Vehicle control method and device, computer device and storage medium

Abstract

The application relates to a vehicle control method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a current image frame in a video stream collected by an image collection device; acquiring a wading parameter based on the current image frame, the wading parameter comprising at least one of a wading area, a water surface turbidity degree and an image change rate of the current image frame relative to a previous image frame; performing wading risk judgment according to the wading parameter to determine a wading risk category; in the case that the wading risk category is a wading risk, detecting a water level depth through a radar; determining a difference between the water level depth and a preset minimum safe water inlet height, and determining a wading passing category based on the difference; in the case that the wading passing category is to raise the vehicle body, raising the vehicle body through an air suspension according to the difference. The method can improve the safety of vehicle control.

Description

Technical Field

[0001] This application relates to the field of automotive auxiliary systems technology, and in particular to a vehicle control method, device, computer equipment, storage medium, and computer program product. Background Technology

[0002] When driving, vehicles inevitably pass through waterlogged sections. If the water is too deep, it can easily cause the vehicle to stall, or even cause water to enter the engine, damage the engine, prevent the doors from opening, or cause the battery to lose power, threatening the personal safety of the driver and passengers as well as the driving safety of the vehicle itself.

[0003] Existing vehicle control methods often involve issuing a water wading warning when water is detected on the road surface. However, drivers still need to subjectively assess the risk of wading, which results in low vehicle control safety. Summary of the Invention

[0004] Therefore, it is necessary to provide a vehicle control method, device, computer equipment, computer-readable storage medium, and computer program product that can improve vehicle control safety, in order to address the aforementioned problem of low vehicle control safety.

[0005] Firstly, this application provides a vehicle control method. The method includes:

[0006] Acquire the current image frame from the video stream captured by the image acquisition device;

[0007] Based on the current image frame, water wading parameters are obtained, including at least one of the following: water wading area, water turbidity, and the rate of change of the current image frame relative to the previous image frame.

[0008] Based on water-related parameters, assess water-related risks and determine the category of water-related risk.

[0009] When the water risk category is "risk of water wading", water level depth is detected by radar.

[0010] Determine the difference between the water level depth and the preset minimum safe water inlet height, and determine the water crossing category based on the difference;

[0011] When wading through water that requires raising the vehicle body, the air suspension controls the vehicle body to be raised based on the difference in elevation.

[0012] In one embodiment, based on the current image frame, wading parameters are obtained, including:

[0013] Preprocess the current image frame to obtain the preprocessed image;

[0014] The preprocessed image is segmented using a convolutional neural network model to obtain wading images;

[0015] Water wading parameters are obtained based on wading images.

[0016] In one embodiment, preprocessing the current image frame to obtain a preprocessed image includes:

[0017] Determine the type of the current image frame, which may be a fisheye image or a planar image;

[0018] If the current image frame is a fisheye image, then based on the current image frame, a corrected image is obtained through distortion correction and perspective transformation; the corrected image is then enhanced to obtain a preprocessed image.

[0019] If the current image frame is a planar image, then image enhancement is performed on the current image frame to obtain a preprocessed image.

[0020] In one embodiment, water risk assessment is performed based on water-related parameters to determine the water risk category, including:

[0021] The water area in the water-wading image is compared with a preset area threshold to obtain the first comparison result;

[0022] The degree of turbidity on the water surface is compared with a preset threshold to obtain a second comparison result;

[0023] The image change rate is compared with a preset change threshold to obtain a third comparison result;

[0024] If the first comparison result, the second comparison result, and the third comparison result all meet the corresponding conditions, then the water risk category is determined to be no water risk.

[0025] If any of the first, second, or third comparison results does not meet the corresponding conditions, the water risk category is determined to be water-related risk.

[0026] In one embodiment, detecting water level depth via radar includes:

[0027] The phase interval between the radar's transmitted and reflected waves is obtained, and the detection range is determined based on the phase interval.

[0028] The water level depth is determined based on the detection range and the radar's installation angle.

[0029] In one embodiment, determining the wading passage category based on the difference includes:

[0030] If the difference is within the preset warning range, then the water crossing category is determined to be one that requires raising the vehicle body;

[0031] If the difference is greater than the maximum value of the preset warning range, the water crossing category is determined to be normal water crossing.

[0032] If the difference is less than the minimum value of the preset warning range, the water passage category is determined to be "unable to pass through water".

[0033] Secondly, this application also provides a vehicle control device. The device includes:

[0034] The image acquisition module is used to acquire the current image frame in the video stream captured by the image acquisition device;

[0035] The parameter acquisition module is used to acquire water wading parameters based on the current image frame. The water wading parameters include at least one of the following: water wading area, water turbidity, and the rate of change of the current image frame relative to the previous image frame.

[0036] The first determination module is used to assess water-related risks based on water-related parameters and determine the category of water-related risks.

[0037] The detection module is used to detect water level depth using radar when the water risk category is "water risk".

