Tire anti-scratch early warning method and device based on cooperation of mobile terminal and vehicle

Abstract

The application provides a tire anti-scraping early warning method and device based on cooperation of a mobile terminal and a vehicle. The method acquires video data including vehicle tires and road edges in the same frame of image photographed by the mobile terminal in real time, displays the video data in a display device, and can continuously present the relative position relationship between the tires and the road edges during vehicle driving or turning. The shortest distance between the vehicle tires and the road edges is determined according to the video data, and a scraping warning message is output when the shortest distance is less than a warning threshold, so that the risk of the tires approaching the road edges can be timely identified and warned, the accuracy and real-time performance of the tire anti-scraping early warning are improved, and the possibility of tire or hub scraping is reduced.

Description

Technical Field

[0001] This application relates to the field of vehicles, and in particular to a tire anti-scratch warning method and device based on the collaboration between a mobile terminal and a vehicle. Background Technology

[0002] Current vehicle tire scratch warning systems mainly rely on onboard surround view systems or radar and other onboard sensors to detect and alert about the gap between the tire and the curb.

[0003] However, the above solutions are limited by camera installation location, image stitching, and monocular measurement conditions. The tire-curb gap is prone to being in the distortion zone or perception blind zone, resulting in insufficient distance measurement accuracy. They also rely heavily on existing vehicle hardware configurations, limiting their applicability. In addition, most solutions only provide the current static distance, making it difficult to reflect the tire movement trend during steering.

[0004] Therefore, how to improve the accuracy and dynamic prediction capability of tire-curb gap detection under limited perception conditions, while taking into account the applicability to different vehicles, has become a technical problem that needs to be solved. Summary of the Invention

[0005] This application provides a tire scratch prevention warning method and device based on mobile terminal and vehicle collaboration. This solution relies on the collaborative cooperation between the mobile terminal and the vehicle. The vehicle analyzes image information containing the tire and curb, identifies the gap between the tire and curb, and issues a timely warning when a scratch risk is imminent. This improves the accuracy of tire-curb gap detection and the ability to predict scratch risks under limited perception conditions, while reducing dependence on specific onboard hardware configurations and increasing applicability to different vehicle scenarios.

[0006] In a first aspect, this application provides a tire scratch prevention warning method based on mobile terminal and vehicle collaboration, the method comprising:

[0007] Real-time acquisition of video data captured by mobile terminals, where the same frame of the video data includes vehicle tires and roadside curbs;

[0008] Display video data on a display device;

[0009] Based on video data, determine the shortest distance between the vehicle tires and the curb;

[0010] When the shortest distance is less than the warning threshold, a scratch warning message is output.

[0011] Furthermore, based on video data, the shortest distance between the vehicle tires and the curb is determined, including:

[0012] For each frame of the image, the vehicle tires and the curb are determined using an edge detection algorithm;

[0013] Determine the shortest pixel distance between the vehicle tires and the curb;

[0014] Based on the camera intrinsic and extrinsic parameters of the mobile terminal, determine the shortest distance corresponding to the shortest pixel distance.

[0015] Furthermore, based on video data, the shortest distance between the vehicle tires and the curb is determined, including:

[0016] For each frame of the image, the vehicle wheel hub and the curb are determined using an edge detection algorithm;

[0017] Based on the actual physical diameter of the wheel hub and tire parameters, determine the current actual distance from the outermost point of the tire sidewall to the curb;

[0018] Determine the shortest distance based on the current actual distance.

[0019] Furthermore, based on the current actual distance, determine the shortest distance, including:

[0020] Determine the instantaneous turning radius of the outermost point based on the current steering wheel angle;

[0021] Based on the instantaneous turning radius, predict the lateral encroachment distance after moving to the roadside at a preset angle;

[0022] Determine the shortest distance based on the current actual distance and the lateral encroachment distance.

[0023] Furthermore, based on the actual physical diameter of the wheel hub and tire parameters, the current actual distance from the outermost point of the tire sidewall to the curb is determined, including:

[0024] Based on the contour of the vehicle's wheel hub, determine the contour imaging ellipse;

[0025] The pixel-to-physical size mapping ratio is determined based on the major axis pixels of the contour imaging ellipse and the actual physical diameter of the hub.

[0026] The outermost point of the tire sidewall is determined based on the pixel-to-physical size mapping ratio, the contour imaging ellipse, and tire parameters.

[0027] Based on the pixel-physical size mapping ratio, determine the current real distance from the outermost point to the roadside pixel.

[0028] Furthermore, tire parameters include tire cross-sectional width and aspect ratio. Based on the pixel-to-physical size mapping ratio, contour imaging ellipse, and tire parameters, the outermost point of the tire sidewall is determined, including:

[0029] Based on the contour imaging ellipse, determine the edge point of the ellipse closest to the curb along its major axis;

[0030] The offset pixel amount is determined using the following formula:

[0031] Offset pixel amount = (tire section width × aspect ratio / 100) / pixel - physical size mapping ratio;

[0032] The outermost point is determined based on the edge point and the offset pixel amount.

[0033] Furthermore, based on the instantaneous turning radius, the lateral encroachment distance after moving a preset angle towards the roadside is predicted, including:

[0034] Subtract the cosine of the preset angle from 1, and multiply it by the instantaneous turning radius to obtain the lateral encroachment distance.

[0035] Secondly, this application provides a tire anti-scratch warning device based on mobile terminal and vehicle collaboration, the device comprising:

[0036] The acquisition module is used to acquire video data captured by the mobile terminal in real time. The video data includes vehicle tires and roadside curbs in the same frame.

[0037] The display module is used to display video data on a display device;

[0038] The calculation module is used to determine the shortest distance between the vehicle tires and the curb based on video data;

[0039] The early warning module is used to output a scratch warning message when the shortest distance is less than the early warning threshold.

[0040] Thirdly, this application provides an electronic device, including: a memory and a processor;

[0041] The memory stores the instructions that the computer executes;

[0042] The processor executes computer execution instructions stored in memory, causing the processor to perform the methods described above.

[0043] Fourthly, this application provides a vehicle, including: a vehicle body, a controller, a communication module, and a display device, wherein the controller is used to execute the method provided above.

[0044] Fifthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method provided above.

