Vehicle control method, electronic device, and vehicle

Abstract

A vehicle control method, applied to the technical field of intelligent vehicle control. The method comprises: acquiring distortion information of a monitoring image, determining a plurality of target areas having different degrees of distortion in the monitoring image on the basis of the distortion information, and performing target detection on the monitoring image; in response to detecting a target, determining at least one target area where the target is located; and on the basis of the target area where the target is located, determining the relative position between the target and a vehicle, so as to determine whether the target invades an alert area, wherein the alert area is used for determining whether the target has a safety impact on the vehicle. The control method reduces errors caused by distortions of monitoring images, and improves the accuracy and reliability of target intrusion detection. In addition, the present application also relates to an electronic device and a vehicle.

Description

Vehicle control methods, electronic equipment and vehicles

[0001] This application claims priority to Chinese Patent Application No. 2024119373483, filed on December 26, 2024, entitled "Vehicle Control Method, Electronic Device and Vehicle", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of vehicle intelligent control technology, and in particular to a vehicle control method, electronic device and vehicle. Background Technology

[0003] In recent years, an increasing number of car brands have begun to equip their vehicles with intrusion detection features. These features utilize onboard cameras and other sensors to monitor the area around the vehicle in real time after it has been parked and turned off, and record any unusual activity. However, traditional intrusion detection primarily relies on images captured by fisheye cameras for monitoring and assessment. Fisheye cameras, however, suffer from significant image distortion, leading to substantial errors in identifying potential intrusions. Summary of the Invention

[0004] In view of this, the purpose of this application is to propose a vehicle control method, electronic equipment and vehicle to avoid large errors in target intrusion judgment caused by image distortion.

[0005] To achieve the above objectives, this application provides a vehicle control method, comprising:

[0006] Obtain distortion information of the monitoring image, determine multiple target regions with different distortion degrees in the monitoring image based on the distortion information, and perform target detection on the monitoring image;

[0007] In response to the detection of a target, at least one target region is determined where the target is located;

[0008] Based on the target area where the target is located, the relative position between the target and the vehicle is determined to determine whether the target has intruded into the warning area;

[0009] The warning zone is used to determine whether the target poses a safety threat to the vehicle.

[0010] Furthermore, in response to determining that the target area is a region in the monitored image where the area of ​​distorted image is less than or equal to a preset percentage, the step of determining the relative position of the target and the vehicle based on the target area where the target is located, to determine whether the target has intruded into the warning area, includes:

[0011] Whether the target has intruded into the warning area is determined based on the position of the lower left / right corner of the target's bounding box relative to the vehicle's warning area; or,

[0012] Whether the target has intruded into the warning area is determined based on the position of the lower left / right corner and the lower boundary of the target's bounding box relative to the vehicle's warning area; or,

[0013] Whether the target has intruded into the warning area is determined based on the position of the lower boundary of the target's bounding box relative to the vehicle's warning area.

[0014] Further, determining whether the target has intruded into the warning area based on the position of the lower left / right corner and the lower boundary of the target's bounding box relative to the vehicle's warning area includes:

[0015] In response to determining the warning area of ​​the lower left / right corner of the target bounding box where no intruding vehicle is located, it is determined whether the lower boundary of the target bounding box intersects with both the upper and lower boundaries of the warning area simultaneously.

[0016] In response to determining that the lower boundary of the target bounding box intersects with both the upper and lower boundaries of the warning area, the target intrusion warning area is determined.

[0017] Furthermore, the monitoring image includes a preset central region; determining whether the target has intruded into the warning area based on the position of the lower boundary of the target's bounding box relative to the vehicle's warning area includes:

[0018] In response to determining that the center point of the target bounding box is located in the middle preset area of ​​the monitoring image, the folding state of the vehicle's rearview mirror is determined when acquiring the monitoring image outside the vehicle.

[0019] In response to determining that the rearview mirror is in an open state, it is determined whether the center segment of the lower boundary of the target bounding box is within the warning area of ​​the vehicle;

[0020] In response to determining that the lower boundary center segment of the target bounding box is within the vehicle's warning zone, the target intrusion warning zone is determined.

[0021] Furthermore, when the rearview mirror is in an open state, determining that the lower boundary center segment of the target bounding box is within the vehicle's warning zone includes:

[0022] Extract the coordinate values ​​of all points in the lower boundary center segment of the target bounding box;

[0023] In response to determining that the coordinates of any point on the lower boundary center segment are within the warning area, the lower boundary center segment of the target bounding box is determined to be within the warning area of ​​the vehicle.

