Vehicle driving control methods, devices and storage media

Abstract

This application discloses a vehicle driving control method, device, and storage medium, belonging to the field of vehicle control technology. The method includes: acquiring video images of the road ahead of the vehicle; extracting edge information of the vehicle ahead from the video images, including the bottom edge line of the vehicle ahead; calculating the vertical displacement of the bottom edge line of the vehicle ahead; determining the degree of potholes in the road ahead based on the vertical displacement, including no potholes, slight potholes, and severe potholes; and adjusting the vertical control of the vehicle in response to whether the pothole degree is slight or severe. This allows for advance preparation for potholes on the road ahead, enabling the vehicle to predict and adapt to the degree of potholes, thereby improving the safety and stability of the vehicle when driving on pothole-prone roads while controlling costs and energy consumption.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a vehicle driving control method, device and storage medium. Background Technology

[0002] During vehicle operation, it is necessary to predict the road surface conditions ahead and adjust the vehicle's vertical control based on the degree of potholes and the presence of obstacles to help the vehicle travel smoothly. Current technologies, such as LiDAR and sensors, detect the degree of potholes ahead, but these suffer from high cost and energy consumption. Furthermore, the use of LiDAR is limited when the distance to the vehicle in front is close, as it cannot collect road surface information. Therefore, how to predict the road surface conditions ahead under various operating conditions while controlling cost and energy consumption, ensuring smooth vehicle driving, and thus guaranteeing vehicle safety and stability, is a problem that needs to be solved. Summary of the Invention

[0003] This application provides a vehicle driving control method, device, and storage medium, which can be used to ensure smooth vehicle operation while controlling cost and energy consumption. The technical solution is as follows:

[0004] On one hand, embodiments of this application provide a vehicle driving control method, the method comprising:

[0005] Collect video images of the road ahead of the vehicle;

[0006] Edge information of the vehicle in front is extracted from the video image, and the edge information of the vehicle in front includes the bottom edge line of the vehicle in front;

[0007] Calculate the vertical sway of the bottom edge line of the vehicle in front;

[0008] The degree of potholes in the road ahead of the vehicle is determined based on the vertical runout, and the degree of potholes includes no potholes, slight potholes, and severe potholes.

[0009] The vertical control of the vehicle is adjusted in response to whether the pothole is classified as a minor pothole or a severe pothole.

[0010] On the other hand, a vehicle driving control device is provided, the device comprising:

[0011] The acquisition module is used to acquire video images of the road ahead of the vehicle;

[0012] An extraction module is used to extract edge information of a vehicle in front from the video image, wherein the edge information of the vehicle in front includes the bottom edge line of the vehicle in front;

[0013] The calculation module is used to calculate the vertical sway of the bottom edge line of the vehicle in front;

[0014] The determination module is used to determine the pothole level of the road in front of the vehicle based on the vertical sway, wherein the pothole level includes no potholes, minor potholes, and severe potholes.

[0015] An adjustment module is used to adjust the vertical control of the vehicle in response to whether the pothole is of the degree of minor pothole or the degree of severe pothole.

[0016] On the other hand, a non-transitory computer-readable storage medium is also provided, characterized in that the computer-readable storage medium stores a computer program, which is loaded and executed by a processor to implement any of the vehicle driving control methods described above.

[0017] On the other hand, a computer program product is also provided, the computer program product including computer instructions, which, when executed by a processor, implement the steps of any of the vehicle driving control methods described above.

[0018] The technical solution provided in this application brings at least the following beneficial effects:

[0019] This application acquires video images of the road ahead of a vehicle, extracts the edge information of the vehicle ahead from the video images, including the bottom edge line of the vehicle ahead, which facilitates the prediction of the pothole level of the road where the vehicle is located based on the bottom edge line of the vehicle ahead; then calculates the vertical runout of the bottom edge line of the vehicle ahead, and determines the pothole level of the road ahead based on the vertical runout, realizing a fast and convenient detection of the pothole level of the road ahead; responding to whether the pothole level is light or severe, the vertical control of the vehicle is adjusted to prepare for the pothole road ahead in advance, realizing the vehicle's prediction and adaptation to the pothole level of the road surface, improving the safety and stability of the vehicle driving in pothole road conditions under various operating conditions while controlling costs and energy consumption. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of an implementation environment provided in an embodiment of this application;