[0045] Sixthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the method provided above.

[0046] This application provides a tire scratch prevention warning method and device based on mobile terminal and vehicle collaboration. By acquiring video data captured by the mobile terminal in real time, with the same frame including the vehicle tire and the curb, and displaying the video data on a display device, the relative positional relationship between the tire and the curb can be continuously presented during vehicle driving or turning. By determining the shortest distance between the vehicle tire and the curb based on the video data, and outputting a scratch warning message when the shortest distance is less than a warning threshold, the risk of the tire approaching the curb can be identified and warned in a timely manner, thereby improving the accuracy and real-time performance of tire scratch prevention warning and reducing the possibility of tire or rim scratches. Attached Figure Description

[0047] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0048] Figure 1 A scenario illustration provided for this application;

[0049] Figure 2 Flowchart of the tire anti-scratch warning method based on mobile terminal and vehicle collaboration provided in this application Figure 1 ;

[0050] Figure 3 A flowchart illustrating the tire scratch prevention warning method based on mobile terminal and vehicle collaboration provided in this application. Figure 2 ;

[0051] Figure 4 A flowchart illustrating the tire scratch prevention warning method based on mobile terminal and vehicle collaboration provided in this application. Figure 3 ;

[0052] Figure 5 A schematic diagram of a tire anti-scratch warning device based on mobile terminal and vehicle collaboration provided in this application;

[0053] Figure 6 A schematic diagram of the structure of the electronic device provided in this application.

[0054] The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0055] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0056] In vehicle driver assistance and driving safety warning technologies, tire-to-curb scraping protection is a sub-application that addresses high-frequency pain points in actual driving. It mainly targets scenarios such as parking on the side of the road, temporary parking, meeting oncoming traffic on narrow roads, entering and exiting residential gates, driving close to the curb at the corner of underground parking garage ramps, and slowly correcting the vehicle's posture along the curb.

[0057] Figure 1 A scenario illustration provided for this application, such as Figure 1 As shown, when a user parks close to the curb on the side, there is a risk of scraping between the vehicle's tires and the curb. In the above-mentioned parallel parking scenario, the driver usually needs to control the vehicle close to the curb within a limited lateral space to balance parking position, traffic efficiency, and vehicle avoidance safety. The distance between the tire sidewall, rim, and lower edge components and the curb is often very small. If the judgment is misjudged, tire scraping, rim abrasion, or even damage to the chassis edge can easily occur.

[0058] Most existing tire scratch warning solutions are based on in-vehicle surround view systems or radar perception systems. The basic idea is to use cameras placed around the vehicle to acquire images of the surrounding environment, stitch them together to form a top-down or partial view, and then have the driver visually estimate the relative position of the tires to the curb through the in-vehicle display interface. Alternatively, the system estimates the distance to nearby obstacles based on images, ultrasonic waves, millimeter-wave signals, etc., and triggers a warning. While these technologies are effective for general parking assistance, they have significant limitations when applied to the more precise task of tire edge scratch prevention. First, the fixed camera installation position means that the observation angle of the tire's lower edge, sidewall, and contact boundary with the curb is not ideal. The most critical narrow gap between the tire and the curb is often located at the boundary of adjacent camera images, making it susceptible to fisheye distortion, stitching errors, and perspective stretching. This results in local contour distortion, positional drift, or loss of detail in the displayed image, making it difficult for the driver to accurately determine the true shortest distance even if they see the image.

[0059] Furthermore, for many existing vehicles, if the original vehicle is not equipped with high-specification surround view or dedicated sensing hardware, the cost, compatibility, and implementation difficulty of subsequent upgrades are all relatively high. This demonstrates that existing technologies are insufficient in accurately determining the shortest distance between the tire and the curb under limited observation conditions, resulting in a cognitive gap between the displayed image and the actual risk. Consequently, it is difficult to provide drivers with easy-to-use, intuitive, and effective scratch warning support in complex edge-adjacent scenarios.

[0060] In view of this, this application proposes a tire scratch prevention warning method based on mobile terminal and vehicle collaboration. This method can be implemented only through the user's mobile terminal and does not require the deployment of additional hardware on the vehicle side. The user places the mobile terminal at a viewpoint that can capture images of the tire and the curb. The vehicle side simultaneously displays the acquired video data on a display device for the user to view. Based on the real-time video data captured by the mobile terminal, the shortest distance between the vehicle tire and the curb is determined. When the shortest distance is less than a warning threshold, a scratch warning message is further output.

[0061] This technical approach goes beyond the traditional fixed vehicle-mounted sensing perspective, focusing instead on real-time detection and display of the target area between the tires and the curb. This allows for more direct assistance to drivers in identifying and avoiding scratch risks in scenarios such as parking close to the curb and driving slowly on narrow roads, improving the practicality of warnings and their applicability to various vehicles.

[0062] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0063] Example 1

[0064] Figure 2 Flowchart of the tire anti-scratch warning method based on mobile terminal and vehicle collaboration provided in this application Figure 1 ,like Figure 2 As shown, it includes the following steps:

[0065] S101: Real-time acquisition of video data captured by the mobile terminal, including vehicle tires and curbs in the same frame of the video data.

[0066] The mobile terminal in this application embodiment can be a smartphone, tablet computer, portable camera device or other terminal device with image acquisition, data processing and communication capabilities. The video data can be understood as a time-series image set formed by continuous acquisition by the camera.

[0067] The user places their mobile device on the outside of the vehicle to photograph the tires, and the curb appears in the frame. In some implementations, the user's mobile device application has a scene mode selection function. The user can select the current scene mode; for example, if the user selects narrow-edge parking, the application can display curb guide lines and tire guide lines, guiding the user to simultaneously display the curb and tires in the video footage.

[0068] The same frame of the image includes the vehicle tires and the curb. The vehicle side can simultaneously identify the outer contour area of ​​the tires and the edge area of ​​the curb within the current single frame image, so that the distance between the two can be calculated subsequently based on the same coordinate reference. The curb can be an approximate curb structure formed by road curb stones, stepped edges, the side edges of parking spaces, or the lower edge of the underground parking garage wall.