[0024] Furthermore, the monitoring image includes a preset area on the left and a preset area on the right; determining whether the target has intruded into the warning area based on the position of the lower left / right corner of the target's bounding box relative to the vehicle's warning area includes:

[0025] In response to determining that the center point of the target bounding box is located in the preset area on the left side of the monitoring image, it is determined whether the lower right corner of the target bounding box is within the warning area of ​​the vehicle;

[0026] In response to determining that the lower right corner of the target bounding box is within the vehicle's warning area, the target intrusion warning area is determined.

[0027] Furthermore, the monitoring image includes a preset area on the left and a preset area on the right; determining whether the target has intruded into the warning area based on the position of the lower left / right corner of the target's bounding box relative to the vehicle's warning area includes:

[0028] In response to determining that the center point of the target bounding box is located in the preset area on the right side of the monitoring image, it is determined whether the lower left corner of the target bounding box is within the warning area of ​​the vehicle;

[0029] In response to determining that the lower left corner of the target bounding box is within the vehicle's warning area, the target intrusion warning area is determined.

[0030] Furthermore, determining that the lower left corner of the target bounding box is within the vehicle's warning area includes:

[0031] Extract the coordinates of the lower left corner of the target bounding box;

[0032] Compare the coordinates of the lower left corner with the boundary coordinates of the warning area;

[0033] In response to determining that the coordinates of the lower left corner of the target bounding box are within the boundary coordinate range of the warning area, it is determined that the lower left corner of the target bounding box is within the warning area of ​​the vehicle.

[0034] Furthermore, in response to determining that the target area is a region in the monitored image where the area of ​​distorted image is greater than a preset percentage, the step of determining the relative position of the target and the vehicle based on the target area where the target is located, in order to determine whether the target has intruded into the warning area, includes:

[0035] Determine the relative distance between the target and the vehicle;

[0036] In response to determining that the relative distance is less than or equal to a preset distance, it is determined that the target has intruded into the warning area.

[0037] Furthermore, the method also includes:

[0038] In response to determining that the relative distance is greater than a preset distance, it is determined that the target has not intruded into the warning area.

[0039] Furthermore, the method also includes:

[0040] In response to target detection, determine the area of ​​the target bounding box;

[0041] In response to determining that the area is less than or equal to a preset area, the relative distance between the target and the vehicle is determined; in response to determining that the relative distance is less than or equal to a preset distance, the target is determined to have intruded into the warning area.

[0042] Furthermore, determining the at least one target area where the target is located includes:

[0043] By determining the location of the center point of the target bounding box, at least one target region in which the target is located is determined.

[0044] Furthermore, after acquiring monitoring images outside the vehicle, a preprocessing process for the monitoring images is also included, which includes at least one of image denoising, brightness adjustment, and contrast enhancement.

[0045] Based on the same inventive concept, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method described above when executing the computer program.

[0046] Based on the same inventive concept, this application also provides a vehicle that includes the aforementioned electronic equipment.

[0047] As can be seen from the above, the vehicle control method, electronic device, and vehicle provided in this application include: acquiring distortion information of the monitoring image; determining multiple target regions with different distortion degrees in the monitoring image based on the distortion information; and performing target detection on the monitoring image; in response to the detection of a target, determining at least one target region where the target is located; and determining the relative position of the target and the vehicle based on the target region where the target is located, so as to determine whether the target has intruded into the warning area. Due to the characteristics of fisheye cameras, image distortion is more severe at the edges of the monitoring image, resulting in a large error in position determination. By determining multiple target regions with different distortion degrees in the monitoring image based on the distortion information of the monitoring image, and selecting different methods for determining whether the target has intruded into the warning area based on the target region where the target is located, the error caused by the image distortion of the fisheye camera is reduced, so as to accurately detect whether the target has intruded. This can prevent common security threats such as vehicle scratches, door opening accidents, and property theft, and detect other potential anomalies, such as suspicious persons loitering around the vehicle, thereby improving the accuracy and reliability of target intrusion detection. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1a is a flowchart of a vehicle control method according to an embodiment of this application;

[0050] Figure 1b is a schematic diagram of the positional relationship between the vehicle rearview mirror and the camera in an embodiment of this application, wherein 1 is the rearview mirror; 2 is the camera; and 3 is the monitoring image monitored by the camera.