[0022] Figure 2This is a flowchart of a vehicle driving control method provided in an embodiment of this application;

[0023] Figure 3 This is a flowchart of the control logic for vehicle driving provided in an embodiment of this application;

[0024] Figure 4 This is a schematic diagram of the structure of a vehicle driving control device provided in an embodiment of this application. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0026] This application provides a method for controlling vehicle movement. Please refer to... Figure 1 The diagram illustrates the implementation environment of the method provided in this application embodiment. This implementation environment may include: a DCU (Domain Control Unit) 11, an in-vehicle camera 12, a large screen on the center console 13, and a suspension controller 14.

[0027] In one possible implementation, the DCU11 acquires video images of the road in front of the vehicle through the vehicle-mounted camera 12, performs grayscale processing on the video images using OpenCV (an open-source computer vision library), converting the video images from color format to grayscale format, and then smooths the grayscale images using a Gaussian filter to obtain a noise-reduced grayscale image.

[0028] For example, after acquiring the denoised grayscale image, the DCU11 calculates the gradient intensity and gradient direction of each pixel in the denoised grayscale image using the Sobel operator to obtain the gradient image corresponding to the denoised grayscale image. The DCU11 performs non-maximum suppression on the gradient image to identify edge pixels. The DCU11 performs double thresholding on the edge pixels to distinguish between strong edge pixels and weak edge pixels. The DCU11 removes weak edge pixels that do not have strong edge pixels in their neighborhood, and then connects the strong edge pixels with the retained weak edge pixels to obtain the bottom edge line of the vehicle in front.

[0029] Optionally, a preset line is pre-marked in the lens of the vehicle-mounted camera 12, and a spatial coordinate system is established in the camera's view. The DCU 11 calculates in real time the instantaneous angle and vertical distance between the bottom edge line of the vehicle in front and the preset line in the vertical direction, and then determines the vertical jump of the bottom edge line of the vehicle in front based on the instantaneous angle and vertical distance. The DCU 11 can also calculate the height change of the edge line in real time, and determine the vertical jump of the bottom edge line of the vehicle in front based on the height change of the edge line.

[0030] In one possible implementation, the DCU11 continuously monitors the vertical movement of the vehicle's bottom edge line. If the number of times the vertical movement exceeds a first height threshold within a certain time period does not exceed a certain number, the DCU11 determines that there are no potholes in the road ahead. If the number of times the vertical movement exceeds the first height threshold but is less than or equal to a second height threshold exceeds a certain number, the DCU11 determines that there are minor potholes in the road ahead. If the number of times the vertical movement exceeds the second height threshold exceeds a certain number, the DCU11 determines that there are severe potholes in the road ahead. After determining the pothole level, the DCU11 displays the pothole level of the road ahead on the large screen 13 of the vehicle's center console.

[0031] For example, after determining the degree of potholes in the road ahead of the vehicle, if the potholes are minor, the suspension controller 14 increases the stiffness of the suspension system, appropriately increases low-frequency damping, and maintains appropriate high-frequency damping; if the potholes are severe, the suspension controller 14 decreases the stiffness of the suspension system, appropriately increases low-frequency damping, and decreases high-frequency damping. The DCU 11, the vehicle camera 12, the large screen 13 on the center console, and the suspension controller 14 establish a communication connection via a wired or wireless network.

[0032] Based on the above Figure 1 The implementation environment shown in this application provides a vehicle driving control method, such as... Figure 2 As shown, taking the application of this method to DCU as an example, the method includes steps 201-205.

[0033] In step 201, the DCU acquires video images of the road ahead of the vehicle.

[0034] In one possible implementation, the DCU acquires video images of the road ahead of the vehicle via an onboard camera mounted on the vehicle's windshield to capture real-time images of the road. Optionally, after acquiring the captured video images, the images are converted to grayscale to obtain a corresponding grayscale image; the grayscale image is then smoothed to obtain a noise-reduced grayscale image.

[0035] Optionally, the video image is converted to grayscale, including: the DCU performs grayscale processing on the video image using OpenCV, converting the video image from color format to grayscale format. After obtaining the grayscale image corresponding to the video image, the grayscale image is smoothed, including: the DCU performs smoothing processing on the grayscale image using a Gaussian filter to obtain a noise-reduced grayscale image.

