A road slope determination method, device, vehicle and readable storage medium

Abstract

The present application provides a road slope determination method, device, vehicle and readable storage medium, which is applied to the field of intelligent assisted driving technology, and comprises: obtaining an environmental image and a first environmental point cloud in the direction of vehicle travel; determining a first slope value of the road ahead of the vehicle according to the environmental image; determining a second slope value of the road ahead of the vehicle according to the first environmental point cloud; determining a target slope value of the road ahead of the vehicle according to the first slope value and the second slope value. The method can improve the accuracy of the vehicle's road slope detection, thereby improving the stability of the vehicle in driving in a complex and changeable road environment.

Description

Technical Field

[0001] The present application relates to the field of intelligent assisted driving technology, and more specifically, to a road slope determination method, device, vehicle and readable storage medium in the field of autonomous driving technology. Background Art

[0002] With the continuous development of intelligent assisted driving technology, more and more intelligent assisted driving functions are being added to vehicles, such as intelligent hill assist, automatic parking, adaptive cruise control, etc. Among them, in order to ensure the stability and safety of the vehicle during driving, each intelligent assisted driving function of the vehicle needs to rely on the detected road slope value to adjust the vehicle's driving parameters (such as speed and power output, etc.). However, the current accuracy of the vehicle's detection of the road slope value is low, resulting in the vehicle being unable to drive stably in a complex and changeable road environment. Summary of the invention

[0003] The present application provides a road slope determination method, device, vehicle and readable storage medium, which can improve the accuracy of the vehicle's road slope detection, thereby improving the stability of the vehicle when driving in a complex and changeable road environment.

[0004] In a first aspect, a method for determining a road slope is provided, the method comprising: acquiring an environmental image and a first environmental point cloud in a vehicle's driving direction; determining a first slope value of a road ahead of the vehicle based on the environmental image; determining a second slope value of the road ahead of the vehicle based on the first environmental point cloud; and determining a target slope value of the road ahead of the vehicle based on the first slope value and the second slope value.

[0005] In the above technical scheme, the embodiment of the present application provides a method for determining the slope of a road: first, an environmental image and a first environmental point cloud in the direction of vehicle travel are obtained, and then the second slope value of the road ahead of the vehicle is determined according to the environmental image, and the second slope value of the road ahead of the vehicle is determined according to the first environmental point cloud, and finally, the final slope value of the road ahead of the vehicle is determined according to the first slope value and the second slope value, that is, the target slope value of the road ahead of the vehicle. Since two different types of data, namely, the environmental image and the first environmental point cloud, are collected in the process of determining the target slope value of the road ahead of the vehicle, a more accurate and comprehensive environment of the road ahead of the vehicle can be obtained, and in the case where one data error is large, it can be compensated by another type of data, so as to reduce the influence of abnormal data, thereby improving the accuracy of determining the target slope value of the road ahead of the vehicle according to the environment of the road ahead of the vehicle; in addition, when determining the target slope value of the road ahead of the vehicle, the slope values ​​determined according to different types of data, namely, the first slope value and the second slope value, are integrated, so that the reliability and accuracy of the determined target slope value of the road ahead of the vehicle are higher, thereby improving the stability of the vehicle during driving.

[0006] In combination with the first aspect and the above implementations, in some possible implementations, determining a first slope value of a road ahead of the vehicle according to an environment image includes: identifying a road edge line on the environment image;

[0007] Determine the target position information of the road edge line on the environmental image; determine the first slope value according to the first preset parameter, the second preset parameter and the target position information, the first preset parameter is the distance between the vehicle's image acquisition device and the ground, and the second preset parameter is the focal length of the image acquisition device.

[0008] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, determining a second slope value of the road ahead of the vehicle based on the first environmental point cloud includes: determining a second environmental point cloud in the first environmental point cloud, the second environmental point cloud being the environmental point cloud corresponding to the road ahead of the vehicle; determining a second slope value based on the second environmental point cloud.

[0009] In the above technical scheme, the second environmental point cloud in the first environmental point cloud can be determined, and the second slope value of the road ahead of the vehicle can be determined based on the second environmental point cloud. Since the second environmental point cloud is the environmental point cloud corresponding to the road ahead of the vehicle, when the second slope value of the road ahead of the vehicle is determined based on the environmental point cloud corresponding to the road ahead of the vehicle, that is, the second environmental point cloud, the accuracy of the determined second slope value of the road ahead of the vehicle can be further improved, thereby further improving the accuracy of the target slope value of the road ahead of the vehicle determined based on the second slope value.

[0010] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, determining a second slope value based on the second environment point cloud includes: determining at least three third environment point clouds in the second environment point cloud, wherein the at least three third environment point clouds are random environment point clouds in the second environment point cloud; performing plane fitting based on the at least three third environment point clouds to obtain a target fitting plane, wherein the target fitting plane is a plane corresponding to the road ahead of the vehicle, and the target fitting plane is in the form of a function model; determining the second slope value based on the target fitting plane.

[0011] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, plane fitting is performed based on at least three third environment point clouds to obtain a target fitting plane, including: determining a first fitting plane based on at least three third environment point clouds; calculating the target distance between the environment point clouds other than the at least three third environment point clouds in the second environment point cloud and the first fitting plane; when the target distance is less than a distance threshold, determining the environment point cloud corresponding to the target distance as the target environment point cloud, and the target environment point cloud is represented as an environment point cloud within the first fitting plane; determining the number of target environment point clouds; when the number of target environment point clouds is greater than or equal to the number threshold, determining the first fitting plane as the target fitting plane.

[0012] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, determining the second slope value according to the target fitting plane includes: determining the normal vector of the target fitting plane; determining the second slope value according to the unit vector in the vertical direction and the normal vector of the target fitting plane.

[0013] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, a target slope value of the road ahead of the vehicle is determined based on the first slope value and the second slope value, including: calculating the slope average of the first slope value and the second slope value; and determining the slope average as the target slope value.

[0014] In the above technical scheme, in one possible implementation, the average slope value of the first slope value and the second slope value can be calculated, and the average slope value can be determined as the target slope value of the road ahead of the vehicle, so as to fully integrate the slope values ​​determined according to different types of data, namely the first slope value and the second slope value, thereby improving the accuracy of the determined target slope value of the road ahead of the vehicle.

