculating a vehicle heading angle in a farmland road surface environment, and a device for controlling vehicle travel.

[0172] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0173] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program

[0174] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0175] To provide for interaction with a user, the systems and techniques described here can be implemented on a vehicle having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the vehicle. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0176] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0177] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0178] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited herein.

[0179] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the disclosure. Accordingly, the disclosure is not limited to the specific embodiments described above, but only by the scope of the appended claims.

Claims

1. A method for calculating the heading angle of a vehicle in a farmland road environment, characterized in that, include: A camera installed on the vehicle to be controlled is used to acquire an image of the current road surface in front of the vehicle, and the current road surface point to be processed is determined based on the current road surface image. The location status of the currently processed road surface point, the first height value of the camera above the ground, the preset parameters of the camera, and the description information of the currently processed road surface point in the current road surface image are obtained. Based on the location status, the first altitude value, the preset parameters, and the description information, determine the depth estimate of the currently processed road surface point, and determine the current heading angle that matches the currently processed road surface point based on the depth estimate; Based on the current heading angles corresponding to each currently processed road surface point, determine the target heading angle that matches the current road surface image; The preset parameters include the focal length of the camera and the first angle between the camera's line of sight and the vertical direction; The descriptive information includes the first image height value of the current road surface image and the first distance value between the currently processed road surface point and the bottom of the current road surface image; Based on the location status, the first height value, the preset parameters, and the description information, the depth estimate of the currently processed road surface point is determined, including: Based on the focal length value, the first included angle, the first height value of the image, and the first distance value, determine the second included angle between the line of sight of the camera looking at the currently processed road surface point and the vertical direction; Based on the position status, the vertical distance between the camera and the currently processed road surface point is determined according to the first height value; The depth estimate of the currently processed road surface point is determined based on the second included angle and the vertical distance. Based on the location status, determining the vertical distance between the camera and the currently processed road surface point according to the first height value includes: When the current processing road surface point is in a horizontal road segment, the first height value is directly determined as the vertical distance. Determining the depth estimate of the currently processed road surface point based on the second included angle and the vertical distance includes: pass Determine the depth estimate of the currently processed road surface point; wherein, This represents the depth estimate; Indicates the first height value; Indicates the second included angle; Indicates the first included angle; Indicates the third included angle; Alternatively, when the location state is such that the currently processed road surface point is on an uphill section, by... Determine the vertical distance; wherein, Indicates the uphill slope angle of an uphill section; Determining the depth estimate of the currently processed road surface point based on the second included angle and the vertical distance includes: pass Determine the depth estimate; Alternatively, when the location state is such that the currently processed road surface point is on a downhill section, by... Determine the vertical distance, wherein, This indicates the downhill slope angle of the downhill section; Determining the depth estimate of the currently processed road surface point based on the second included angle and the vertical distance includes: pass Determine the depth estimate.

2. The method according to claim 1, characterized in that, Determining the current road surface point to be processed based on the current road surface image includes: Based on the current road surface image, obtain the pixel coordinates of the current road surface navigation line and multiple pixels on the current road surface navigation line; Each pixel is sequentially identified as the current road surface point to be processed.

3. The method according to claim 1, characterized in that, Based on the focal length value, the first included angle, the first height value of the image, and the first distance value, determine the second included angle between the camera's line of sight to the currently processed road surface point and the vertical direction, including: Based on the first height value and the first distance value of the image, determine the second distance value between the first mapping point of the currently processed road surface point in the current road surface image and the second mapping point of the camera's line of sight in the current road surface image in the image coordinate system; Based on the second distance value and the focal length value, determine the third angle between the camera's line of sight direction and the camera's line of sight direction when looking at the currently processed road surface point; The sum of the first included angle and the third included angle is determined as the second included angle.

4. The method according to claim 1, characterized in that, Also includes: The position state is when the currently processed road surface point is in a suspended position. Based on the actual pixel coordinates of the currently processed road surface point in the current road surface image, the second height value of the suspended point from the ground is determined; wherein, the suspended point is the pixel point obtained after the road surface is covered. The depth estimate of the suspended point is determined based on the second included angle, the second height value, and the first height value.

5. The method according to claim 1, characterized in that, The preset parameters of the camera also include the installation pitch angle and intrinsic parameter matrix; Determining the current heading angle matching the currently processed road surface point based on the depth estimate includes: Based on the installation pitch angle, the intrinsic parameter matrix, the depth estimate, the first height value, and the actual pixel coordinates of the currently processed road surface point, the depth estimate is transformed to obtain the estimated three-dimensional coordinates of the depth estimate in the camera coordinate system, and the X-axis coordinate value and Z-axis coordinate value are obtained from the estimated three-dimensional coordinates. The ratio of the X-axis coordinate value to the Z-axis coordinate value is determined as the current heading angle that matches the currently processed road surface point.