[0036] In step 202, the DCU extracts the edge information of the vehicle in front from the video image, including the bottom edge line of the vehicle in front.

[0037] In one possible implementation, the edge information of the vehicle in front includes the bottom edge line of the vehicle. After acquiring the denoised grayscale image, the DCU extracts the edge information of the vehicle in front from the video image, including: detecting the gradient intensity of each pixel in the denoised grayscale image to obtain the gradient image corresponding to the denoised grayscale image, the gradient image including the gradient intensity of each pixel; performing non-maximum suppression on the gradient image to determine the edge pixels of the gradient image; performing double thresholding on the edge pixels to determine strong edge pixels and weak edge pixels; and determining the edge information of the vehicle in front based on the weak edge pixels and strong edge pixels.

[0038] For example, the gradient intensity and gradient direction of each pixel in the denoised grayscale image are calculated using the Sobel operator to obtain the gradient image corresponding to the denoised grayscale image, wherein the gradient image includes the gradient intensity and gradient direction of each pixel.

[0039] Optionally, after obtaining the gradient image, non-maximum suppression is performed on the gradient image, including: if the gradient strength of the current pixel is greater than the strength of two neighboring pixels along the gradient direction, the intensity of the pixel is retained; if the gradient strength of the current pixel is less than or equal to the intensity of at least one of the two neighboring pixels along the gradient direction, the intensity of the pixel is set to 0. Each pixel is processed in the same way to determine edge pixels.

[0040] In one possible implementation, after determining the edge pixels, the edge pixels are then subjected to double thresholding, including: in response to the gradient strength of the edge pixel being greater than or equal to a first threshold, the edge pixel is designated as a strong edge pixel; in response to the gradient strength of the edge pixel being less than the first threshold but greater than or equal to a second threshold, the edge pixel is designated as a weak edge pixel, wherein the first threshold is greater than the second threshold.

[0041] Optionally, after determining the edge pixels, the DCU compares the gradient intensity of each edge pixel with a first threshold and a second threshold. If the gradient intensity of the edge pixel is greater than or equal to the first threshold, the edge pixel is designated as a strong edge pixel; if the gradient intensity of the edge pixel is less than the first threshold but greater than or equal to the second threshold, the edge pixel is designated as a weak edge pixel. For example, the first and second thresholds can be set empirically, and the first threshold must be greater than the second threshold.

[0042] In one possible implementation, after determining the strong edge pixels and weak edge pixels, if a strong edge pixel exists in the neighborhood of any weak edge pixel, the weak edge pixel is retained; if no strong edge pixel exists in the neighborhood of any weak edge pixel, the weak edge pixel is removed. The strong edge pixels and the retained weak edge pixels are then connected to obtain the bottom edge line of the vehicle in front.

[0043] In step 203, the DCU calculates the vertical sway of the bottom edge line of the vehicle ahead.

[0044] For example, after determining the edge information of the vehicle ahead, the DCU calculates the vertical jump of the bottom edge line of the vehicle ahead based on the edge information, including: calculating the vertical jump of the bottom edge line of the vehicle ahead based on the instantaneous angle and vertical distance between the edge line and a preset line on the road surface where the vehicle is located, the preset line being located at a fixed position in the video image; and / or calculating the vertical jump of the bottom edge line of the vehicle ahead based on the height change of the edge line.

[0045] In one possible implementation, a preset line is pre-marked in the lens of the vehicle-mounted camera; that is, the preset line is located at a fixed position in the video image. The DCU acquires the instantaneous angle and vertical distance between the edge line and the preset line on the road surface where the vehicle is located in real time, including: establishing a spatial coordinate system in the camera's image, and calculating in real time the instantaneous angle and vertical distance between the bottom edge line of the vehicle in front and the preset line in the vertical direction. Then, based on the instantaneous angle and vertical distance, the vertical displacement of the bottom edge line of the vehicle in front is determined according to the correspondence between the instantaneous angle and vertical distance and the vertical displacement.

[0046] Alternatively, in another possible implementation, the height change of the edge line can be calculated in real time. Based on the height change of the edge line, the vertical sway of the bottom edge line of the vehicle ahead can be determined according to the correspondence between the height change of the edge line and the vertical sway. For example, the correspondence between instantaneous angle and vertical distance and the vertical sway, as well as the correspondence between the height change of the edge line and the vertical sway, can be determined experimentally.