[0051] Figure 2 is a monitoring image 1 in the vehicle control method of this application embodiment;

[0052] Figure 3 is a second monitoring image in the vehicle control method of this application embodiment;

[0053] Figure 4 is a monitoring image three in the vehicle control method of this application embodiment;

[0054] Figure 5 is a monitoring image four in the vehicle control method of this application embodiment;

[0055] Figure 6 is a monitoring image five in the vehicle control method of this application embodiment;

[0056] Figure 7 is a monitoring image six in the vehicle control method of this application embodiment;

[0057] Figure 8 is a monitoring image seven in the vehicle control method of this application embodiment;

[0058] Figure 9 is a monitoring image eight in the vehicle control method of this application embodiment;

[0059] Figure 10 is a monitoring image nine in the vehicle control method of this application embodiment;

[0060] Figure 11 is a schematic diagram of a vehicle control device according to an embodiment of this application;

[0061] Figure 12 is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0063] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0064] In related technologies, with the rapid development of intelligent vehicle technology, vehicle security monitoring systems have become an important component for improving driving safety and user experience. In recent years, an increasing number of car brands have begun to equip their vehicles with intrusion detection functions. These systems utilize onboard 360-degree fisheye cameras and other sensors to monitor abnormal situations around the vehicle in real time after the vehicle is parked and the engine is off, and record abnormal video. This function can not only effectively prevent vehicle scratches, door opening accidents, and theft, but also provide important evidence. However, traditional intrusion detection functions mainly rely on images from 360-degree fisheye cameras for monitoring and judgment. Due to the significant image distortion of fisheye cameras, relying solely on images for target detection and intrusion determination within the warning area has a large margin of error. This error may lead to missed or false identification of abnormal situations, affecting the accuracy and reliability of the intrusion detection function.

[0065] Based on the above problems, the applicant discovered that: The distortion information of the monitoring image is obtained; multiple target regions with different distortion degrees are identified in the monitoring image based on the distortion information; target detection is performed on the monitoring image; in response to target detection, at least one target region where the target is located is determined; based on the target region where the target is located, the relative position of the target and the vehicle is determined to determine whether the target has intruded into the warning area. Due to the characteristics of fisheye cameras, image distortion is more severe at the edges of the monitoring image, leading to a larger error in position determination. Identifying multiple target regions with different distortion degrees in the monitoring image based on the distortion information of the monitoring image, and selecting different methods to determine whether a target has intruded into the warning area based on the target region where the target is located, reduces the error caused by fisheye camera image distortion, accurately detects whether the target has intruded, and can prevent common security threats such as vehicle scrapes, door opening accidents, and property theft, as well as detect other potential anomalies, such as suspicious persons loitering around the vehicle, thus improving the accuracy and reliability of target intrusion detection.

[0066] The embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0067] This application provides a vehicle control method, as shown in Figures 1a and 1b. In some embodiments, the method is executed by a vehicle controller or a data processor independently of the vehicle controller. Subsequent embodiments will use the vehicle controller as an example for illustration. A camera 2 is installed on the rearview mirror 1 of the vehicle to collect monitoring images 3 outside the vehicle. The monitoring images include a warning area. The warning area is used to determine whether a target poses a safety impact on the vehicle. The size and position of the warning area can be configured according to actual needs. The method includes:

[0068] S101. Obtain distortion information of the monitoring image, determine multiple target regions with different distortion degrees in the monitoring image based on the distortion information, and perform target detection on the monitoring image.

[0069] For example, the camera is integrated and installed at the bottom or outer edge of the exterior rearview mirror.

[0070] In practice, cameras are installed on the vehicle's rearview mirrors to collect real-time monitoring images of the vehicle's surroundings. Typically, vehicles are equipped with 360-degree fisheye cameras, providing a comprehensive field of view. The distortion monitoring image can be segmented into multiple target regions with varying degrees of distortion; for example, the central region of the image may have less distortion, while the edge regions may have greater distortion. Segmentation can be based on quantitative indicators of distortion degree, such as the numerical range of distortion parameters, or on the proportion of distorted image area in the monitoring image. For example, a region is identified as a target region when its distorted image area proportion is less than or equal to a preset proportion (for example, the preset proportion could be set to 0.6). Monitoring images may be affected by factors such as changes in lighting, weather conditions (e.g., rain or snow), and low-light environments at night. Therefore, image preprocessing may be necessary before target detection. Preprocessing steps may include image denoising, brightness adjustment, and contrast enhancement to improve image quality and facilitate subsequent target detection. Object detection refers to the identification and localization of specific objects (such as pedestrians, vehicles, bicycles, etc.) in an image. It typically uses deep learning-based object detection algorithms, such as R-CNN (Region-based Convolutional Neural Networks), YOLO (You Only Look Once), and SSD (Single Shot MultiBox Detector). These algorithms analyze the input image using a trained model, identify the objects in the image, and output the bounding boxes of these objects and their categories (such as pedestrians, cars, bicycles, etc.).