[0015] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the light intensity of the vehicle's external environment is obtained; when the light intensity is greater than or equal to an intensity threshold, the first weight is determined as the weight of the first slope value, and the second weight is determined as the weight of the second slope value, and the first weight is greater than the second weight; when the light intensity is less than the intensity threshold, the second weight is determined as the weight of the first slope value, and the first weight is determined as the weight of the second slope value; the target slope value is determined based on the first slope value, the second slope value, the first weight and the second weight.

[0016] In the above technical solution, in another possible implementation, when the illumination intensity is greater than or equal to the intensity threshold, the environmental image can display clearer road detail features relative to the first environmental point cloud. Therefore, after determining the first slope value and the second slope value, the illumination intensity of the vehicle's external environment can be obtained, so that when the illumination intensity is greater than or equal to the intensity threshold, that is, when the environmental image can display clear road detail features, the accuracy of the first slope value determined according to the environmental image is higher than the accuracy of the second slope value determined according to the first environmental point cloud, the first weight is determined as the weight of the first slope value, and the second weight, which is less than the first weight, is determined as the weight of the second slope value, and the target slope value is determined based on the first slope value, the second slope value, the first weight and the second weight, so as to improve the accuracy of the first slope value and the second slope value. When the light intensity is less than the intensity threshold, that is, when the environmental image cannot display clear road detail features, the accuracy of the first slope value determined according to the environmental image will be lower than the accuracy of the second slope value determined according to the first environmental point cloud, a second weight that is less than the first weight is determined as the weight of the first slope value, and the first weight is determined as the weight of the second slope value, and the target slope value is determined according to the first slope value, the second slope value, the first weight and the second weight, so as to improve the accuracy of the target slope value of the road ahead of the vehicle determined according to the first slope value and the second slope value.

[0017] In a second aspect, a road slope determination device is provided, the device comprising:

[0018] An acquisition module, used to acquire an environment image and a first environment point cloud in a vehicle driving direction;

[0019] A first determination module, used to determine a first slope value of a road ahead of the vehicle according to the environment image;

[0020] A second determination module, used to determine a second slope value of the road ahead of the vehicle according to the first environment point cloud;

[0021] The third determination module is used to determine a target slope value of the road ahead of the vehicle according to the first slope value and the second slope value.

[0022] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the device also includes an identification module for identifying the road edge line on the environmental image; a first determination module, specifically used to determine the target position information of the road edge line on the environmental image; determine the first slope value according to the first preset parameter, the second preset parameter and the target position information, the first preset parameter is the distance between the vehicle's image acquisition device and the ground, and the second preset parameter is the focal length of the image acquisition device.

[0023] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the second determination module is specifically used to determine a second environmental point cloud in the first environmental point cloud, where the second environmental point cloud is the environmental point cloud corresponding to the road ahead of the vehicle; and determine a second slope value based on the second environmental point cloud.

[0024] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the second determination module is specifically used to determine at least three third environmental point clouds in the second environmental point cloud, and the at least three third environmental point clouds are random environmental point clouds in the second environmental point cloud; the device also includes a fitting module, which is used to perform plane fitting according to at least three third environmental point clouds to obtain a target fitting plane, the target fitting plane is a plane corresponding to the road ahead of the vehicle, and the target fitting plane is in the form of a function model; the second determination module is specifically used to determine a second slope value according to the target fitting plane.

[0025] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the second determination module is specifically used to determine the first fitting plane based on at least three third environmental point clouds; the device also includes a calculation module, which is used to calculate the target distance between the environmental point clouds other than the at least three third environmental point clouds in the second environmental point cloud and the first fitting plane; the second determination module is specifically used to determine the environmental point cloud corresponding to the target distance as the target environmental point cloud when the target distance is less than the distance threshold, and the target environmental point cloud is represented as the environmental point cloud in the first fitting plane; determine the number of target environmental point clouds; when the number of target environmental point clouds is greater than or equal to the number threshold, determine the first fitting plane as the target fitting plane.

[0026] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the second determination module is specifically used to determine the normal vector of the target fitting plane; and determine the second slope value based on the unit vector in the vertical direction and the normal vector of the target fitting plane.

[0027] In combination with the second aspect and the above implementations, in some possible implementations, the third determination module is specifically configured to calculate an average slope value of the first slope value and the second slope value; and determine the average slope value as the target slope value.

[0028] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the device also includes a second acquisition module, used to obtain the light intensity of the external environment of the vehicle; a third determination module, specifically used to determine the first weight as the weight of the first slope value and the second weight as the weight of the second slope value when the light intensity is greater than or equal to the intensity threshold, and the first weight is greater than the second weight; when the light intensity is less than the intensity threshold, the second weight is determined as the weight of the first slope value, and the first weight is determined as the weight of the second slope value; determine the target slope value according to the first slope value, the second slope value, the first weight and the second weight.

[0029] In a third aspect, a vehicle is provided, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the vehicle executes the road slope determination method in the first aspect or any possible implementation of the first aspect.

[0030] In a fourth aspect, a computer program product is provided, which includes: a computer program code, which, when executed on a computer, enables the computer to execute the road slope determination method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0031] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the road slope determination method in the above-mentioned first aspect or any possible implementation of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of an implementation environment of a road slope determination method provided in an embodiment of the present application;

[0033] Figure 2 is a schematic flow chart of a method for determining a road slope provided in an embodiment of the present application;

[0034] Figure 3 is a schematic structural diagram of a road slope determination device provided in an embodiment of the present application;

[0035] Figure 4 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] The technical solution in the present application will be described clearly and in detail below in conjunction with the accompanying drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0037] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0038] Before introducing the solutions of the embodiments of the present application, the professional terms that may be involved in the embodiments of the present application are first explained.

[0039] LiDAR (Light Detection And Ranging) is an active remote sensing technology that measures distance by emitting laser pulses and receiving their echoes. It is widely used in a variety of fields, such as autonomous driving, robotics, mapping, environmental monitoring, archeology, etc. The working principle of LiDAR sensors is to determine the distance by emitting a laser beam and measuring its return time.