[0047] In step 204, the DCU determines the pothole level of the road ahead of the vehicle based on the vertical runout, which includes no potholes, minor potholes, and severe potholes.

[0048] In one possible implementation, pothole severity is categorized as no potholes, minor potholes, and severe potholes. The vertical movement of the vehicle's bottom edge line is continuously monitored. If the number of times the vertical movement exceeds a first height threshold within a certain time period does not exceed a certain threshold, the road ahead is determined to have no potholes. If the number of times the vertical movement exceeds the first height threshold but is less than or equal to a second height threshold exceeds a certain threshold, the road ahead is determined to have minor potholes. If the number of times the vertical movement exceeds the second height threshold exceeds a certain threshold, the road ahead is determined to have severe potholes.

[0049] For example, after determining the degree of potholes, the degree of potholes on the road ahead is displayed on the large screen of the vehicle's center console, thereby prompting the driver to prepare in advance. Optionally, the first height threshold, a certain number of times, the first height threshold, and the second height threshold can be set based on experience, but the second height threshold must be greater than the first height threshold.

[0050] In step 205, in response to whether the pothole is mild or severe, the DCU adjusts the vertical control of the vehicle.

[0051] Optionally, after determining the degree of potholes in the road ahead of the vehicle, in response to whether the potholes are minor or severe, the DCU adjusts the vertical control of the vehicle, including: if the potholes are minor, increasing the stiffness of the suspension system through the vehicle's suspension controller, appropriately increasing low-frequency damping, and keeping high-frequency damping unchanged; if the potholes are severe, decreasing the stiffness of the suspension system through the vehicle's suspension controller, appropriately increasing low-frequency damping, and decreasing high-frequency damping.

[0052] For example, in the case of minor potholes, increasing the stiffness of the suspension system improves its responsiveness, allowing the vehicle to maintain better contact with the road, reducing body roll, and enhancing handling and stability, enabling the vehicle to better cope with minor road surface changes. Increasing low-frequency damping controls the movement of the vehicle chassis, allowing the vehicle to remain stable even with minor bumps. And maintaining appropriate high-frequency damping absorbs vibrations caused by minor potholes, improving ride comfort.

[0053] In one possible implementation, when dealing with severe potholes, reducing the stiffness of the suspension system makes it more flexible, thus more effectively absorbing impacts and preventing excessive shock to the vehicle's chassis. This helps reduce vibrations felt by occupants and improves ride comfort. Lowering high-frequency damping allows the suspension system to move more flexibly, better adapting to severely uneven road surfaces while effectively preventing pitch and roll.

[0054] Optionally, the system continuously monitors the pothole condition of the road ahead of the vehicle. If it detects that the vehicle has moved from a slightly potholed section to a smooth section, the suspension controller appropriately reduces the stiffness of the suspension system and lowers the low-frequency damping, while keeping the high-frequency damping unchanged. If it detects that the vehicle has moved from a severely potholed section to a smooth section, the suspension controller increases the stiffness of the suspension system to the level before the reduction, increases the high-frequency damping to the level before the reduction, and lowers the low-frequency damping to the level before the increase.

[0055] In summary, with Figure 3The following is an example of a vehicle driving control logic flowchart. The execution entity can be the DCU. Step 301: The onboard camera acquires video images of the road ahead of the vehicle. Step 302: Extract the edge information of the vehicle ahead. Step 303: Calculate the vertical movement of the bottom edge line of the vehicle ahead. Step 304: Determine the degree of potholes in the road ahead. Step 305: Determine whether the potholes are minor or severe. If the potholes are minor or severe, proceed to step 306; if not, proceed to step 307. Step 306: Adjust the stiffness and damping of the suspension system through the vehicle's suspension controller. Step 307: Determine that there are no potholes in the road ahead.

[0056] This application embodiment acquires video images of the road ahead of the vehicle, extracts the edge information of the vehicle ahead from the video images, including the bottom edge line of the vehicle ahead, which facilitates the prediction of the pothole level of the road where the vehicle is located based on the bottom edge line of the vehicle ahead; then, it calculates the vertical runout of the bottom edge line of the vehicle ahead, and determines the pothole level of the road ahead based on the vertical runout, realizing a fast and convenient detection of the pothole level of the road ahead; in response to whether the pothole level is mild or severe, the vertical control of the vehicle is adjusted to prepare for the pothole road ahead in advance, realizing the vehicle's prediction and adaptation to the pothole level of the road surface, improving the safety and stability of the vehicle driving in pothole road conditions under various operating conditions while controlling costs and energy consumption.