[0038] The second determining module is used to determine the difference between the water level depth and the preset minimum safe water inlet height, and to determine the water crossing category based on the difference;

[0039] The control module is used to raise the vehicle body via air suspension based on the difference in elevation when the wading category requires raising the vehicle body.

[0040] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0041] Acquire the current image frame from the video stream captured by the image acquisition device;

[0042] Based on the current image frame, water wading parameters are obtained, including at least one of the following: water wading area, water turbidity, and the rate of change of the current image frame relative to the previous image frame.

[0043] Based on water-related parameters, assess water-related risks and determine the category of water-related risk.

[0044] When the water risk category is "risk of water wading", water level depth is detected by radar.

[0045] Determine the difference between the water level depth and the preset minimum safe water inlet height, and determine the water crossing category based on the difference;

[0046] When wading through water that requires raising the vehicle body, the air suspension controls the vehicle body to be raised based on the difference in elevation.

[0047] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0048] Acquire the current image frame from the video stream captured by the image acquisition device;

[0049] Based on the current image frame, water wading parameters are obtained, including at least one of the following: water wading area, water turbidity, and the rate of change of the current image frame relative to the previous image frame.

[0050] Based on water-related parameters, assess water-related risks and determine the category of water-related risk.

[0051] When the water risk category is "risk of water wading", water level depth is detected by radar.

[0052] Determine the difference between the water level depth and the preset minimum safe water inlet height, and determine the water crossing category based on the difference;

[0053] When wading through water that requires raising the vehicle body, the air suspension controls the vehicle body to be raised based on the difference in elevation.

[0054] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0055] Acquire the current image frame from the video stream captured by the image acquisition device;

[0056] Based on the current image frame, water wading parameters are obtained, including at least one of the following: water wading area, water turbidity, and the rate of change of the current image frame relative to the previous image frame.

[0057] Based on water-related parameters, assess water-related risks and determine the category of water-related risk.

[0058] When the water risk category is "risk of water wading", water level depth is detected by radar.

[0059] Determine the difference between the water level depth and the preset minimum safe water inlet height, and determine the water crossing category based on the difference;

[0060] When wading through water that requires raising the vehicle body, the air suspension controls the vehicle body to be raised based on the difference in elevation.

[0061] The aforementioned vehicle control method, device, computer equipment, storage medium, and computer program products can determine the wading risk category by using wading parameters in the current image frame of the video stream acquired by the image acquisition device. If the wading risk category is wading risk, the water depth detected by radar can determine the wading passage category. This method, which first determines the wading risk through images and then determines the wading passage category through radar detection, can accurately judge the actual wading situation. Furthermore, if the wading passage category requires raising the vehicle body, the air suspension controls the vehicle body to raise the corresponding height for different wading depths to allow the vehicle to pass through the wading section, improving the safety of vehicle control. Attached Figure Description

[0062] Figure 1 This is a diagram illustrating the application environment of a vehicle control method in one embodiment.

[0063] Figure 2 This is a flowchart illustrating a vehicle control method in one embodiment;

[0064] Figure 3 This is a schematic diagram of a sub-process of S202 in one embodiment;

[0065] Figure 4 This is a schematic diagram of a sub-process of S301 in one embodiment;

[0066] Figure 5 This is a schematic diagram of the composition structure of a vehicle control system in one embodiment;

[0067] Figure 6 This is a structural block diagram of a vehicle control device in one embodiment;

[0068] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0069] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0070] The vehicle control method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, terminal 102 communicates with vehicle 104 via a network. Terminal 102 acquires the current image frame from the video stream captured by the image acquisition device; based on the current image frame, it acquires wading parameters, including at least one of the following: wading area, water turbidity, and the rate of change of the current image frame relative to the previous image frame; it assesses wading risk based on the wading parameters and determines the wading risk category; if the wading risk category is wading risk, it detects the water level depth using radar; it determines the difference between the water level depth and a preset minimum safe water ingress height, and based on the difference, determines the wading passage category; if the wading passage category requires raising the vehicle body, it controls the vehicle body to be raised using air suspension based on the difference. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc.

[0071] In one embodiment, such as Figure 2 As shown, a vehicle control method is provided, which is applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps:

[0072] S201, Obtain the current image frame from the video stream acquired by the image acquisition device.

[0073] The image acquisition device is used to capture video streams of road conditions while the vehicle is in motion. The video stream includes at least one image frame. The current image frame is a frame from the video stream captured by the image acquisition device at the current moment. The image acquisition device is mounted on the vehicle. Optionally, the image acquisition device can be mounted in front of the vehicle or on either side of the vehicle. For example, the image acquisition device can be a fisheye camera or a non-fisheye camera.

[0074] Specifically, the terminal acquires the current image frame from the video stream captured by the image acquisition device.

[0075] S202, based on the current image frame, obtain water wading parameters, including at least one of the following: water wading area, water turbidity, and the rate of change of the current image frame relative to the previous image frame.