[0040] Environmental point cloud: refers to a set of discrete points captured in three-dimensional space by sensors (such as lidar sensors, depth cameras, etc.), which usually carry three-dimensional coordinate information (X, Y, Z) and may also include additional attributes such as color, intensity, reflectivity, etc. Environmental point clouds play an important role in many fields, especially applications involving three-dimensional space perception and understanding, such as autonomous driving, robotics, drone navigation, 3D modeling, virtual reality (VR) and augmented reality (AR).

[0041] Ambient Light Sensor (ALS): An ambient light sensor is a photoelectric sensor that detects the light intensity of the surrounding environment. It usually uses a photodiode or phototransistor to measure light.

[0042] Random Sample Consensus (RANSAC): is a widely used robust estimation technique for estimating parameter models from a set of data containing outliers. The RANSAC algorithm is particularly suitable for situations where there is a lot of noise or outliers, such as in point cloud data processing, image registration, feature matching, etc. The core idea of ​​the RANSAC algorithm is to randomly extract a minimum number of data points from the data set to estimate the model parameters, and then check whether the remaining data points conform to the model (i.e., whether they are consistent). This process is repeated many times, and finally the model with the most consistent points is selected as the final estimation result.

[0043] Hough Transform: It is a technique used to detect simple shapes (such as lines, circles, etc.) in image processing and computer vision. It maps points in the image space to curves or lines in the parameter space, and then detects shapes through the intersection of the curves in the parameter space.

[0044] With the continuous development of intelligent assisted driving technology, more and more intelligent assisted driving functions are being added to vehicles, such as intelligent hill assist, automatic parking, adaptive cruise control, etc. Among them, in order to ensure the stability and safety of the vehicle during driving, each intelligent assisted driving function of the vehicle needs to rely on the detected road slope value to adjust the vehicle's driving parameters (such as speed and power output, etc.). However, the current accuracy of the vehicle's detection of the road slope value is low, resulting in the vehicle being unable to drive stably in a complex and changeable road environment.

[0045] Based on the above problems, the present application provides a road slope determination method, device, vehicle and readable storage medium. The method can improve the accuracy of the vehicle's road slope detection, thereby improving the stability of the vehicle in complex and changeable road environments.

[0046] Figure 1 This is a schematic diagram of the implementation environment of a road slope determination method provided in this application.

[0047] For example, Figure 1 As shown, the implementation environment includes a vehicle controller 101, a lidar sensor 102 and an image acquisition device 103.

[0048] The laser radar sensor 102 is used to collect a first environmental point cloud in the direction of vehicle travel; the image acquisition device 103 is used to collect an environmental image in the direction of vehicle travel.

[0049] Among them, the image acquisition device 103 can be a camera configured on the vehicle's rearview mirror, or a camera configured on the outside of the vehicle (the front of the vehicle), which is not limited in this embodiment of the present application.

[0050] The vehicle controller 101 is an important control unit of the vehicle, which can obtain relevant data of the vehicle, such as the environmental image on the road ahead of the vehicle and the environmental point cloud around the vehicle, and determine the slope value on the road ahead of the vehicle based on the relevant parameters.

[0051] In some embodiments, the vehicle controller 101 obtains the environmental point cloud in the vehicle's driving direction collected by the lidar sensor 102 and the environmental image in the vehicle's driving direction collected by the image acquisition device 103 through a communication bus in the vehicle (e.g., a controller area network (CAN) bus), and determines the slope value of the road ahead of the vehicle based on the environmental point cloud in the vehicle's driving direction and the environmental image in the vehicle's driving direction, thereby achieving the purpose of improving the accuracy of the vehicle controller 101 in detecting the road slope.

[0052] Below through Figure 2 The method provided in the embodiments of the present application is described in detail.

[0053] Figure 2 It is a schematic flowchart of a road slope determination method provided in an embodiment of the present application.

[0054] For example, Figure 2 As shown, taking the execution subject as a vehicle controller as an example, the method 200 includes:

[0055] Step 201: Acquire an environment image and a first environment point cloud in a vehicle driving direction.

[0056] The vehicle's driving direction can be understood as the direction in which the vehicle moves on the road, that is, the direction in which the front of the vehicle is located.

[0057] The first environmental point cloud refers to data recorded in the form of point clouds by some devices on the vehicle (for example, a lidar sensor) that scans the environmental information in the direction of the vehicle's travel. The first environmental point cloud may specifically include the three-dimensional coordinates (X, Y, Z), laser reflection intensity, and color information of each point. The three-dimensional coordinates are used to represent the position information of the surface of each object (for example, obstacles, roads, and pedestrians) in the direction of the vehicle's travel.

[0058] Among them, the three-dimensional coordinates of each point can be the coordinates in the Cartesian coordinate system, specifically including the horizontal axis coordinate, the vertical axis coordinate and the vertical axis coordinate in the Cartesian coordinate system. The Cartesian coordinate system is a three-dimensional space coordinate system established with the laser radar sensor in the vehicle as the origin, and the three-dimensional space coordinate system includes the horizontal axis (x-axis), the vertical axis (y-axis) and the vertical axis (z-axis). The three-dimensional space coordinate system established with the laser radar sensor as the origin satisfies the right-hand rule. The x-axis coordinate in the three-dimensional coordinate represents the longitudinal distance of the scanned object surface relative to the laser radar sensor, the y-axis coordinate represents the lateral offset of the scanned object surface relative to the laser radar sensor, and the z-axis coordinate represents the height of the scanned object surface relative to the laser radar sensor.

[0059] It is understandable that during the process of automatic or non-automatic driving, the vehicle can scan the environment in the direction of vehicle travel through the lidar sensor installed on the vehicle to obtain the corresponding environmental point cloud, i.e., the first environmental point cloud, and send the environmental point cloud collected by the lidar sensor to the vehicle controller.

[0060] The environmental image refers to an image in the direction of vehicle travel acquired by an image acquisition device on the vehicle (for example, a camera disposed outside the vehicle).

[0061] Step 202: Determine a first slope value of the road ahead of the vehicle based on the environment image.

[0062] It should be noted that since the environmental image acquired in the direction of vehicle travel may include multiple objects such as the road in front of the vehicle, pedestrians and obstacles, in order to ensure the accuracy of the first slope value of the road in front of the vehicle determined based on the environmental image, when the vehicle controller acquires the environmental image, it can first identify the road in front of the vehicle on the environmental image, and thus determine the first slope value of the road in front of the vehicle, thereby improving the accuracy and reliability of the first slope value of the road in front of the vehicle determined based on the environmental image.