[0069] In practice, the mobile terminal can be handheld by the driver, passenger, or assistant and positioned on the side of the vehicle closest to the curb. Alternatively, it can be fixed in a forward or rearward area away from the vehicle using an adsorption bracket, clamping bracket, magnetic mounting component, or temporary fixing assembly, remaining stationary with the vehicle. It can also be fixed near the rearview mirror or fender, moving with the vehicle. Preferably, the mobile terminal is configured to remain stationary with the vehicle, maintaining a fixed viewing angle. The fixed position of the mobile terminal should ensure that the camera's shooting direction is towards the gap between the tire being inspected and the adjacent curb.

[0070] In some embodiments, the mobile terminal can perform a framing guidance process before starting the acquisition, displaying the tire target frame and the curb target frame on the display interface. When the tire edge and the curb edge appear simultaneously in the camera's field of view, the terminal confirms that the current image meets the valid acquisition conditions and automatically enters the continuous acquisition state.

[0071] The vehicle continuously receives the camera's output image stream at a preset frame rate, which can be set to 15 to 60 frames per second to balance processing real-time performance and terminal power consumption. During low-speed maneuvers such as pulling over to the side of the road, parking corrections, or driving close to the curb in narrow sections, the video stream is continuously updated, allowing the system to dynamically obtain the latest images based on the tires' position relative to the curb.

[0072] In one possible embodiment, to mitigate the impact of complex lighting, shadows, rain reflections, or ground stains on recognition performance, the mobile terminal can perform image preprocessing locally after acquiring the raw video data. This preprocessing may include grayscale conversion to reduce the interference of color variations on edge detection; it may also include local contrast enhancement or dynamic histogram equalization to enhance the distinguishability of tire sidewalls, rim boundaries, and curb edges.

[0073] S102: Display video data on a display device.

[0074] The display device can be the mobile terminal's own screen, or it can be an in-vehicle central control screen, instrument display, head-up display, or a separate external monitor that communicates with the mobile terminal. Displaying video data means continuously outputting the real-time video stream captured by the camera in chronological order, allowing the driver or an observer to intuitively see the current relative position between the tires and the curb.

[0075] In some implementations, the display includes not only the presentation of the original video footage, but also the overlay of visualizations of tire edges, curb edges, distance results, and risk status, thereby forming an enhanced display interface that facilitates driving decisions.

[0076] In practice, after completing video capture, the mobile terminal can either refresh the real-time image directly on its own screen via a local display thread, or compress the video stream using an encoding module and transmit it to the vehicle's onboard unit, where it will be decoded and displayed on the central control screen. If wireless transmission is used, a low-latency video transmission protocol can be used to control end-to-end latency, ensuring that the image seen by the driver remains synchronized with the actual changes in the vehicle's position.

[0077] Display devices can use either a single-screen full-screen display or a split-screen display.

[0078] S103: Determine the shortest distance between the vehicle tires and the curb based on video data.

[0079] The shortest distance refers to the minimum physical distance between the outer surface of the tire or the outer edge envelope of the tire and the edge of the curb within the current frame.

[0080] In one specific implementation, the onboard processing unit first performs target recognition and edge extraction processing on the current video frame. For the tire area, the outer edge of the tire, the sidewall boundary, and the rim projection contour can be extracted through contour detection, semantic segmentation, instance segmentation, or feature point-based arc recognition. For the curb area, the upper edge of the curb, the vertical edge line, or the contact risk boundary can be extracted through edge operator detection, line fitting, texture segmentation, or a deep learning-based curb boundary recognition model. After completing the extraction of the two types of targets, a set of tire edge points and a set of curb edge points are constructed in the image coordinate system, and the minimum Euclidean distance between the two point sets or the minimum perpendicular distance from the tire danger boundary point to the fitted curb boundary line is calculated to obtain the pixel-level shortest spacing of the current frame.

[0081] If we represent tire edge points as set A and roadside edge points as set B, then the shortest pixel distance in the current frame can be represented as the minimum distance between any point a belonging to A and any point b belonging to B. In other words, the pair with the smallest distance from all candidate point pairs is selected as the risk proximity point. This minimum value reflects the nearest neighbor relationship in the image plane and is the basis for subsequent physical distance conversions.

[0082] Since pixel distance is not directly equivalent to actual physical distance, this application further establishes a mapping relationship between pixel scale and physical scale. In one possible embodiment, the known physical diameter of the rim or the standard specification of the tire can be used as a self-calibration reference. First, the projected ellipse of the rim or the visible diameter of the tire is identified in the image. Then, based on the ratio between the known actual size and the image pixel size, the pixel-to-millimeter conversion factor under the current shooting conditions is obtained.

[0083] Let the actual diameter of the wheel rim be D, and the corresponding pixel length identified in the image be d. Then, the scaling factor can be expressed as the ratio of D to d. Multiplying the shortest pixel distance by this scaling factor yields the corresponding physical distance. In another possible implementation, if the mobile terminal has pre-calibrated the camera, distortion correction can be performed using the intrinsic parameter matrix and distortion parameters. Combined with shooting pose estimation, a local scale model can be established to improve the accuracy of close-range measurements.

[0084] To improve stability in continuous scenes, this embodiment can also fuse distance results from multiple consecutive frames. Since mobile terminals may experience slight jitter, and the tire displacement relative to the frame continuously changes when the vehicle rolls at low speed, direct measurement of a single frame may result in instantaneous fluctuations. Therefore, sliding window averaging, exponential smoothing, Kalman filtering, or temporal consistency constraints can be introduced to smoothly update the shortest distance of the current frame. If the tire edge is occluded by a shadow in a frame, the system can use the target trajectory of adjacent frames for compensation estimation to avoid erroneous warning triggers. If the vehicle provides steering wheel angle, wheel steering angle, or vehicle speed information, the system can also predict the tire's tendency to approach the curb at the next moment based on the vehicle's motion geometry, and correct the current shortest distance accordingly. For example, when turning at low speed towards the curb, even if the current static distance is not yet below a threshold, if the turning trend indicates that it will approach further, the risk level can be increased in advance, thereby improving the foresight of the warning.

[0085] S104: When the shortest distance is less than the warning threshold, output a scratch warning message.

[0086] Scratch warning messages can be text prompts, graphic prompts, color warnings, sound reminders, voice broadcasts, vibration feedback, or a combination of the above.