[0057] See Figure 4 This application provides a vehicle driving control device, which includes:

[0058] Acquisition module 401 is used to acquire video images of the road in front of the vehicle;

[0059] The extraction module 402 is used to extract edge information of a vehicle in front from a video image, the edge information of which includes the bottom edge line of the vehicle in front.

[0060] Calculation module 403 is used to calculate the vertical sway of the bottom edge line of the vehicle in front;

[0061] The determination module 404 is used to determine the pothole level of the road ahead of the vehicle based on the vertical runout, including no potholes, minor potholes, and severe potholes.

[0062] The adjustment module 405 is used to adjust the vertical control of the vehicle in response to whether the pothole is mild or severe.

[0063] In one possible implementation, the calculation module 403 is used to calculate the vertical jump based on the instantaneous angle and vertical distance between the edge line and a preset line on the road surface where the vehicle is located, the preset line being located at a fixed position in the video image; and / or to calculate the vertical jump based on the height change of the edge line.

[0064] In one possible implementation, the extraction module 402 is further configured to perform grayscale processing on the video image to obtain a grayscale image corresponding to the video image; and to perform smoothing processing on the grayscale image to obtain a noise-reduced grayscale image.

[0065] In one possible implementation, the extraction module 402 is used to detect the gradient intensity of each pixel in the noise-reduced grayscale image to obtain the gradient image corresponding to the noise-reduced grayscale image, the gradient image including the gradient intensity of each pixel; perform non-maximum suppression on the gradient image to determine the edge pixels of the gradient image; perform double thresholding on the edge pixels to determine strong edge pixels and weak edge pixels; and determine the edge information of the vehicle in front based on the weak edge pixels and strong edge pixels.

[0066] In one possible implementation, the extraction module 402 is used to identify edge pixels as strong edge pixels in response to the gradient intensity of the edge pixels being greater than or equal to a first threshold; and to identify edge pixels as weak edge pixels in response to the gradient intensity of the edge pixels being less than the first threshold but greater than or equal to a second threshold, wherein the first threshold is greater than the second threshold.

[0067] In one possible implementation, the adjustment module 405 is used to adjust the stiffness and damping characteristics of the vehicle's suspension system in response to whether the pothole is of a mild or severe degree.

[0068] This device acquires video images of the road ahead of the vehicle, extracts the edge information of the vehicle in front from the video images, including the bottom edge line of the vehicle, which facilitates the prediction of the pothole level on the road. It then calculates the vertical runout of the bottom edge line of the vehicle in front and determines the pothole level based on this vertical runout, enabling rapid and convenient detection of pothole levels. Responding to whether the pothole level is minor or severe, the device adjusts the vehicle's vertical control to prepare for potholes ahead, achieving prediction and adaptation of the vehicle to road surface pothole levels. This improves the safety and stability of vehicles driving on pothole-prone roads under various conditions while controlling costs and energy consumption.

[0069] It should be noted that the apparatus provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above 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. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0070] In an exemplary embodiment, a computer-readable storage medium is also provided, which stores at least one computer program, which is loaded and executed by a processor of a computer device to enable the computer to implement any of the above-described vehicle driving control methods.

[0071] In one possible implementation, the aforementioned computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0072] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform any of the vehicle driving control methods described above.

[0073] It should be noted that all information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in this application have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the video images of the road in front of the vehicle, the vertical movement of the vehicle's bottom edge line, and the degree of potholes in the road in front of the vehicle involved in this application were all obtained with full authorization.