[0076] The wading parameters are parameters related to wading in the current image frame. The terminal performs image processing on the current image frame to obtain the wading parameters. Optionally, the wading parameters include at least one of the following: wading area, water turbidity, and the rate of change of the current image frame relative to the previous image frame.

[0077] Specifically, the terminal extracts features from the current frame image, identifies wading edges in the image, and obtains the wading area in the current frame image based on the wading edges. The terminal performs color recognition on the current image frame, obtains the color parameters in the current frame image, and obtains the water turbidity level corresponding to the current image frame based on the mapping relationship between the water surface color parameters and the water turbidity level. The terminal uses the MOT (Multiple Object Tracking) algorithm to calculate the rate of change of the current image frame relative to the previous image frame.

[0078] S203, assess water-related risks based on water-related parameters and determine the water-related risk category.

[0079] Among these methods, water wading risk assessment involves determining the water wading risk category by analyzing water wading parameters. For example, water wading risk categories include no water wading risk, water wading risk, and uncertain water wading risk. This method, which determines the water wading risk category based on water wading parameters obtained from the current image frame, can provide a preliminary assessment of whether a vehicle faces water wading risk, thus improving vehicle safety when traversing flooded road sections.

[0080] S204, in cases where the water risk category is "water risk present", uses radar to detect water level depth.

[0081] Water level depth refers to the water level depth based on the current image frame. Water level depth can be detected using radar emitting radar pulses. For example, the radar can be installed on a vehicle. The radar type can be either ultrasonic radar or millimeter-wave radar. Optionally, when the wading risk category is "there is a wading risk" or "the wading risk is uncertain," the terminal detects the water level depth using radar.

[0082] S205, determine the difference between the water level depth and the preset minimum safe water inlet height, and determine the water crossing category based on the difference.

[0083] The minimum safe water ingress height is the safe depth at which a vehicle can wade through water. The terminal presets the minimum safe water ingress height for different vehicles. The terminal calculates the difference between the water level depth and the preset minimum safe water ingress height.

[0084] The wading passage category characterizes how safely a vehicle can pass through a flooded section of road. Optionally, the wading passage category includes normal wading passage, inability to wade through water, and the need to raise the vehicle body. The terminal determines the corresponding wading passage category based on the difference between the water level depth and a preset minimum safe water ingress height. This ability to further assess the wading risk of vehicles passing through flooded sections helps improve vehicle safety when navigating such sections.

[0085] S206, when the water crossing category requires raising the vehicle body, controls the vehicle body height by using air suspension based on the difference.

[0086] Air suspension is a vehicle device that can lower or raise the vehicle chassis to control the vehicle's height. When wading through water that requires raising the vehicle body, the system uses air suspension to raise the vehicle to a height greater than or equal to the difference between the water depth and a preset minimum safe water ingress height. This ensures the vehicle can safely pass through water-covered sections and improves vehicle control safety.

[0087] In the aforementioned vehicle control method, the wading risk category can be determined by the wading parameters in the current image frame of the video stream acquired by the image acquisition device. If the wading risk category is "there is a risk of wading," the water depth detected by radar can determine the wading passage category. This method, which first determines the wading risk through images and then determines the wading passage category through radar detection, can accurately judge the actual wading situation. Furthermore, if the wading passage category requires raising the vehicle body, the air suspension controls the vehicle body to raise the corresponding height for different wading depths, thus improving the safety of vehicle control.

[0088] In one embodiment, such as Figure 3 As shown, based on the current image frame, the wading parameters are obtained, including:

[0089] S301, preprocess the current image frame to obtain the preprocessed image.

[0090] Preprocessing refers to the method of processing the current image frame using image processing algorithms. The terminal preprocesses the current image frame to obtain a preprocessed image. Preprocessing may include distortion correction, perspective adjustment, and image enhancement.

[0091] S302 uses a convolutional neural network model to segment the preprocessed image to obtain a wading image.

[0092] The preprocessed image includes both wading areas and non-wading areas. Segmentation refers to dividing the preprocessed image into wading images with wading areas and non-wading images without wading areas. The convolutional neural network model can be a common image segmentation convolutional neural network. Optionally, the convolutional neural network can be UNET (Unity Networking) or PSPNet (Pyramid Scene Parsing Network). Since the number of wading images acquired by the image acquisition device is limited, using UNET or PSPNet for pixel-level binary classification of the wading images can accurately segment the preprocessed image into wading images. Specifically, the terminal inputs the preprocessed image into the convolutional neural network model for image segmentation to obtain wading images and non-wading images. The training method of the convolutional neural network model includes: inputting wading image samples and wading labels into an initial convolutional neural network model for training, and adjusting the initial neural network model through a loss function to obtain the trained convolutional neural network model. Wading labels refer to the wading area features in the wading sample images.

[0093] S303, based on wading images, acquires wading parameters.

[0094] The terminal processes the wading image to obtain wading parameters. Compared to directly processing the current image frame to obtain wading parameters, this avoids interfering pixels, improves the efficiency of obtaining wading parameters, and helps improve the safety of vehicle control.