[0087] If the shortest distance is less than the warning threshold, it means that the system has determined that the remaining safe clearance between the tire and the curb has entered the risk zone. At this time, it is necessary to promptly transmit the risk information to the driver or assistant through a perceptible means so as to prompt them to take evasive actions such as slowing down, straightening, stopping, or adjusting the vehicle's posture.

[0088] In practice, after obtaining the updated shortest distance each time, the system compares this distance with a preset warning threshold. The warning threshold can be set at the system's factory settings or configured based on the vehicle model, tire specifications, rim size, sidewall thickness, vehicle width, and user usage scenarios. For example, for vehicles with a large degree of rim exposure, a higher warning threshold can be set to reserve a safety margin in advance. When the comparison result shows that the shortest distance is not lower than the threshold, the system maintains normal monitoring and displays the current distance and safety indicator on the display interface. When the shortest distance is lower than the threshold, the system triggers warning logic, generates a corresponding scratch warning message, and sends it to the display device, audio module, and vibration module for execution output.

[0089] In one possible embodiment, the scratch warning message employs a tiered output mechanism. The system can set at least two thresholds, for example, a first threshold corresponding to a proximity warning and a second threshold corresponding to a high-risk warning. When the shortest distance is between the first and second thresholds, a yellow visual cue and intermittent audible alert are output; when the shortest distance is below the second threshold, a red visual cue, continuous audible alert, and stronger vibration feedback are output.

[0090] This application provides a tire scratch prevention warning method based on mobile terminal and vehicle collaboration. The method includes: acquiring video data captured by the mobile terminal in real time, where each frame of the video data includes the vehicle tire and the curb; displaying the video data on a display device; determining the shortest distance between the vehicle tire and the curb based on the video data; and outputting a scratch warning message when the shortest distance is less than a warning threshold. In this embodiment, by using the mobile terminal as a visual acquisition node close to the local scene of the tire and curb, combined with real-time display, shortest distance analysis within the same frame, and a threshold-triggered warning mechanism, the system can directly detect and alert drivers around the area with the highest actual scratch risk. This overcomes the limitations of traditional fixed vehicle-mounted perception perspectives that cannot adequately observe local gaps. Furthermore, by linking video visualization with distance results, the system improves the driver's understanding of the risk location, risk level, and adjustment direction. Therefore, it can achieve a highly practical tire scratch prevention warning effect with low hardware dependence in scenarios such as parking close to the curb, driving slowly on narrow roads, cornering in underground parking garages, and temporary parking.

[0091] It should be understood that the above examples are merely illustrative and not limiting. In one possible embodiment, the specific algorithms, threshold settings, display forms, and communication architectures in video acquisition, display, ranging, and early warning can be equivalently replaced or adjusted according to terminal performance, vehicle configuration, and application scenarios, without affecting the implementation idea of ​​real-time early warning based on the shortest distance between the tire and the curb in this application embodiment.

[0092] Example 2

[0093] Figure 3A flowchart illustrating the tire scratch prevention warning method based on mobile terminal and vehicle collaboration provided in this application. Figure 2 ,like Figure 3 As shown, based on the above embodiment 1, the specific steps of determining the shortest distance between the vehicle tire and the curb in step S103 include:

[0094] S1031: For each frame of image, the vehicle tires and curb are determined using an edge detection algorithm.

[0095] Edge detection algorithms are used to extract the contour information of the outer edge of the tire and the edge of the curb from the image, making it easier to identify their relative positional relationship within the same frame.

[0096] In one implementation, after acquiring real-time video frames containing the vehicle tires and the curb, the images are first converted to grayscale, filtered for noise reduction, and contrast enhanced. Then, edge detection is performed to improve the distinguishability of the tire sidewalls and curb boundaries.

[0097] The edge detection results can form a set of edge points for the tire profile and the curb profile.

[0098] S1032: Determine the shortest pixel distance between the vehicle tires and the curb.

[0099] The system iterates and matches the two sets of points to obtain the shortest pixel distance in the image coordinate system. The shortest pixel distance is represented as the minimum Euclidean distance between the set of pixels at the tire edge and the set of pixels at the road edge, or based on the vertical spacing after contour fitting, to reflect the nearest gap in the image domain.

[0100] S1033: Determine the shortest distance corresponding to the shortest pixel distance based on the camera intrinsic and extrinsic parameters of the mobile terminal.

[0101] Camera intrinsic parameters are used to characterize the focal length, principal point position, and pixel scale parameters of the mobile terminal camera, while camera extrinsic parameters are used to characterize the camera's attitude and position relative to the space where the vehicle tires and curb are located. Together, they are used to establish the mapping relationship between pixel coordinates and actual spatial coordinates.

[0102] By combining the pre-calibrated camera intrinsic and extrinsic parameters, the pixel distance is converted into the actual physical distance through a perspective projection model, thereby outputting the shortest distance between the vehicle tire and the curb.

[0103] This implementation first determines the shortest pixel interval between the tire and the curb in the image domain, and then completes the spatial distance mapping based on the camera imaging parameters, so that the distance calculation directly corresponds to the real target area in the video image, which can reduce the error caused by simple visual estimation or rough sensing estimation.

[0104] By adopting the above method, the proximity relationship between the tire and the curb can be directly extracted from each frame of video, and the pixel domain results can be stably converted into the real distance. This improves the accuracy and real-time performance of the scraping risk assessment in edge-close scenarios, allowing drivers to obtain more intuitive and quantifiable distance prompts and reducing the probability of tires scraping against the curb.

[0105] Example 3

[0106] Figure 4 A flowchart illustrating the tire scratch prevention warning method based on mobile terminal and vehicle collaboration provided in this application. Figure 3 ,like Figure 4 As shown, based on the above embodiment 1, the specific steps of determining the shortest distance between the vehicle tire and the curb in step S103 include:

[0107] S1035: For each frame of image, the vehicle wheel hub and curb are determined by the edge detection algorithm.

[0108] Since the tire sidewall is made of black rubber, its edges are difficult to extract accurately and consistently visually. In this embodiment, a wheel hub (also known as a rim) that is mounted coaxially with the tire and has a high-contrast metallic texture is used as a visual measurement reference.