6. The method according to claim 5, characterized in that, Based on the installation pitch angle, the intrinsic parameter matrix, the depth estimate, and the first height value, a coordinate system transformation is performed on the depth estimate to obtain the estimated three-dimensional coordinates of the depth estimate in the camera coordinate system, including: pass Obtain the Z-axis coordinates; where, This represents the depth estimate. Indicates the installation pitch angle. Indicates the first height value; pass Obtain the Y-axis coordinate; pass Obtain the X-axis coordinates; where, Represents the intrinsic parameter matrix; , This represents the actual pixel coordinates of the currently processed road surface point.

7. The method according to claim 6, characterized in that, Before determining the current heading angle that matches the currently processed road surface point, the process also includes: pass The estimated pixel coordinates of the currently processed road surface point in the pixel coordinate system are obtained; wherein, , and This represents the estimation of three-dimensional coordinates. , Indicates estimated pixel coordinates; Represents the intrinsic parameter matrix; The estimated pixel coordinates are compared with the actual pixel coordinates of the currently processed road surface point to determine whether the estimated pixel coordinates of the currently processed road surface point meet the accuracy requirements. For the current road surface point that meets the accuracy requirements, determine the matching current heading angle.

8. The method according to claim 1, characterized in that, Based on the current heading angles corresponding to each currently processed road surface point, determine the target heading angle that matches the current road surface image, including: The current heading angles that exceed the preset offset threshold are filtered out from the current heading angles to obtain the remaining current heading angles; The average value of the remaining current heading angles is calculated to determine the current backup heading angle that matches the current road surface image; The current backup heading angle is transformed to obtain the target heading angle in the geographic coordinate system.

9. A vehicle driving control method, comprising: Obtain the target heading angle corresponding to the current road surface image; The target heading angle is used to control the movement of the vehicle to be controlled. The feature is that the method for obtaining the target heading angle corresponding to the current road surface image adopts the vehicle heading angle calculation method in farmland road environment as described in any one of claims 1-8.

10. A device for calculating the heading angle of a vehicle in a farmland road environment, characterized in that, include: The current processing point determination module is used to acquire the current road surface image in front of the vehicle using a camera set on the vehicle to be controlled, and determine the current processing road surface point based on the current road surface image. The information acquisition module is used to acquire the position status of the currently processed road surface point, the first height value of the camera above the ground, the preset parameters of the camera, and the description information of the currently processed road surface point in the current road surface image; The current heading angle determination module is used to determine the depth estimate of the currently processed road surface point based on the position state, the first altitude value, the preset parameters and the description information, and to determine the current heading angle that matches the currently processed road surface point based on the depth estimate. The target heading angle determination module is used to determine the target heading angle that matches the current road surface image based on the current heading angles corresponding to each currently processed road surface point. The preset parameters include the focal length of the camera and the first angle between the camera's line of sight and the vertical direction; The descriptive information includes the first image height value of the current road surface image and the first distance value between the currently processed road surface point and the bottom of the current road surface image; The current heading angle determination module includes: The second included angle determination submodule is used to determine the second included angle between the camera's line of sight to the currently processed road surface point and the vertical direction based on the focal length value, the first included angle, the first height value of the image, and the first distance value; The vertical distance determination submodule is used to determine the vertical distance between the camera and the currently processed road surface point based on the position state and the first height value; The depth estimation value determination submodule is used to determine the depth estimation value of the currently processed road surface point based on the second included angle and the vertical distance; The vertical distance determination submodule includes a first vertical distance determination unit, used for: When the current processing road surface point is in a horizontal road segment, the first height value is directly determined as the vertical distance. The depth estimation determination submodule includes a first depth estimation determination unit, used for: pass Determine the depth estimate of the currently processed road surface point; wherein, This represents the depth estimate; Indicates the first height value; Indicates the second included angle; Indicates the first included angle; Indicates the third included angle; The vertical distance determination submodule further includes a second vertical distance determination unit, used for: The location status is when the currently processed road surface point is on an uphill section, through Determine the vertical distance; wherein, Indicates the uphill slope angle of an uphill section; The depth estimation determination submodule further includes a second depth estimation determination unit, used for: pass Determine the depth estimate; The vertical distance determination submodule further includes a third vertical distance determination unit, used for: The location status is when the currently processed road surface point is on a downhill section, through Determine the vertical distance, wherein, This indicates the downhill slope angle of the downhill section; The depth estimation determination submodule further includes a third depth estimation determination unit, used for: pass Determine the depth estimate.

11. A vehicle driving control device, characterized in that, include: The target heading angle acquisition module is used to acquire the target heading angle corresponding to the current road surface image; The vehicle control module is used to control the movement of the vehicle to be controlled using the target heading angle; The feature is that the method for obtaining the target heading angle corresponding to the current road surface image adopts the vehicle heading angle calculation method in farmland road environment as described in any one of claims 1-8.

12. A vehicle, characterized in that, The vehicles include: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to execute the method for calculating the heading angle of a vehicle in a farmland road environment as described in any one of claims 1-8, and the vehicle driving control method as described in any one of claims 9; Alternatively, the vehicle may integrate the vehicle heading angle calculation device for farmland road environment as described in claim 10, and the vehicle driving control device as described in claim 11.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for calculating the heading angle of a vehicle in a farmland road environment as described in any one of claims 1-8, and the vehicle driving control method as described in any one of claims 9.

Images