[0063] The following is a detailed introduction in three parts on the specific implementation method of the vehicle controller determining the first slope value of the road ahead of the vehicle based on the environmental image.

[0064] Part 1: Identify road edge lines on the environment image.

[0065] It can be seen from the above embodiments that the environmental image obtained in the direction of vehicle travel may include various objects such as the road in front of the vehicle, pedestrians, and obstacles. Therefore, in order to ensure the accuracy and reliability of the first slope value of the road in front of the vehicle determined based on the environmental image, in an embodiment of the present application, the vehicle controller can first identify the road edge line on the environmental image, that is, the road edge line of the road in front of the vehicle, so as to ensure the accuracy and reliability of the first slope value of the road in front of the vehicle determined based on the environmental image.

[0066] It should be noted that in order to enable the vehicle controller to accurately identify the road edge lines on the environmental image, after acquiring the environmental image in the direction of vehicle travel, the environmental image can be first subjected to image denoising and image enhancement processing to improve the clarity and contrast of the environmental image, making the road edge lines in the environmental image more vivid and clear, so that the vehicle controller can accurately identify the road edge lines on the environmental image.

[0067] Optionally, the environmental image can be denoised by means of mean filtering, median filtering, Gaussian filtering, bilateral filtering, deep learning network or Kalman filtering, and the environmental image can be enhanced by means of histogram equalization, gamma correction or Laplace enhancement, but the embodiments of the present application are not limited to this.

[0068] In a possible implementation, the Canny edge detection algorithm may be used to identify the road edge line on the environment image. It should be noted that, in order to improve the detection efficiency, the environment image may be converted into a grayscale image to reduce the amount of data, and then the Sobel operator is used to calculate the gradient value of each pixel point on the environment image, so that the gradient value of each pixel point can be used to determine whether the pixel point is on the road edge.

[0069] Specifically, after determining the gradient value of each pixel, it is possible to determine whether each pixel is a pixel on the edge of the road according to two pre-set gradient thresholds (a first gradient threshold and a second gradient threshold). The first gradient threshold is greater than the second gradient threshold, so that when the gradient value of the pixel is greater than the first gradient threshold, the pixel is determined to be a strong edge pixel on the edge of the road; when the gradient value of the pixel is less than the second gradient threshold, the pixel is determined to be an irrelevant pixel that is not on the edge of the road. It should be noted that in order to obtain a clear and definite road edge line, the irrelevant pixel needs to be suppressed in this case, that is, the specific attributes of the irrelevant pixel, such as brightness and color intensity, are eliminated, so as to highlight the pixel on the edge of the road, thereby making the road edge line clearer in the environmental image; when the gradient value of the pixel is greater than the second gradient threshold and less than the first gradient threshold, the pixel is determined to be a weak edge pixel on the edge of the road.

[0070] It should be noted that in order to improve the accuracy of the pixel points determined to be on the edge of the road, after determining that the pixel point is a weak edge pixel point, it is necessary to further determine whether the pixel point (weak edge pixel point) is a pixel point on the edge of the road. Specifically, it can be detected whether the weak edge pixel point is connected to all strong edge pixels. When it is determined that the weak edge pixel point is connected to all strong edge pixels, it is determined that the weak edge pixel point is a pixel point on the edge of the road; when it is determined that the weak edge pixel point is not connected to some strong edge pixels, the pixel point is suppressed to ensure the accuracy of the pixel points determined to be on the edge of the road. Furthermore, after determining the pixel point on the edge of the road on the environmental image, the identified road edge line can be displayed on the environmental image in combination with the Hough Transform.

[0071] Optionally, the road edge line on the environment image can also be identified by a target detection algorithm (You Only Look Once, YOLO), a single shot multi-box detection algorithm (Single Shot MultiBox Detector, SSD) or a deep learning network model, but this embodiment of the present application is not limited to this.

[0072] The second part is to determine the target position information of the road edge line on the environment image.

[0073] It should be noted that the identified road edge line of the road ahead of the vehicle can be divided into a left road edge line and a right road edge line, that is, determining the target position information of the road edge line on the environmental image can be understood as determining the target position information of the left road edge line on the environmental image and the target position information of the right road edge line on the environmental image.

[0074] In a possible implementation, the YOLO algorithm can be used to first determine the upper left corner coordinates and lower right corner coordinates of the bounding boxes of the left road edge line and the right road edge line on the environment image, and then calculate the center coordinates of the left road edge line on the environment image, that is, the target position information of the left road edge line on the environment image, based on the upper left corner coordinates and lower right corner coordinates of the bounding box of the right road edge line on the environment image, and calculate the center coordinates of the right road edge line on the environment image, that is, the target position information of the right road edge line on the environment image, based on the upper left corner coordinates and lower right corner coordinates of the bounding box of the right road edge line on the environment image, thereby obtaining the center coordinates of the left road edge line and the right road edge line on the environment image, that is, obtaining the target position information of the left road edge line and the right road edge line on the environment image.

[0075] Exemplarily, when the upper left corner coordinates and lower right corner coordinates of the bounding box of the left road edge line on the environmental image are determined to be (X1, Y1) and (X2, Y2) respectively, the center coordinates of the left road edge line on the environmental image are calculated, that is, the target position information of the left road edge line on the environmental image is (X1-X2, Y1-Y2); when the upper left corner coordinates and lower right corner coordinates of the bounding box of the right road edge line on the environmental image are determined to be (X3, Y3) and (X4, Y4) respectively, the center coordinates of the right road edge line on the environmental image are calculated, that is, the target position information of the right road edge line on the environmental image is (X3-X4, Y3-Y4).

[0076] Part three: determining a first slope value according to a first preset parameter, a second preset parameter and target position information, wherein the first preset parameter is the distance between the image acquisition device of the vehicle and the ground, and the second preset parameter is the focal length of the image acquisition device.

[0077] In the embodiment of the present application, the vehicle controller may specifically use the following formula (1) to determine the first slope value of the road ahead of the vehicle:

[0078] Formula (1)

[0079] in, is the first slope value of the road ahead of the vehicle, h is the distance between the vehicle's image acquisition device and the ground, f is the focal length of the image acquisition device, is the position information of the left road edge line in the longitudinal (y-axis) direction on the environment image, is the position information of the right road edge line in the longitudinal direction of the environment image, It can be understood as the distance difference between the left road edge line and the right road edge line in the longitudinal axis direction.