[0109] S1036: Determine the current actual distance from the outermost point of the tire sidewall to the curb based on the actual physical diameter of the wheel hub and tire parameters.

[0110] The actual physical diameter of the wheel hub refers to the nominal outer diameter of the vehicle's wheel hub within the actual vehicle structure. This parameter can be used to establish the correspondence between image pixel scale and actual length scale. Tire parameters characterize the outward expansion of the tire sidewall relative to the outer edge of the wheel hub. Tire parameters may include one or more of the following: tire size, cross-sectional width, aspect ratio, or rolling radius. Users can pre-enter their tire model into the application to automatically retrieve these parameters and associate them with their vehicle, allowing for direct access during subsequent use.

[0111] The projected ellipse of the wheel rim due to rear-side perspective has a major axis that corresponds precisely to the known physical diameter of the rim in perspective projection geometry. Based on this, the pixel-to-physical size mapping ratio at the current viewpoint can be calculated. The outward offset of the tire sidewall relative to the outer edge of the wheel rim is determined based on tire parameters, and this offset is superimposed on the corresponding real position of the outer edge of the wheel rim to obtain the position of the outermost point of the tire sidewall. Then, based on the real position of the curb edge in the same coordinate system, the current real distance between the outermost point of the tire sidewall and the curb is calculated. This method requires no additional calibration objects in the scene.

[0112] S1037: Determine the shortest distance based on the current actual distance.

[0113] In one implementation, the calculated current actual distance is determined as the shortest distance. The warning threshold is then determined based on this shortest distance.

[0114] In one implementation, the shortest distance is predicted after rotating by a preset angle based on the calculated current actual distance. This method can increase redundancy.

[0115] By adopting this implementation method, the geometric accuracy and scene adaptability of the distance judgment between the tire and the curb can be improved. Since the distance result is corrected by the actual physical diameter of the wheel hub and the tire parameters, the measurement error caused by changes in shooting angle, tire shape differences or local edge recognition deviation can be reduced, thereby improving the reliability and timeliness of scratch warning.

[0116] Example 4

[0117] Based on the aforementioned embodiment 3, step S1037 further determines the shortest distance according to the current actual distance, specifically including the following steps:

[0118] S10371: Determine the instantaneous turning radius of the outermost point based on the current steering wheel angle.

[0119] The steering wheel angle can be output by the vehicle's steering angle sensor or read by the onboard controller via the CAN communication interface, facilitating real-time reflection of the vehicle's current steering status. The instantaneous steering radius characterizes the radius of the outermost point's trajectory under current steering conditions. The controller can calculate this radius based on Ackermann steering geometry, taking into account the vehicle's wheelbase, track width, and steering wheel angle. The smaller the radius, the sharper the vehicle's turn and the higher the risk of tire encroachment towards the curb.

[0120] S10372: Based on the instantaneous turning radius, predict the lateral encroachment distance after moving to the side of the road edge by a preset angle.

[0121] The preset angle describes the incremental angle at which the vehicle continues to deflect towards the roadside within a short period of time. Its value can be set in relation to vehicle speed, steering wheel angular velocity, or driving scenario to adapt to scenarios such as low-speed driving close to the roadside and correcting the vehicle's posture when approaching the curb. For example, the preset angle can be set to a fixed 5°.

[0122] The lateral encroachment distance represents the lateral displacement of the outermost point relative to the current curb position towards the inward or towards the curb under the action of a preset angle. The controller can calculate this distance based on the circular motion model, using the instantaneous turning radius and the preset angle, thereby reflecting the further encroachment of the vehicle on the original clearance under a continuous turning trend.

[0123] Specifically, based on the Ackermann steering geometry principle, the steering wheel angle δ is converted into the front wheel deflection angle θ:

[0124] θ = δ / i;

[0125] Where i represents the vehicle's steering ratio, which can be obtained from a vehicle model parameter database (which records the correspondence between the number of steering wheel turns and the wheel deflection angle). Combined with the vehicle's wheelbase L, the instantaneous turning radius R at the outermost point of the tire sidewall is calculated. w :

[0126] Target: front wheel: R w ≈ L / sin(θ) ± d track ;

[0127] Target is the rear wheel: R w ≈ L / tan(θ) ± d track ;

[0128] In the formula, d track This is the track width offset correction term, which physically represents the lateral distance from the outermost point of the tire sidewall to the vehicle's longitudinal axis. This distance can be determined by both the vehicle's track width and the tire's cross-sectional width, i.e., d. track ≈ (Wheel width) / 2 + (Tire cross-section width) / 2. Its sign depends on the direction of front wheel deflection (take a plus sign when deflecting outwards and a minus sign when deflecting inwards).

[0129] Starting from the outermost point of the tire sidewall, along a radius of R w The circular motion is at a small preset angle Δφ (this value can be configured within the application according to sensitivity requirements), and the lateral encroachment distance ΔD to the roadside is:

[0130] ΔD ≈ R w × (1 - cos(Δφ)).

[0131] S10373: Determine the shortest distance based on the current actual distance and the lateral encroachment distance.

[0132] In one specific implementation, the shortest distance can be obtained by subtracting the lateral encroachment distance from the current actual distance.

[0133] By introducing the lateral intrusion prediction corresponding to the instantaneous turning radius and preset angle through the above method, the shortest distance can reflect the vehicle's impending edge intrusion trend, thereby improving the ability to identify tire scratch risks in advance, reducing misjudgments caused by static images alone, and improving the timeliness and accuracy of scratch warnings.

[0134] Example 5

[0135] In one possible implementation, determining the current actual distance from the outermost point of the tire sidewall to the curb in step S1036 includes the following steps:

[0136] S10361: Determine the contour imaging ellipse based on the contour of the vehicle wheel hub.

[0137] In one implementation, edge extraction and contour filtering are performed on the hub region in the image to obtain a set of points on the outer edge of the hub. Robust ellipse fitting is then performed on the point set to obtain a contour imaging ellipse.

[0138] In one implementation, an ellipse fitting algorithm based on arc segment clustering extracts continuous arc segments from the image, clusters them according to their convexity and direction, and performs least-squares ellipse fitting on the clustered arc segment set to obtain a candidate ellipse set. Based on the constraints of the wheel hub's major axis size and its position in the image, ellipse selection is performed to obtain the contour imaging ellipse of the vehicle wheel hub.