[0095] In this embodiment, by preprocessing the current image frame and obtaining the wading image based on the segmentation of the preprocessed image using a convolutional neural network model, wading parameters are obtained. Compared to directly processing the current image frame to obtain wading parameters, this avoids interfering pixels, improves the efficiency of obtaining wading parameters, and is beneficial to improving the safety of vehicle control.

[0096] In one embodiment, such as Figure 4 As shown, the current image frame is preprocessed to obtain a preprocessed image, including:

[0097] S401, determine the type of the current image frame. The type of the current image frame includes either a fisheye image or a planar image.

[0098] Fisheye images offer a wider field of view compared to planar images. In vehicle control, fisheye images are often used to cover the road segment traversed in the direction of travel. A fisheye image is captured using a fisheye camera. A planar image is captured by a non-fisheye camera. The terminal can determine whether the current image frame is a fisheye image or a planar image based on the type of image acquisition device corresponding to that frame.

[0099] S402, if the current image frame is a fisheye image, then based on the current image frame, obtain the corrected image through distortion correction and perspective transformation; perform image enhancement on the corrected image to obtain the preprocessed image.

[0100] Distortion correction is the process of projecting distorted pixels in a fisheye image onto the corrected pixel positions. Perspective transformation is a method of projecting an image onto a new viewpoint or plane. When the current image frame is a fisheye image, the terminal performs distortion correction on the current image frame to obtain a first corrected image. Then, it performs perspective transformation on the first corrected image to obtain a corrected image, which is a planar image.

[0101] Image enhancement is a method that uses at least one image processing technique to process degraded image features, such as edges, contours, and contrast, to improve the visual effect of the image, increase its clarity, highlight features of interest, and weaken features of non-interest. The terminal performs image enhancement on the corrected image to obtain the enhanced image; the preprocessed image is the enhanced image.

[0102] S403, if the current image frame is a planar image, then perform image enhancement on the current image frame to obtain a preprocessed image.

[0103] In the case where the current image frame is a planar image, the terminal directly performs image enhancement on the current image frame, and the enhanced image is the preprocessed image.

[0104] In this embodiment, by determining the type of the current image frame, distortion correction and perspective transformation are performed on the fisheye image to convert it into a planar image. Then, image enhancement is applied to the planar image, simplifying image processing and improving the effectiveness of image preprocessing. For planar images, image enhancement can be performed directly, which helps improve the efficiency of image preprocessing. Image segmentation based on the preprocessed image will help obtain accurate wading images, improving the safety of vehicle control.

[0105] In one embodiment, determining the water risk category based on water-related parameters includes: comparing the water-related area of ​​the water-related image with a preset area threshold to obtain a first comparison result; comparing the turbidity of the water surface with a preset degree threshold to obtain a second comparison result; comparing the image change rate with a preset change threshold to obtain a third comparison result; when the first comparison result, the second comparison result, and the third comparison result all meet the corresponding conditions, the water risk category is determined to be no water risk; when any one of the first comparison result, the second comparison result, and the third comparison result does not meet the corresponding condition, the water risk category is determined to be water risky.

[0106] The terminal assesses each water-related parameter in the water-related image separately. Specifically, it compares the water-related area with a preset area threshold to obtain a first comparison result. The first comparison result indicates whether the water-related area exceeds the preset area threshold. The terminal compares the water turbidity with a preset turbidity threshold to obtain a second comparison result. The second comparison result indicates whether the water turbidity exceeds the preset turbidity threshold. The terminal compares the image change rate with a preset change threshold to obtain a third comparison result. The third comparison result indicates whether the image change rate exceeds the preset change threshold. If the first, second, and third comparison results indicate that none of the water-related parameters exceed their corresponding thresholds, the terminal determines the water-related risk category as "no water-related risk." If the first, second, and third comparison results indicate that any one of the water-related parameters exceeds its corresponding threshold, the terminal determines the water-related risk category as "water-related risk."

[0107] In this embodiment, the water wading risk category is determined by comparing each water wading parameter with the corresponding threshold. The obtained water wading risk category can make a preliminary judgment on water wading risk based on the image, which is beneficial to improving the safety of vehicle control when the vehicle is wading through water.

[0108] In one embodiment, detecting water level depth by radar includes: acquiring the time interval between the radar's transmitted and reflected waves, determining the detection distance based on the time interval, and determining the water level depth based on the detection distance and the radar's installation angle.

[0109] One method for detecting water level depth using radar is by calculating the time interval between the radar's transmitted and reflected waves. The terminal calculates the detection range by combining the time interval between the transmitted and reflected waves with their propagation speeds. The radar's installation height is then obtained, and the water level depth is determined based on the detection range and the radar's installation angle. In some embodiments, the formula for calculating water level depth is: Where h represents the water level depth, H represents the radar installation height, and S represents the detection range. This indicates the installation angle of the radar.