[0080] In order to improve the efficiency of the vehicle controller in determining the first slope value, in a possible implementation, after the vehicle controller determines the first slope value based on the environmental image, it can determine whether there is a target object on the environmental image, so that if there is a target object, the environmental image and the target object are stored with the corresponding first slope value, so that when the vehicle obtains the same image as the environmental image again, the first slope value can be directly determined according to the pre-stored correspondence, thereby improving the efficiency of the vehicle controller in determining the first slope value.

[0081] The target objects are iconic buildings, such as schools, office buildings, banks or shopping malls.

[0082] Optionally, whether a target object exists in the environment image can be identified by means of a target detection algorithm, a single multi-border detection algorithm, or a deep learning network model, which is not limited in the embodiments of the present application.

[0083] Step 203: Determine a second slope value of the road ahead of the vehicle based on the first environment point cloud.

[0084] It should be noted that since the first environmental point cloud obtained in the direction of vehicle travel may include multiple point clouds such as the environmental point cloud corresponding to the road in front of the vehicle, the environmental point cloud corresponding to pedestrians, and the environmental point cloud corresponding to obstacles, in order to ensure the accuracy of the second slope value of the road in front of the vehicle determined according to the first environmental point cloud, when the vehicle controller obtains the first environmental point cloud, it can first determine the environmental point cloud corresponding to the road in front of the vehicle, that is, the second environmental point cloud, and then determine the second slope value of the road in front of the vehicle based on the second environmental point cloud, thereby improving the accuracy and reliability of the second slope value of the road in front of the vehicle determined according to the first environmental point cloud.

[0085] The following is a detailed introduction in three parts on the specific implementation method of the vehicle controller determining the second slope value of the road ahead of the vehicle based on the first environmental point cloud.

[0086] Part 1: determining a second environment point cloud in the first environment point cloud, where the second environment point cloud is an environment point cloud corresponding to the road ahead of the vehicle.

[0087] It should be noted that in order to reduce the amount of calculation of the vehicle controller so that the vehicle controller can accurately and quickly determine the second environment point cloud in the first environment point cloud, after obtaining the first environment point cloud in the vehicle's driving direction, the first environment point cloud can be first subjected to point cloud denoising processing to eliminate the environment point cloud with large errors, that is, the environment point cloud with a large degree of discreteness, in the second environment point cloud, so that the vehicle controller can accurately and quickly determine the second environment point cloud in the first environment point cloud.

[0088] Optionally, the first environment point cloud may be subjected to point cloud denoising processing by means of statistical filtering, curvature calculation, or neighborhood construction, and this is not limited in the embodiments of the present application.

[0089] It should be noted that, from the above embodiments, it can be seen that the first environmental point cloud may include multiple point clouds such as environmental point clouds corresponding to the road in front of the vehicle, environmental point clouds corresponding to pedestrians, and environmental point clouds corresponding to obstacles. Therefore, when determining the environmental point cloud corresponding to the road in front of the vehicle in the first environmental point cloud, that is, the second environmental point cloud, it is necessary to divide the first environmental point cloud into ground point clouds, that is, the environmental point cloud corresponding to the road in front of the vehicle (second environmental point cloud) and non-ground point clouds, that is, objects on the road in front of the vehicle, such as pedestrians, buildings or vehicles.

[0090] In a possible implementation, the vehicle controller may segment the first environmental point cloud according to a preset height threshold. Specifically, the environmental point cloud with a height less than or equal to the height threshold is determined as the environmental point cloud corresponding to the road ahead of the vehicle (the second environmental point cloud), and the environmental point cloud with a height greater than the height threshold is determined as the environmental point cloud corresponding to the object on the road ahead of the vehicle (the non-ground point cloud).

[0091] Optionally, the vehicle controller may also segment the first environment point cloud by any one of a geometric relationship method, a normal vector method, an absolute height method, and an average height method, etc., which is not limited in the embodiments of the present application.

[0092] Part 2: determining a second slope value according to the second environment point cloud.

[0093] Specifically, after the vehicle controller determines the second environmental point from the first environmental point cloud, it can perform plane fitting on the second environmental point cloud through the Random Sample Consensus (RANSAC) algorithm to obtain a target fitting plane, that is, a plane corresponding to the road in front of the vehicle, and determine the second slope value based on the target fitting plane.

[0094] Optionally, the second environment point cloud may be plane-fitted by a least squares method (LSM) or a principal component analysis algorithm (PCA), which is not limited in the embodiment of the present application.

[0095] The following is a detailed introduction in three steps, in which the vehicle controller determines a specific implementation method for the second slope value based on the second environment point cloud.

[0096] Step 1: Determine at least three third environment point clouds in the second environment point cloud, where the at least three third environment point clouds are random environment point clouds in the second environment point cloud.

[0097] Specifically, after determining the environmental point cloud corresponding to the road ahead of the vehicle from the first environmental point cloud, that is, the second environmental point cloud, the vehicle controller can randomly select at least three environmental point clouds from the second environmental point cloud, that is, at least three third environmental point clouds, so as to perform plane fitting based on the at least three randomly selected third environmental point clouds to obtain the plane corresponding to the road ahead of the vehicle, that is, the target fitting plane.

[0098] It should be noted that, since at least three environmental point clouds are required to define a plane, when determining the target fitting plane, at least three environmental point clouds need to be randomly selected from the second environmental point cloud, that is, at least three third environmental point clouds.

[0099] Step 2: Perform plane fitting based on at least three third environment point clouds to obtain a target fitting plane, where the target fitting plane is a plane corresponding to the road in front of the vehicle, and the target fitting plane is in the form of a function model.

[0100] Exemplarily, the vehicle controller can perform plane fitting on at least three third environment point clouds through the RANSAC algorithm to obtain a target fitting plane. It should be noted that the target fitting plane is in the form of a function model, which can also be called a plane equation. For example, the plane equation can be a three-variable linear equation.