[0139] S10362: Determine the pixel-physical size mapping ratio based on the major axis pixels of the contour imaging ellipse and the actual physical diameter of the hub.

[0140] Based on the calibrated physical diameter of the wheel hub and the length of the major axis pixels, the pixel-physical size mapping ratio corresponding to a unit pixel can be calculated and used as the reference for subsequent distance conversion.

[0141] S10363: Determine the outermost point of the tire sidewall based on the pixel-physical size mapping ratio, the contour imaging ellipse, and tire parameters.

[0142] Based on the tire specification information, determine the geometric expansion of the tire sidewall relative to the outer edge of the rim, and then determine the outermost point of the tire sidewall.

[0143] In one specific implementation, tire parameters include tire cross-sectional width and aspect ratio. The tire cross-sectional width characterizes the nominal width between the outer edges of the tire tread, while the aspect ratio characterizes the ratio between the sidewall height and the cross-sectional width. Together, they are used to estimate the physical dimension of the tire sidewall extending outward from the outer edge of the rim. The major axis edge point located on the curb side is extracted based on the contour imaging ellipse, and this point is used as the starting position for the sidewall outward calculation, i.e., the outermost point of the rim. The offset pixel amount is then determined using the following formula: Offset pixel amount = (Tire cross-sectional width × Aspect ratio / 100) / Pixel - Physical size mapping ratio. That is, the outward distance of the tire sidewall relative to the edge point at the pixel level is obtained using the above formula. The outermost point is determined by shifting the edge point by the offset pixel amount along a direction away from the rim center and pointing outward from the sidewall.

[0144] By incorporating tire parameters into the image geometry positioning process, the tire's outer edge is no longer inferred directly from the rim profile, but is corrected by combining the actual outward expansion of the tire sidewall. Therefore, it can more accurately reflect the actual space occupied by the tire.

[0145] S10364: Determine the current real distance from the outermost point to the roadside pixel based on the pixel-physical size mapping ratio.

[0146] Calculate the pixel distance between the outermost point of the tire sidewall and the curb, and multiply it by the pixel-to-physical size mapping ratio to obtain the current true distance.

[0147] By incorporating the actual diameter of the wheel hub into a scale reference and establishing a mapping relationship between the image and physical space using a contour imaging ellipse, the outermost point of the tire sidewall and its actual distance to the curb can be accurately calculated even when the tire sidewall boundary is not easily and stably identified directly. This improves the stability and consistency of distance judgment in tire-edge-hugging scenarios and reduces errors caused by image distortion, local occlusion, or contour blurring.

[0148] The solution will be illustrated with a complete example below.

[0149] (a) Preparatory stage

[0150] When using the vehicle for the first time or when replacing it, users need to complete the following parameter configuration in the mobile application:

[0151] 1. Wheel reference size: The system prioritizes reading the vehicle's VIN code via vehicle-to-everything (V2X) or OBD interface, and automatically obtains the precise rim diameter D from the cloud-based vehicle database. rim And tire specifications. When automatic retrieval fails, the user is guided to manually enter the tire sidewall specification identifier (e.g., "235 / 50 R18"), which the application will automatically parse to obtain the D... rim And tire width and aspect ratio.

[0152] 2. Camera intrinsic parameter acquisition: The application automatically calls the camera interface of the mobile terminal operating system to obtain the current camera's horizontal focal length fx and vertical focal length fy, which are used for distortion correction and perspective projection modeling.

[0153] (II) Real-time Measurement and Early Warning Stage

[0154] The user parks the vehicle near the target location, gets out of the car, stands to the side and rear of the vehicle with a mobile terminal in hand, launches the application, and points the camera at the target wheel and the nearby curb area. The application processes video frames in real time, executing the following four steps sequentially.

[0155] Step 1: Image acquisition and feature extraction.

[0156] The goal of this step is to robustly extract the imaging profile of the wheel rim and the straight lines of the curb from a complex background. Unlike in-vehicle surround view systems which are limited by a fixed viewing angle, this step fully utilizes the free viewing angle advantage of mobile terminals to ensure that the target area is captured in a complete and distortion-free form.

[0157] 1.1 Rim ellipse detection.

[0158] For each acquired frame or interval frame image, grayscale conversion, Gaussian blurring, and Canny edge detection are first performed to obtain a binary edge map. Since the user is shooting from the side and rear, the originally circular rim appears as an ellipse under perspective projection. An ellipse fitting algorithm based on arc segment clustering is adopted: continuous arc segments are extracted from the edge map, clustered according to the convexity and direction of the arc segments, and least-squares ellipse fitting is performed on the clustered arc segment set to obtain a candidate ellipse set.

[0159] 1.2 Rim Ellipse Screening.

[0160] From the set of candidate ellipses, the rim imaging ellipse is uniquely determined by the following dual constraints:

[0161] Long axis dimension constraint: Based on the known physical diameter D of the rim rim Based on the estimated shooting distance (which can be obtained through a laser focusing and ranging module or empirical values), the pixel range within which the major axis of the rim projection ellipse should be located is calculated, and ellipses with obviously inconsistent sizes are filtered out.

[0162] Positional constraints: With the wheel rim positioned in the lower middle of the frame in a normal shooting posture, the center of the ellipse is limited to the range of 50% to 90% of the vertical height of the frame, eliminating irrelevant circular or elliptical interference from the background.

[0163] If no ellipse meeting the criteria is detected, the system displays an arrow or text prompt on the screen to guide the user to adjust the shooting angle.

[0164] 1.3 Key Feature Extraction.

[0165] The selected ellipse is used as the rim imaging contour, and the following key features are extracted:

[0166] Ellipse major axis pixel length L: twice the length of the semi-major axis of the ellipse, in pixels.

[0167] P, the outermost point of the rim ellipse ellipse : That is, the edge pixel on the side of the elliptical outline closest to the curb.

[0168] Based on the fixed geometric relationship between the rim and the tire, P ellipse The outermost point P of the tire sidewall is calculated by offsetting outward along the minor axis of the ellipse. tire The offset is determined by the tire width, aspect ratio, and rim diameter, and can be calculated using the following formula:

[0169] Pixel-to-physical size mapping ratio S = D rim / L;

[0170] Offset pixel amount Δpixel ≈ (tire section width × aspect ratio / 100) / S;

[0171] 1.4 Roadside feature extraction and filtering.