[0074] It should be understood that "multiple" as used in this article refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0075] It should be noted that the terms "first," "second," etc. (if applicable) in the specification and claims of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0076] The above description is merely an exemplary embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A method for controlling vehicle movement, characterized in that, The method includes: Collect video images of the road ahead of the vehicle; Edge information of the vehicle in front is extracted from the video image, and the edge information of the vehicle in front includes the bottom edge line of the vehicle in front; The vertical jump is calculated based on the instantaneous angle and vertical distance between the bottom edge line and a preset line on the road surface where the vehicle is located, where the preset line is located at a fixed position in the video image; and / or The vertical sway is calculated based on the height change of the bottom edge line; The autonomous driving controller continuously monitors the vertical sway of the bottom edge line of the vehicle; If the vertical sway exceeds the first height threshold a certain number of times within a certain time period, the autonomous driving controller determines that there are no potholes on the road ahead of the vehicle; if the vertical sway exceeds the first height threshold but is less than or equal to the second height threshold a certain number of times, the autonomous driving controller determines that there are minor potholes on the road ahead; if the vertical sway exceeds the second height threshold a certain number of times, the autonomous driving controller determines that there are severe potholes on the road ahead. The vertical control of the vehicle is adjusted in response to whether the pothole is classified as a minor pothole or a severe pothole.

2. The method according to claim 1, characterized in that, Before extracting the edge information of the vehicle ahead from the video image, the method further includes: The video image is converted to grayscale to obtain a grayscale image corresponding to the video image; The grayscale image is smoothed to obtain a noise-reduced grayscale image.

3. The method according to claim 2, characterized in that, Extracting edge information of the vehicle ahead from the video image includes: The gradient intensity of each pixel in the noise-reduced grayscale image is detected to obtain the gradient image corresponding to the noise-reduced grayscale image, wherein the gradient image includes the gradient intensity of each pixel; Non-maximum suppression is applied to the gradient image to determine the edge pixels of the gradient image; Perform dual thresholding on the edge pixels to determine strong edge pixels and weak edge pixels; The edge information of the vehicle in front is determined based on the weak edge pixels and the strong edge pixels.

4. The method according to claim 3, characterized in that, The step of performing dual threshold processing on the edge pixels to determine strong edge pixels and weak edge pixels includes: In response to the gradient intensity of the edge pixel being greater than or equal to a first threshold, the edge pixel is designated as a strong edge pixel; In response to the gradient intensity of the edge pixel being less than the first threshold and greater than or equal to the second threshold, the edge pixel is designated as a weak edge pixel, where the first threshold is greater than the second threshold.

5. The method according to claim 1, characterized in that, The adjustment of the vertical control of the vehicle in response to whether the pothole level is mild or severe includes: In response to the pothole severity being either mild or severe, the stiffness and damping characteristics of the vehicle's suspension system are adjusted.

6. A vehicle driving control device, characterized in that, The device includes: The acquisition module is used to acquire video images of the road ahead of the vehicle; An extraction module is used to extract edge information of a vehicle in front from the video image, wherein the edge information of the vehicle in front includes the bottom edge line of the vehicle in front; The calculation module is used to calculate the vertical jump based on the instantaneous angle and vertical distance between the bottom edge line and a preset line on the road surface where the vehicle is located, wherein the preset line is located at a fixed position in the video image; and / or to calculate the vertical jump based on the height change of the bottom edge line. The determination module is used by the autonomous driving controller to continuously monitor the vertical undulation of the bottom edge line of the vehicle; if the number of times the vertical undulation exceeds a first height threshold within a certain time period does not exceed a certain number, the autonomous driving controller determines that there are no potholes on the road ahead of the vehicle; if the number of times the vertical undulation exceeds the first height threshold but is less than or equal to a second height threshold exceeds a certain number, the autonomous driving controller determines that there are minor potholes on the road ahead; if the number of times the vertical undulation exceeds the second height threshold exceeds a certain number, the autonomous driving controller determines that there are severe potholes on the road ahead. An adjustment module is used to adjust the vertical control of the vehicle in response to whether the pothole is of the degree of minor pothole or the degree of severe pothole.

7. The apparatus according to claim 6, characterized in that, The calculation module is used to calculate the vertical jump based on the instantaneous angle and vertical distance between the edge line and a preset line on the road surface where the vehicle is located, wherein the preset line is located at a fixed position in the video image; and / or to calculate the vertical jump based on the height change of the edge line.

8. A computer program product comprising computer instructions that, when executed by a processor, implement the steps of the vehicle driving control method as described in any one of claims 1 to 5.

9. A non-transitory computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which is loaded and executed by a processor to implement the vehicle driving control method as described in any one of claims 1 to 5.

Images