[0101] Since the third environmental point cloud is randomly selected from the second environmental point cloud, the error of the target fitting plane obtained by plane fitting at least three third environmental point clouds may be large, that is, the environmental point clouds other than the third environmental point cloud in the second environmental point cloud may not be in the same plane (target fitting plane) as the third environmental point cloud, that is, the target fitting plane obtained by fitting cannot truly reflect the true shape of the plane corresponding to the road in front of the vehicle.

[0102] Therefore, in order to make the target fitting plane close to the plane corresponding to the road in front of the vehicle, that is, to truly reflect the true shape of the plane corresponding to the road in front of the vehicle, in a possible implementation, the vehicle controller performs plane fitting according to at least three third environment point clouds, and a specific implementation method of obtaining the target fitting plane may include the following steps:

[0103] Step (1): determining a first fitting plane according to at least three third environment point clouds.

[0104] The first fitting plane may be understood as an initially determined target fitting plane, that is, an initially determined plane corresponding to the road ahead of the vehicle.

[0105] Exemplarily, the vehicle controller performs plane fitting on at least three third environment point clouds through the RANSAC algorithm, thereby obtaining a first fitting plane. It should be noted that the first fitting plane is in the form of a function model, which can also be called a plane equation.

[0106] Step (2), calculating the target distance between the first fitting plane and at least three environment point clouds other than the third environment point cloud in the second environment point cloud.

[0107] Exemplarily, when the plane equation corresponding to the first fitting plane is (ax+by+cz+d=0), and the three-dimensional coordinates of the environmental point clouds in the second environmental point cloud except for at least three third environmental point clouds are (X1, Y1, Z1), the vehicle controller can calculate the target distance between (X1, Y1, Z1) and (ax+by+cz+d=0).

[0108] Specifically, the vehicle controller may use the following formula (2) to determine the target distance between the environment point clouds other than at least three third environment point clouds in each second environment point cloud and the first fitting plane:

[0109] Formula (2)

[0110] Where D is the target distance, a, b and c are the coefficients of the plane equation corresponding to the first fitting plane, which can also be understood as the normal vector of the first fitting plane. = (a, b, c), d is the distance from the first fitting plane to the origin of the three-dimensional coordinate system.

[0111] Step (3): when the target distance is less than the distance threshold, the environment point cloud corresponding to the target distance is determined as the target environment point cloud, and the target environment point cloud is represented as the environment point cloud in the first fitting plane.

[0112] It should be noted that, since the target distance between the environmental point cloud other than at least three third environmental point clouds in the second environmental point cloud and the first fitting plane is less than the distance threshold, it indicates that the point cloud is located near the first fitting plane, that is, the point belongs to the point on the road surface in front of the corresponding vehicle. Therefore, when the target distance is less than the distance threshold, the vehicle controller can determine the environmental point cloud corresponding to the target distance as the environmental point cloud in the first fitting plane, that is, the target environmental point cloud.

[0113] Exemplarily, the distance threshold is 22 mm. When the vehicle controller calculates that the target distance between at least three environmental point clouds other than the third environmental point clouds in the second environmental point cloud and the first fitting plane is 20 mm, the vehicle controller can determine the environmental point cloud corresponding to the target distance as the target environmental point cloud.

[0114] Step (4), determine the number of target environment point clouds.

[0115] It should be noted that after determining the first fitting plane, the vehicle controller will calculate the target distance between the environmental point clouds of each non-third environmental point cloud in the second environmental point cloud and the first fitting plane, and when it is determined that the target distance between an environmental point cloud and the first fitting plane is less than the distance threshold and the environmental point cloud is determined as the target environmental point cloud, the vehicle controller will simultaneously record the number of determined target environmental point clouds, so as to subsequently judge whether the first fitting plane is close to the plane corresponding to the road ahead of the vehicle based on the number of target environmental point clouds, that is, whether it can truly reflect the true shape of the plane corresponding to the road ahead of the vehicle.

[0116] Step (5): when the number of the target environment point cloud is greater than or equal to the number threshold, the first fitting plane is determined as the target fitting plane.

[0117] It should be noted that, when the number of target environment point clouds is greater than or equal to the quantity threshold, it indicates that the first fitting plane can be close to the plane corresponding to the road in front of the vehicle, that is, it can truly reflect the true shape of the plane corresponding to the road in front of the vehicle. Therefore, when the vehicle controller determines that the number of target environment point clouds is greater than or equal to the quantity threshold, the first fitting plane can be determined as the target fitting plane, so as to ensure that the determined target fitting plane can truly reflect the true shape of the plane corresponding to the road in front of the vehicle.

[0118] In a possible implementation, when it is determined that the number of target environment point clouds is less than a quantity threshold, the vehicle controller can update the parameters of the RANSAC algorithm (for example, the number of iterations, sample set size, and confidence, etc.) so that the first fitting plane fitted by the RANSAC algorithm can allow the target environment point clouds whose number is greater than or equal to the quantity threshold to be within the plane.

[0119] Step 3: Determine the second slope value based on the target fitting plane.

[0120] It can be seen from the above embodiments that the target fitting plane may be in the form of a plane equation. For example, the plane equation may be a three-variable linear equation.

[0121] For example, when the plane equation of the target fitting plane is a three-variable linear equation (ax+by+cz+d=0), the vehicle controller can determine that the normal vector of the plane equation is = (a, b, c), and according to the normal vector = (a, b, c) and the unit vector in the vertical direction (z-axis direction) = (0, 0, 1), determine the second slope value.

[0122] Specifically, the vehicle controller can use the following formula (3) to determine the second slope value:

[0123] Formula (3)

[0124] in, is the second slope value of the road ahead of the vehicle, is the unit vector in the vertical direction ( ), is the normal vector to the plane equation ( ).

[0125] Step 204: Determine a target slope value of the road ahead of the vehicle according to the first slope value and the second slope value.

[0126] It should be noted that after the vehicle controller determines the first slope value and the second slope value, the first slope value and the second slope value can be fused, and the fused slope value can be determined as the target slope value of the road ahead of the vehicle.

[0127] Among them, in order to fully integrate the slope values ​​determined according to different types of data (the first environmental point cloud and the environmental image), that is, the first slope value and the second slope value, in a possible implementation, the vehicle controller can calculate the slope average of the first slope value and the second slope value, and determine the slope average as the target slope value of the road ahead of the vehicle, so as to fully integrate the slope values ​​determined according to different types of data, thereby improving the reliability and accuracy of the target slope value of the road ahead of the vehicle that is finally determined.