[0172] Independent edge detection is performed on the lower half of the image to extract the edge pixel set. Then, Hough line detection is performed on the edge pixel set to obtain a candidate line set. To accurately identify the upper edge of the curb from the candidate lines, multiple selection rules are comprehensively applied:

[0173] Position Priority: Prioritize the straight line segment located below the rim ellipse and on the outside of the ellipse (away from the side of the vehicle body).

[0174] Angle constraints: The direction of the curb is usually approximately parallel to the longitudinal axis of the vehicle body. Based on the center of the wheel rim ellipse and the perspective relationship of the picture, the expected slope range of the curb is estimated (such as ±30° with the horizontal axis of the picture), and straight lines with excessive angle deviation are eliminated.

[0175] Continuity priority: Road edges are usually long and continuous edges, so the candidate straight line with the longest connected length of the edge points is selected first.

[0176] Inter-frame consistency verification: Detect multiple consecutive frames. If the position and angle of a certain line change less than a preset threshold in consecutive frames (e.g., 3 frames), it is confirmed as a road edge; otherwise, it is judged as interference and removed.

[0177] Ultimately, the straight segment with the highest overall score was selected as the upper edge L of the curb. curb This multi-screening mechanism ensures the robustness of curb extraction, effectively addressing minor hand-held shooting tremors and interference from complex road surface textures.

[0178] Step 2: Monocular scale mapping and current distance measurement.

[0179] The principle is to convert the rim projection ellipse extracted in step 1 into a scale bar, so as to achieve pixel-physical scale mapping without the need for additional calibration objects.

[0180] 2.1 Establish pixel-physical mapping ratio.

[0181] In perspective projection geometry, the major axis of the rim's image ellipse corresponds exactly to the rim's actual physical diameter D. rim The projected length from the current viewpoint. Therefore, the pixel-to-physical-size mapping ratio from the current viewpoint can be obtained by the following formula:

[0182] S = D rim / L (unit: millimeters / pixel);

[0183] Since the wheel and the curb are spatially adjacent and approximately on the same plane, the mapping ratio can be considered a constant within the local measurement area. This rim self-calibration strategy is fundamentally different from all other methods that require external calibration. The rim is both part of the object to be measured and a provider of the measurement reference (due to the challenges of elastic deformation of the tire sidewall and the difficulty in detecting the black rubber edge, using the rim as a visual reference can improve stability and accuracy).

[0184] 2.2 Calculate the current physical distance.

[0185] In the image coordinate system, calculate the outermost point P of the tire sidewall derived in step 1. tire straight line L to the curb curb The vertical pixel distance d. Then the current true distance D between the tire sidewall and the curb. current for:

[0186] D current = d × S;

[0187] Step 3: Steering wheel angle acquisition and trajectory prediction.

[0188] This step represents a crucial leap from static distance measurement to dynamic trajectory prediction.

[0189] 3.1 Real-time acquisition of steering wheel angle.

[0190] The mobile terminal establishes a data link with the vehicle's infotainment system via wireless communication. The vehicle's infotainment system reads the steering wheel angle δ in real time via the CAN bus and sends it to the mobile terminal at a preset frequency (such as every 100 milliseconds).

[0191] 3.2 Ackermann turn geometric modeling.

[0192] This step is the same as the modeling in Example 4 above, and will not be repeated here.

[0193] 3.3 Prediction of lateral encroachment distance.

[0194] To detect scraping trends even under extremely small steering movements, a simplified and practical prediction model is proposed: starting from the outermost point of the tire sidewall, along a radius of R... w The circular arc motion is at a small angle Δφ, and its lateral encroachment distance ΔD to the roadside is:

[0195] ΔD ≈ R w × (1 - cos(Δφ));

[0196] The physical meaning of this formula is: at the current steering wheel angle, if the vehicle continues to travel at a small angle, the outermost point of the tire sidewall will approach the roadside by an additional distance.

[0197] Step 4: Collision risk assessment and graded early warning.

[0198] The current actual distance D between the tire and the curb. current Calculate the predicted shortest distance D based on the predicted lateral encroachment ΔD. predicted :

[0199] D predicted = D current – ΔD;

[0200] According to D predicted For the range of values, implement a tiered early warning strategy:

[0201] Safe zone: D predicted The first threshold (e.g., 15cm) will display a green indicator or distance value on the screen, indicating that there is no risk of scratching during the current operation.

[0202] Warning interval: Second threshold (e.g., 5cm) < D predicted If the distance is less than or equal to the first threshold, the screen turns yellow and displays the real-time distance value, prompting the driver to operate with caution and suggesting that the driver slow down and reduce the steering wheel angle.

[0203] Danger zone: D predicted If the threshold is less than or equal to the second threshold, the screen turns red and triggers an audible and vibration alarm, clearly reminding the driver to stop immediately or reverse the steering wheel to avoid scratches.

[0204] The specific values ​​of the first and second thresholds can be configured by the user within the application according to their personal driving habits, in order to balance the sensitivity and comfort of the warning.

[0205] This example leverages the free-viewpoint advantage of mobile terminals to bypass the perception blind spots and distortions of the vehicle's surround-view system; it uses the projected ellipse of the wheel rim as a "natural scale" to achieve monocular scale mapping without the need for additional calibration objects; and it introduces the vehicle's Ackerman steering geometry model to complete the upgrade of the early warning logic from "static distance measurement" to "dynamic trajectory prediction".

[0206] Figure 5 A schematic diagram of a tire anti-scratch warning device based on mobile terminal and vehicle collaboration provided in this application is shown below. Figure 5 As shown, the tire anti-scratch warning device 40 based on mobile terminal and vehicle collaboration provided in this embodiment includes:

[0207] The acquisition module 401 is used to acquire video data captured by the mobile terminal in real time. The video data includes vehicle tires and roadside curbs in the same frame of the image.

[0208] Display module 402 is used to display video data in a display device;

[0209] The calculation module 403 is used to determine the shortest distance between the vehicle tires and the curb based on video data;

[0210] The early warning module 404 is used to output a scratch warning message when the shortest distance is less than the early warning threshold.