[0110] In this embodiment, the detection range is determined by acquiring the time interval between the radar's transmitted and reflected waves. Then, based on the detection range, the radar's installation angle, and the formula for calculating water level depth, the water level depth is determined. This allows for accurate water level depth detection via radar, and vehicle control based on the detected water level depth improves vehicle control safety.

[0111] In one embodiment, determining the wading passage category based on the difference includes: if the difference is within a preset warning range, the wading passage category is determined to be one where the vehicle body needs to be raised; if the difference is greater than the maximum value of the preset warning range, the wading passage category is determined to be one where normal wading passage is possible; if the difference is less than the minimum value of the preset warning range, the wading passage category is determined to be one where wading passage is impossible.

[0112] The terminal determines the wading category by comparing the difference between the water level depth and the preset minimum safe water inlet height with a preset warning range. If the difference is within the preset warning range, the wading category is determined to require raising the vehicle body; if the difference is greater than the maximum value of the preset warning range, the wading category is determined to be normal wading; if the difference is less than the minimum value of the preset warning range, the wading category is determined to be wading impossible.

[0113] In this embodiment, the water crossing category is determined by judging the relationship between the difference between the water level depth and the preset minimum safe water ingress height and the preset warning range. This helps to improve the accuracy of water crossing category judgment and improve vehicle control safety.

[0114] To illustrate the vehicle control method and its effects in this solution in detail, a specific embodiment is described below:

[0115] For commercial vehicles used in water-related applications, the vehicle control system includes a signal acquisition unit, a vehicle status control unit, and an information interaction unit. For example... Figure 5The diagram illustrates the structural composition of a vehicle control system. The signal acquisition unit includes an image acquisition device, an image processing unit, and radar. The vehicle status control unit includes an air suspension axle height sensor and a body controller. The information interaction unit includes a combination instrument cluster, an in-vehicle terminal, and a TBOX (Telematics Box, intelligent in-vehicle terminal). For example, the image acquisition device in the signal acquisition unit has a horizontal viewing angle of 140 degrees and a vertical viewing angle of 110 degrees, positioned below the vehicle emblem at the front of the vehicle, to acquire real-time video streams of road conditions within its downward field of view. The signal acquisition unit transmits signals to the image processing unit via a coaxial cable. The terminal sends the wading risk category and wading passage category to the in-vehicle terminal via a CAN (Controller Area Network) bus. The in-vehicle terminal displays the wading risk category and wading passage category, provides corresponding warnings, and switches to the forward image acquisition device to acquire real-time images for the driver to observe and assess road conditions. The vehicle status control unit receives the water level depth transmitted by the radar, compares it with a preset minimum safe water ingress height, and controls the solenoid valve to inflate the airbags in the air suspension to raise the vehicle height based on the difference. The body control unit automatically unlocks the doors to prevent the driver from being trapped inside, improving vehicle control safety. The signal interaction unit receives water wading risk and water passage categories from the CAN bus and issues corresponding alarms. The TBOX alerts the driver of the risks via SMS.

[0116] The terminal acquires the current image frame from the video stream captured by the image acquisition device. It determines the type of the current image frame, which can be either a fisheye image or a planar image. If the current image frame is a fisheye image, it obtains a corrected image through distortion correction and perspective transformation based on the current image frame. Image enhancement is then performed on the corrected image to obtain a preprocessed image.

[0117] If the current image frame is a planar image, then image enhancement is performed on the current image frame to obtain a preprocessed image.

[0118] The preprocessed image is segmented using a convolutional neural network model to obtain a wading image. Based on the wading image, wading parameters are obtained, including at least one of the following: wading area, water turbidity, and the rate of change of the current image frame relative to the previous image frame.

[0119] Water risk is assessed based on water-related parameters to determine the water risk category. Specifically, this includes: comparing the water-related area of ​​the water-related image with a preset area threshold to obtain a first comparison result; comparing the water turbidity level with a preset turbidity threshold to obtain a second comparison result; comparing the image change rate with a preset change threshold to obtain a third comparison result; if all three comparison results meet the corresponding conditions, the water risk category is determined to be no water risk; if any one of these results does not meet the corresponding condition, the water risk category is determined to be water risky.

[0120] When the water wading risk category is "water wading risk," water level depth is detected using radar. Specifically, this involves: obtaining the time interval between the radar's transmitted and reflected waves; determining the detection distance based on this time interval; and determining the water level depth based on the detection distance and the radar's installation angle. The formula for calculating water level depth is: Where h represents the water level depth, H represents the radar installation height, and S represents the detection range. This indicates the installation angle of the radar.

[0121] The system determines the difference between the water level depth and the preset minimum safe water ingress height, and based on this difference, determines the wading passage category. Specifically, if the difference is within the preset warning range, the wading passage category is determined to be one where the vehicle body needs to be raised; if the difference is greater than the maximum value of the preset warning range, the wading passage category is determined to be normal wading passage; if the difference is less than the minimum value of the preset warning range, the wading passage category is determined to be one where wading is not possible.

[0122] When wading through water that requires raising the vehicle body, the air suspension controls the vehicle body to be raised based on the difference in elevation.