[0128] For example, when the first slope value The second slope value is 20° When it is 22°, the vehicle controller can calculate the first slope value (20°) and the second slope value The average slope of (22°) is ( + ) / 2=(20°+22°) / 2=21°, and the average slope value (21°) is determined as the target slope value of the road ahead of the vehicle.

[0129] In another possible implementation, when the illumination intensity is greater than or equal to the intensity threshold, the environment image can display clearer road detail features relative to the first environment point cloud. Therefore, after the vehicle controller determines the first slope value and the second slope value, the illumination intensity of the vehicle's external environment can be obtained, so that when the illumination intensity is greater than or equal to the intensity threshold, that is, when the environment image can display clear road detail features, and the accuracy of the first slope value determined based on the environment image is higher than the accuracy of the second slope value determined based on the first environment point cloud, the first weight is determined as the weight of the first slope value, and the second weight, which is less than the first weight, is determined as the weight of the second slope value, and the target slope value is determined based on the first slope value, the second slope value, the first weight, and the second weight, so as to improve the accuracy of the first slope value and the second slope value. The accuracy of the target slope value of the road ahead of the vehicle determined by the slope value; when the light intensity is less than the intensity threshold, that is, when the environmental image cannot display clear road detail features, the accuracy of the first slope value determined based on the environmental image will be lower than the accuracy of the second slope value determined based on the first environmental point cloud, the second weight that is less than the first weight is determined as the weight of the first slope value, and the first weight is determined as the weight of the second slope value, and the target slope value is determined based on the first slope value, the second slope value, the first weight and the second weight, so as to improve the accuracy of the target slope value of the road ahead of the vehicle determined based on the first slope value and the second slope value.

[0130] Exemplarily, when the intensity threshold is 1000lx, the first weight is 0.7, the second weight is 0.3, the first slope value is 18°, and the second slope value is 22°, when the acquired light intensity of the vehicle's external environment is 1050lx, that is, when the light intensity of the vehicle's external environment (1050lx) is greater than the intensity threshold (1000lx), the vehicle controller can determine the first weight (0.7) as the weight of the first slope value (18°), and after determining that the weight of the first slope value (18°) is 0.7 and determining that the weight of the second slope value (22°) is 0.3, calculate the target slope value by weighted averaging. Specifically, the final calculated target slope value is: 18°×0.7+22°×0.3=19.2°.

[0131] Optionally, the light intensity of the vehicle's external environment can be obtained through devices such as an ambient light sensor (ALS), a photoresistor, a photodiode, a phototransistor, or an infrared sensor, but this is not limited in the embodiments of the present application.

[0132] To summarize, a method for determining a road slope is provided in an embodiment of the present application: since two different types of data, namely, an environmental image and a first environmental point cloud, are collected in the process of determining a target slope value of the road ahead of the vehicle, a more accurate and comprehensive environment of the road ahead of the vehicle can be obtained, and in the case where one type of data has a large error, it can be compensated by another type of data, thereby reducing the impact of abnormal data and improving the accuracy of determining the target slope value of the road ahead of the vehicle based on the environment of the road ahead of the vehicle; in addition, when determining the target slope value of the road ahead of the vehicle, the slope values ​​determined according to different types of data, namely, the first slope value and the second slope value, are integrated, thereby making the reliability and accuracy of the determined target slope value of the road ahead of the vehicle higher, thereby improving the stability of the vehicle during driving.

[0133] Figure 3 It is a structural schematic diagram of a road slope determination device provided in an embodiment of the present application.

[0134] For example, Figure 3 As shown, the device 300 includes:

[0135] A first acquisition module 301 is used to acquire an environment image and a first environment point cloud in the direction of vehicle travel;

[0136] A first determination module 302, configured to determine a first slope value of the road ahead of the vehicle according to the environment image;

[0137] A second determination module 303, configured to determine a second slope value of the road ahead of the vehicle according to the first environmental point cloud;

[0138] The third determination module 304 is used to determine a target slope value of the road ahead of the vehicle according to the first slope value and the second slope value.

[0139] In one possible implementation, the device 300 also includes an identification module for identifying a road edge line on an environmental image; a first determination module 302, specifically for determining target position information of the road edge line on the environmental image; and determining a first slope value based on a first preset parameter, a second preset parameter, and the target position information, wherein the first preset parameter is the distance between the image acquisition device of the vehicle and the ground, and the second preset parameter is the focal length of the image acquisition device.

[0140] In a possible implementation, the second determination module 303 is specifically used to determine a second environment point cloud in the first environment point cloud, where the second environment point cloud is an environment point cloud corresponding to the road ahead of the vehicle; and determine a second slope value according to the second environment point cloud.

[0141] In one possible implementation, the second determination module 303 is further specifically used to determine at least three third environmental point clouds in the second environmental point cloud, and the at least three third environmental point clouds are random environmental point clouds in the second environmental point cloud; the device 300 also includes a fitting module, which is used to perform plane fitting based on at least three third environmental point clouds to obtain a target fitting plane, where the target fitting plane is a plane corresponding to the road ahead of the vehicle, and the target fitting plane is in the form of a function model; the second determination module 303 is further specifically used to determine a second slope value based on the target fitting plane.

[0142] In one possible implementation, the second determination module 303 is further used to determine the first fitting plane based on at least three third environmental point clouds; the device 300 also includes a calculation module, which is used to calculate the target distance between the environmental point clouds other than the at least three third environmental point clouds in the second environmental point cloud and the first fitting plane; the second determination module 303 is further used to determine the environmental point cloud corresponding to the target distance as the target environmental point cloud when the target distance is less than the distance threshold, and the target environmental point cloud is represented as the environmental point cloud in the first fitting plane; determine the number of target environmental point clouds; and determine the first fitting plane as the target fitting plane when the number of target environmental point clouds is greater than or equal to the number threshold.

[0143] In a possible implementation, the second determination module 303 is further configured to determine a normal vector of the target fitting plane; and determine a second slope value according to a unit vector in a vertical direction and the normal vector of the target fitting plane.

[0144] In a possible implementation, the third determination module 304 is specifically configured to calculate an average slope value of the first slope value and the second slope value; and determine the average slope value as the target slope value.