[0211] Furthermore, the calculation module 403 is specifically used for:

[0212] For each frame of the image, the vehicle tires and the curb are determined using an edge detection algorithm;

[0213] Determine the shortest pixel distance between the vehicle tires and the curb;

[0214] Based on the camera intrinsic and extrinsic parameters of the mobile terminal, determine the shortest distance corresponding to the shortest pixel distance.

[0215] Furthermore, the calculation module 403 is specifically used for:

[0216] For each frame of the image, the vehicle wheel hub and the curb are determined using an edge detection algorithm;

[0217] Based on the actual physical diameter of the wheel hub and tire parameters, determine the current actual distance from the outermost point of the tire sidewall to the curb;

[0218] Determine the shortest distance based on the current actual distance.

[0219] Furthermore, the calculation module 403 is specifically used for:

[0220] Determine the instantaneous turning radius of the outermost point based on the current steering wheel angle;

[0221] Based on the instantaneous turning radius, predict the lateral encroachment distance after moving to the roadside at a preset angle;

[0222] Determine the shortest distance based on the current actual distance and the lateral encroachment distance.

[0223] Furthermore, the calculation module 403 is specifically used for:

[0224] Based on the contour of the vehicle's wheel hub, determine the contour imaging ellipse;

[0225] The pixel-to-physical size mapping ratio is determined based on the major axis pixels of the contour imaging ellipse and the actual physical diameter of the hub.

[0226] The outermost point of the tire sidewall is determined based on the pixel-to-physical size mapping ratio, the contour imaging ellipse, and tire parameters.

[0227] Based on the pixel-physical size mapping ratio, determine the current real distance from the outermost point to the roadside pixel.

[0228] Furthermore, the calculation module 403 is specifically used for:

[0229] Based on the contour imaging ellipse, determine the edge point of the ellipse closest to the curb along its major axis;

[0230] The offset pixel amount is determined using the following formula:

[0231] Offset pixel amount = (tire section width × aspect ratio / 100) / pixel - physical size mapping ratio;

[0232] The outermost point is determined based on the edge point and the offset pixel amount.

[0233] The apparatus provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0234] Figure 6 This is a schematic diagram of the electronic device provided in this application. The electronic device can be a vehicle controller or a terminal device equipped with blind spot assist. Figure 6 As shown, the electronic device 60 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus 504.

[0235] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0236] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0237] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0238] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0239] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0240] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0241] This application also provides a vehicle, including: a vehicle body, a controller, a communication module, and a display device, wherein the controller is used to perform the methods as described in the above method embodiments.

[0242] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0243] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0244] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0245] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0246] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0247] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0248] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0249] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0250] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A tire scratch prevention warning method based on mobile terminal and vehicle collaboration, characterized in that, The method includes: Real-time acquisition of video data captured by a mobile terminal, wherein the same frame of the video data includes vehicle tires and roadside curbs; The video data is displayed on a display device; Based on the video data, determine the shortest distance between the vehicle tires and the curb; When the shortest distance is less than the warning threshold, a scratch warning message is output.

2. The method according to claim 1, characterized in that, Determining the shortest distance between the vehicle tires and the curb based on the video data includes: For each frame of the image, the vehicle tires and the curb are determined using an edge detection algorithm; Determine the shortest pixel distance between the vehicle tires and the curb; The shortest distance corresponding to the shortest pixel distance is determined based on the camera intrinsic and extrinsic parameters of the mobile terminal.

3. The method according to claim 1, characterized in that, Determining the shortest distance between the vehicle tires and the curb based on the video data includes: For each frame of the image, the vehicle wheel hub and the curb are determined using an edge detection algorithm; Based on the actual physical diameter of the wheel hub and tire parameters, determine the current actual distance from the outermost point of the tire sidewall to the curb. The shortest distance is determined based on the current actual distance.

4. The method according to claim 3, characterized in that, Determining the shortest distance based on the current actual distance includes: Determine the instantaneous turning radius of the outermost point based on the current steering wheel angle; Based on the instantaneous turning radius, predict the lateral encroachment distance after moving towards the curb side by a preset angle; The shortest distance is determined based on the current actual distance and the lateral encroachment distance.

5. The method according to claim 3 or 4, characterized in that, The step of determining the current actual distance from the outermost point of the tire sidewall to the curb based on the actual physical diameter of the wheel hub and tire parameters includes: Based on the contour of the vehicle wheel hub, determine the contour imaging ellipse; The pixel-physical size mapping ratio is determined based on the major axis pixels of the contour imaging ellipse and the actual physical diameter of the wheel hub. The outermost point of the tire sidewall is determined based on the pixel-physical size mapping ratio, the contour imaging ellipse, and the tire parameters. Based on the pixel-physical size mapping ratio, determine the current real distance from the outermost point to the roadside pixel.

6. The method according to claim 5, characterized in that, The tire parameters include the tire cross-sectional width and aspect ratio. Determining the outermost point of the tire sidewall based on the pixel-to-physical size mapping ratio, the contour imaging ellipse, and the tire parameters includes: Based on the contour-imaged ellipse, determine the edge point of the ellipse closest to the curb along its major axis; The offset pixel amount is determined using the following formula: Offset pixel amount = (tire section width × aspect ratio / 100) / pixel - physical size mapping ratio; The outermost point is determined based on the edge point and the offset pixel amount.

7. The method according to claim 4, characterized in that, The step of predicting the lateral encroachment distance after moving a preset angle toward the roadside based on the instantaneous turning radius includes: Subtract the cosine of the preset angle from 1, and multiply it by the instantaneous turning radius to obtain the lateral encroachment distance.

8. A tire anti-scratch warning device based on mobile terminal and vehicle collaboration, characterized in that, The device includes: The acquisition module is used to acquire video data captured by the mobile terminal in real time. The video data includes vehicle tires and roadside curbs in the same frame of the image. A display module is used to display the video data in a display device; A calculation module is used to determine the shortest distance between the vehicle tires and the curb based on the video data; The early warning module is used to output a scratch warning message when the shortest distance is less than the early warning threshold.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A vehicle, characterized in that, include: The vehicle body, controller, communication module, and display device, wherein the controller is used to perform the method as described in any one of claims 1-7.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

12. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images