[0123] The aforementioned vehicle control method determines the wading risk category by using wading parameters in the current image frame of the video stream acquired by the image acquisition device. If the wading risk category is 'risk of wading,' the water depth detected by radar determines the wading passage category. This method, which first determines the wading risk through images and then uses radar detection to determine the wading passage category, accurately assesses the actual wading situation. Furthermore, when the wading passage category requires raising the vehicle body, the air suspension controls the vehicle body to raise the corresponding height based on different wading depths, thus improving vehicle control safety.

[0124] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0125] Based on the same inventive concept, this application also provides a vehicle control device for implementing the above-mentioned vehicle control method. The solution provided by this device is similar to the solution described in the above-described method; therefore, the specific limitations of one or more vehicle control method device embodiments provided below can be found in the limitations of the vehicle control method described above, and will not be repeated here.

[0126] In one embodiment, such as Figure 6 As shown, a vehicle control method apparatus 100 is provided, including: an image acquisition module 110, a parameter acquisition module 120, a first determination module 130, a detection module 140, a second determination module 150, and a control module 160, wherein:

[0127] The image acquisition module 110 is used to acquire the current image frame in the video stream acquired by the image acquisition device.

[0128] The parameter acquisition module 120 is used to acquire water wading parameters based on the current image frame. The water wading parameters include at least one of the following: water wading area, water turbidity, and the rate of change of the current image frame relative to the previous image frame.

[0129] The first determining module 130 is used to assess water-related risks based on water-related parameters and determine the category of water-related risks.

[0130] The detection module 140 is used to detect water level depth by radar when the water risk category is "water risk".

[0131] The second determining module 150 is used to determine the difference between the water level depth and the preset minimum safe water inlet height, and to determine the water crossing category based on the difference.

[0132] The control module 160 is used to control the vehicle body to rise via air suspension based on the difference when the water crossing category requires raising the vehicle body.

[0133] The aforementioned vehicle control device can determine the wading risk category by using wading parameters in the current image frame of the video stream acquired by the image acquisition device. If the wading risk category is 'risk of wading,' the water depth detected by radar can determine the wading passage category. This method of first determining the wading risk through images and then determining the wading passage category through radar detection can accurately assess the actual wading situation. Furthermore, if the wading passage category requires raising the vehicle body, the air suspension controls the vehicle body to raise the corresponding height based on different wading depths to facilitate passage through the wading section, thus improving vehicle control safety.

[0134] In one embodiment, in obtaining wading parameters based on the current image frame, the parameter acquisition module 120 is further configured to: preprocess the current image frame to obtain a preprocessed image; segment the preprocessed image using a convolutional neural network model to obtain a wading image; and obtain wading parameters based on the wading image.

[0135] In one embodiment, in preprocessing the current image frame to obtain a preprocessed image, the parameter acquisition module 120 is further configured to: determine the type of the current image frame, wherein the type of the current image frame includes a fisheye image or a planar image; if the type of the current image frame is a fisheye image, then obtain a corrected image based on the current image frame through distortion correction and perspective transformation; perform image enhancement on the corrected image to obtain a preprocessed image; if the type of the current image frame is a planar image, then perform image enhancement on the current image frame to obtain a preprocessed image.

[0136] In one embodiment, in determining the water risk category based on water-related parameters, the first determining module 130 is further configured to: compare the water-related area of ​​the water-related image with a preset area threshold to obtain a first comparison result; compare the turbidity of the water surface with a preset degree threshold to obtain a second comparison result; compare the image change rate with a preset change threshold to obtain a third comparison result; when the first comparison result, the second comparison result, and the third comparison result all meet the corresponding conditions, the water risk category is determined to be no water risk; when any of the first comparison result, the second comparison result, and the third comparison result does not meet the corresponding conditions, the water risk category is determined to be water risky.

[0137] In one embodiment, in detecting water level depth by radar, the detection module 140 is further configured to: obtain the time interval between the radar's transmitted wave and reflected wave, determine the detection distance based on the time interval, and determine the water level depth based on the detection distance and the radar's installation angle.

[0138] In one embodiment, in determining the wading passage category based on the difference, the second determining module 150 is further configured to: if the difference is within a preset warning range, determine the wading passage category as requiring the vehicle body to be raised; if the difference is greater than the maximum value of the preset warning range, determine the wading passage category as normal wading passage; if the difference is less than the minimum value of the preset warning range, determine the wading passage category as unable to wade through water.

[0139] Each module in the aforementioned vehicle control method device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0140] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a vehicle control method.

[0141] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0142] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0143] The system acquires the current image frame from the video stream captured by the image acquisition device; based on the current image frame, it acquires wading parameters, including at least one of the following: wading area, water turbidity, and the rate of change of the current image frame relative to the previous image frame; it assesses wading risk based on the wading parameters and determines the wading risk category; if the wading risk category is wading risk, it detects the water level depth using radar; it determines the difference between the water level depth and the preset minimum safe water ingress height, and based on the difference, it determines the wading passage category; if the wading passage category requires raising the vehicle body, it controls the vehicle body to be raised using air suspension based on the difference.