[0145] In one possible implementation, the device 300 also includes a second acquisition module, used to acquire the light intensity of the external environment of the vehicle; a third determination module 304, specifically used to determine the first weight as the weight of the first slope value and the second weight as the weight of the second slope value when the light intensity is greater than or equal to an intensity threshold, and the first weight is greater than the second weight; when the light intensity is less than the intensity threshold, determine the second weight as the weight of the first slope value and determine the first weight as the weight of the second slope value; determine the target slope value based on the first slope value, the second slope value, the first weight and the second weight.

[0146] Figure 4 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application.

[0147] For example, Figure 4The vehicle 400 includes: a memory 401 and a processor 402, wherein the memory 401 stores an executable program code 403, and the processor 402 is used to call and execute the executable program code 403 to perform a road slope determination method provided in an embodiment of the present application.

[0148] In addition, an embodiment of the present application also protects a device, which may include a memory and a processor, wherein the memory stores an executable program code, and the processor is used to call and execute the executable program code to execute a road slope determination method provided by an embodiment of the present application.

[0149] In this embodiment, the functional modules of the device can be divided according to the above method example. For example, each functional module can be corresponded, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0150] In the case of dividing each functional module according to each function, the device may also include a second acquisition module, an identification module, a calculation module, and a fitting module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.

[0151] It should be understood that the device provided in this embodiment is used to execute a road slope determination method provided in the above embodiment, and thus can achieve the same effect as the above implementation method.

[0152] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to a vehicle, the processing module may be used to control and manage the actions of the vehicle. The storage module may be used to support the vehicle in executing related program codes, etc.

[0153] The processing module may be a processor or a controller, which may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module may be a memory.

[0154] In addition, the device provided in the embodiments of the present application may specifically be a chip, component or module, and the chip may include a connected processor and memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a road slope determination method provided in the above embodiments.

[0155] This embodiment also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement a road slope determination method provided in the above embodiment.

[0156] This embodiment also provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement a road slope determination method provided in the above-mentioned embodiment.

[0157] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here.

[0158] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0159] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0160] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for determining a road slope, characterized in that: The method comprises: Acquire an environment image and a first environment point cloud in the vehicle's driving direction; Determining a first slope value of a road ahead of the vehicle according to the environment image; Determining a first slope value of the road ahead of the vehicle according to the environment image includes: Identifying a road edge line on the environment image; Determining target position information of the road edge line on the environment image; Determine the first slope value according to a first preset parameter, a second preset parameter and the target position information, the first preset parameter being the distance between the image acquisition device of the vehicle and the ground, and the second preset parameter being the focal length of the image acquisition device; Determining a second slope value of the road ahead of the vehicle according to the first environmental point cloud; A target slope value of the road ahead of the vehicle is determined according to the first slope value and the second slope value.

2. The method according to claim 1, characterized in that The step of determining a second slope value of the road ahead of the vehicle according to the first environmental point cloud includes: Determine a second environment point cloud in the first environment point cloud, where the second environment point cloud is an environment point cloud corresponding to the road ahead of the vehicle; The second slope value is determined according to the second environment point cloud.

3. The method according to claim 2, characterized in that The determining the second slope value according to the second environment point cloud includes: Determine at least three third environment point clouds in the second environment point cloud, where the at least three third environment point clouds are random environment point clouds in the second environment point cloud; Performing plane fitting according to the at least three third environment point clouds to obtain a target fitting plane, wherein the target fitting plane is a plane corresponding to the road in front of the vehicle, and the target fitting plane is in the form of a function model; The second slope value is determined according to the target fitting plane.

4. The method according to claim 3, characterized in that The performing plane fitting according to the at least three third environment point clouds to obtain a target fitting plane includes: Determining a first fitting plane according to the at least three third environment point clouds; Calculating a target distance between an environment point cloud other than the at least three third environment point clouds in the second environment point cloud and the first fitting plane; When the target distance is less than a distance threshold, determining the environment point cloud corresponding to the target distance as a target environment point cloud, wherein the target environment point cloud is represented as an environment point cloud within the first fitting plane; Determining the number of the target environment point clouds; When the number of the target environment point clouds is greater than or equal to a number threshold, the first fitting plane is determined as the target fitting plane.

5. The method according to claim 3, characterized in that: The step of determining the second slope value according to the target fitting plane includes: Determining a normal vector of the target fitting plane; The second slope value is determined according to a unit vector in a vertical direction and a normal vector of the target fitting plane.

6. The method according to claim 1, characterized in that Determining a target slope value of the road ahead of the vehicle according to the first slope value and the second slope value includes: Calculating a slope average of the first slope value and the second slope value; The slope average value is determined as the target slope value.

7. The method according to claim 1, characterized in that Determining a target slope value of the road ahead of the vehicle according to the first slope value and the second slope value includes: Acquire the light intensity of the external environment of the vehicle; When the illumination intensity is greater than or equal to an intensity threshold, determining a first weight as a weight of the first slope value, and determining a second weight as a weight of the second slope value, the first weight being greater than the second weight; In a case where the illumination intensity is less than the intensity threshold, determining the second weight as the weight of the first slope value, and determining the first weight as the weight of the second slope value; The target slope value is determined according to the first slope value, the second slope value, the first weight, and the second weight.

8. A road slope determination device, characterized in that: The device comprises: A first acquisition module, used to acquire an environment image and a first environment point cloud in the direction of vehicle travel; A first determination module, configured to determine a first slope value of the road ahead of the vehicle according to the environment image; Determining a first slope value of the road ahead of the vehicle according to the environment image includes: Identifying a road edge line on the environment image; Determining target position information of the road edge line on the environment image; Determine the first slope value according to a first preset parameter, a second preset parameter and the target position information, the first preset parameter being the distance between the image acquisition device of the vehicle and the ground, and the second preset parameter being the focal length of the image acquisition device; A second determination module, configured to determine a second slope value of the road ahead of the vehicle according to the first environmental point cloud; The third determination module is used to determine a target slope value of the road ahead of the vehicle according to the first slope value and the second slope value.

9. A vehicle, characterized in that: The vehicle comprises: A memory for storing executable program codes; A processor, configured to call and run the executable program code from the memory, so that the vehicle executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 7 is implemented.

Images