[0144] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0145] The current image frame is preprocessed to obtain a preprocessed image; the preprocessed image is segmented using a convolutional neural network model to obtain a wading image; and wading parameters are obtained based on the wading image.

[0146] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0147] Determine the type of the current image frame, which may be a fisheye image or a planar image. If the current image frame is a fisheye image, obtain the corrected image by performing distortion correction and perspective transformation based on the current image frame. Then, perform image enhancement on the corrected image to obtain the preprocessed image. If the current image frame is a planar image, perform image enhancement on the current image frame to obtain the preprocessed image.

[0148] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0149] The water area in the water-related image is compared with a preset area threshold to obtain a first comparison result; the turbidity of the water surface is compared with a preset turbidity threshold to obtain a second comparison result; the image change rate is compared with a preset change threshold to obtain a third comparison result; if the first, second, and third comparison results all meet the corresponding conditions, the water-related risk category is determined to be no water-related risk; if any of the first, second, and third comparison results does not meet the corresponding conditions, the water-related risk category is determined to be water-related risk.

[0150] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0151] The time interval between the radar's transmitted and reflected waves is obtained, and the detection range is determined based on the time interval; the water level depth is determined based on the detection range and the radar's installation angle.

[0152] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0153] If the difference is within the preset warning range, the water crossing category is determined to be "requiring the vehicle body to be raised"; if the difference is greater than the maximum value of the preset warning range, the water crossing category is determined to be "normal water crossing"; if the difference is less than the minimum value of the preset warning range, the water crossing category is determined to be "unable to cross".

[0154] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0155] The system acquires the current image frame from the video stream captured by the image acquisition device; based on the current image frame, it acquires wading parameters, including at least one of the following: wading area, water turbidity, and the rate of change of the current image frame relative to the previous image frame; it assesses wading risk based on the wading parameters and determines the wading risk category; if the wading risk category is wading risk, it detects the water level depth using radar; it determines the difference between the water level depth and the preset minimum safe water ingress height, and based on the difference, it determines the wading passage category; if the wading passage category requires raising the vehicle body, it controls the vehicle body to be raised using air suspension based on the difference.

[0156] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0157] The current image frame is preprocessed to obtain a preprocessed image; the preprocessed image is segmented using a convolutional neural network model to obtain a wading image; and wading parameters are obtained based on the wading image.

[0158] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0159] Determine the type of the current image frame, which may be a fisheye image or a planar image. If the current image frame is a fisheye image, obtain the corrected image by performing distortion correction and perspective transformation based on the current image frame. Then, perform image enhancement on the corrected image to obtain the preprocessed image. If the current image frame is a planar image, perform image enhancement on the current image frame to obtain the preprocessed image.

[0160] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0161] The water area in the water-related image is compared with a preset area threshold to obtain a first comparison result; the turbidity of the water surface is compared with a preset turbidity threshold to obtain a second comparison result; the image change rate is compared with a preset change threshold to obtain a third comparison result; if the first, second, and third comparison results all meet the corresponding conditions, the water-related risk category is determined to be no water-related risk; if any of the first, second, and third comparison results does not meet the corresponding conditions, the water-related risk category is determined to be water-related risk.

[0162] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0163] The time interval between the radar's transmitted and reflected waves is obtained, and the detection range is determined based on the time interval; the water level depth is determined based on the detection range and the radar's installation angle.

[0164] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0165] If the difference is within the preset warning range, the water crossing category is determined to be "requiring the vehicle body to be raised"; if the difference is greater than the maximum value of the preset warning range, the water crossing category is determined to be "normal water crossing"; if the difference is less than the minimum value of the preset warning range, the water crossing category is determined to be "unable to cross".

[0166] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0167] The system acquires the current image frame from the video stream captured by the image acquisition device; based on the current image frame, it acquires wading parameters, including at least one of the following: wading area, water turbidity, and the rate of change of the current image frame relative to the previous image frame; it assesses wading risk based on the wading parameters and determines the wading risk category; if the wading risk category is wading risk, it detects the water level depth using radar; it determines the difference between the water level depth and the preset minimum safe water ingress height, and based on the difference, it determines the wading passage category; if the wading passage category requires raising the vehicle body, it controls the vehicle body to be raised using air suspension based on the difference.

[0168] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0169] The current image frame is preprocessed to obtain a preprocessed image; the preprocessed image is segmented using a convolutional neural network model to obtain a wading image; and wading parameters are obtained based on the wading image.

[0170] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0171] Determine the type of the current image frame, which may be a fisheye image or a planar image. If the current image frame is a fisheye image, obtain the corrected image by performing distortion correction and perspective transformation based on the current image frame. Then, perform image enhancement on the corrected image to obtain the preprocessed image. If the current image frame is a planar image, perform image enhancement on the current image frame to obtain the preprocessed image.

[0172] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0173] The water area in the water-related image is compared with a preset area threshold to obtain a first comparison result; the turbidity of the water surface is compared with a preset turbidity threshold to obtain a second comparison result; the image change rate is compared with a preset change threshold to obtain a third comparison result; if the first, second, and third comparison results all meet the corresponding conditions, the water-related risk category is determined to be no water-related risk; if any of the first, second, and third comparison results does not meet the corresponding conditions, the water-related risk category is determined to be water-related risk.

[0174] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0175] The time interval between the radar's transmitted and reflected waves is obtained, and the detection range is determined based on the time interval; the water level depth is determined based on the detection range and the radar's installation angle.

[0176] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0177] If the difference is within the preset warning range, the water crossing category is determined to be "requiring the vehicle body to be raised"; if the difference is greater than the maximum value of the preset warning range, the water crossing category is determined to be "normal water crossing"; if the difference is less than the minimum value of the preset warning range, the water crossing category is determined to be "unable to cross".

[0178] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0179] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0180] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0181] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A vehicle control method characterized by, The method comprises: acquiring a current image frame in a video stream collected by an image collection device; based on the current image frame, acquiring a wading parameter, the wading parameter comprising at least one of a wading area, a water surface turbidity degree, and an image change rate of the current image frame relative to a previous image frame; judging a wading risk according to the wading parameter, and determining a wading risk category; in a case where the wading risk category is a wading risk, detecting a water level depth by a radar; determining a difference between the water level depth and a preset minimum safe water entry height, and determining a wading passing category based on the difference; in a case where the wading passing category is a need to raise the vehicle body, raising the vehicle body by an air suspension according to the difference; the judging of the wading risk according to the wading parameter and the determining of the wading risk category comprise: comparing the wading area of a wading image with a preset area threshold to obtain a first comparison result; comparing the water surface turbidity degree with a preset degree threshold to obtain a second comparison result; comparing the image change rate with a preset change threshold to obtain a third comparison result; in a case where the first comparison result, the second comparison result, and the third comparison result all satisfy corresponding conditions, determining that the wading risk category is no wading risk; in a case where any one of the first comparison result, the second comparison result, and the third comparison result does not satisfy the corresponding condition, determining that the wading risk category is a wading risk.

2. The method of claim 1, wherein, the acquiring of the wading parameter based on the current image frame comprises: preprocessing the current image frame to obtain a preprocessed image; segmenting the preprocessed image by a convolutional neural network model to obtain a wading image; acquiring the wading parameter based on the wading image.

3. The method of claim 2, wherein, the preprocessing of the current image frame to obtain the preprocessed image comprises: judging a type of the current image frame, the type of the current image frame comprising a fisheye image or a planar image; if the type of the current image frame is the fisheye image, obtaining a corrected image by distortion correction and perspective change according to the current image frame; and performing image enhancement on the corrected image to obtain the preprocessed image; if the type of the current image frame is the planar image, performing image enhancement on the current image frame to obtain the preprocessed image.

4. The method of claim 1, wherein, the detecting of the water level depth by the radar comprises: acquiring a time interval between a transmitted wave and a reflected wave of the radar, and determining a detection distance based on the time interval; determining the water level depth according to the detection distance and an installation angle of the radar.

5. The method of claim 1, wherein, the determining of the wading passing category based on the difference comprises: if the difference is within a preset warning range, determining that the wading passing category is a need to raise the vehicle body; if the difference is greater than a maximum value of the preset warning range, determining that the wading passing category is a normal wading passing; if the difference is less than a minimum value of the preset warning range, determining that the wading passing category is an impossible wading passing.

6. A vehicle control device characterized by comprising: the device comprises: an image acquisition module, configured to acquire a current image frame in a video stream collected by an image collection device; The parameter acquisition module is configured to acquire a wading parameter based on the current image frame, the wading parameter comprising at least one of a wading area, a water surface turbidity degree, and an image change rate of the current image frame relative to a previous image frame. The first determination module is configured to determine a wading risk category according to the wading parameter. The detection module is configured to detect a water level depth by radar in a case where the wading risk category is a wading risk. The second determination module is configured to determine a difference between the water level depth and a preset minimum safe water entry height, and determine a wading passing category based on the difference. The control module is configured to control the vehicle body to be raised by an air suspension according to the difference in a case where the wading passing category is to raise the vehicle body. The first determination module is further configured to compare the wading area of the wading image with a preset area threshold to obtain a first comparison result, compare the water surface turbidity degree with a preset degree threshold to obtain a second comparison result, and compare the image change rate with a preset change threshold to obtain a third comparison result. When the first comparison result, the second comparison result, and the third comparison result all satisfy corresponding conditions, it is determined that the wading risk category is no wading risk. When any one of the first comparison result, the second comparison result, and the third comparison result does not satisfy the corresponding condition, it is determined that the wading risk category is a wading risk. 7.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-6 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the method of any one of claims 1 to 5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

9. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

Images