[0071] In practical implementation, the preprocessing stage, as a crucial step before target detection, aims to eliminate degrading factors introduced by sudden changes in illumination, severe weather, or low-light environments in the monitored image, thereby improving the detection accuracy and robustness of subsequent deep learning models. For image denoising, considering that fisheye cameras are susceptible to interference from water droplets, fog scattering, and sensor thermal noise in rainy or snowy weather, adaptive algorithms such as bilateral filtering, non-local means (NL-Means), or deep learning-based denoising networks (such as DnCNN) can be employed to effectively suppress random noise while preserving target edge details, avoiding image blurring caused by traditional Gaussian filtering. Brightness adjustment utilizes histogram equalization, gamma correction, or scene-statistic-based adaptive brightness mapping methods to suppress overexposed areas and compensate for dark areas. This is particularly effective for complex lighting distributions at night, where streetlight glare and shadows coexist, achieving dynamic normalization of the overall image brightness to prevent target misses due to brightness imbalances. Contrast enhancement further employs limited contrast adaptive histogram equalization or a multi-scale decomposition algorithm based on Retinex theory to independently adjust contrast within local windows. This highlights the texture features of targets such as pedestrians and vehicles while avoiding noise amplification and artifacts caused by global enhancement, ensuring that the monitored image maintains high visual recognizability in different regions. These preprocessing steps are typically executed sequentially in cascade and parameters can be dynamically adjusted based on real-time environmental perception data (such as feedback from light and rain sensors). The final output is a standardized, high-quality feature image, providing stable and reliable input data for target detection models based on R-CNN, YOLO, or SSD.

[0072] S102. In response to detecting a target, determine at least one target area where the target is located;

[0073] In practice, after acquiring and preprocessing the monitoring images, target detection algorithms are used to identify targets in the images. The target detection algorithm outputs a bounding box for each target (as shown in Figure 7, after a vehicle is detected, the vehicle is selected using the bounding box). This bounding box describes the target's position and size in the monitoring image. The location of the target can be determined by identifying the center point of the bounding box. The center point of the bounding box is its geometric center, providing a simplified reference point, making location determination in complex images more intuitive and efficient, and accurately identifying at least one target region.

[0074] S103. Based on the target area where the target is located, determine the relative position between the target and the vehicle to determine whether the target has intruded into the warning area.

[0075] In practice, the monitoring image is usually divided into multiple target regions to facilitate more precise determination of the target location. Specifically, due to the characteristics of fisheye cameras, image distortion is more severe at the edges of the monitoring image, leading to larger errors in location determination. If the target region is determined to be an area in the monitoring image where the proportion of distorted image area is less than or equal to a preset proportion (for example, the target region is part S2 in Figure 2), when the center point of the target detection box is determined to be in the target region of the monitoring image, the detection of whether the target has intruded into the warning area is based on the relative position of the target bounding box and the vehicle's warning area. Because the proportion of distorted image area in the target region is small, the accuracy of detecting whether the target has intruded within the target region by the position of the target bounding box is higher. If the target region is determined to be an area in the monitoring image where the proportion of distorted image area is greater than a preset proportion (for example, the target region is part of the left edge 1 / 5 and the right edge 1 / 5 of the monitoring image, as shown in parts S1A and S1B in Figure 2), then the detection method can be more precise. When the center point of the target detection box is determined to be within the target area of ​​the monitored image, direct reliance on the monitored image for target location determination may lead to significant errors due to the large proportion of distorted image area in the target region. Therefore, the relative distance between the target and the vehicle is determined, and the intrusion is detected based on this relative distance. High-precision distance measurement data can be provided by the vehicle's radar sensors, thereby improving the accuracy of target location determination and more accurately determining whether an intrusion has occurred. If it is determined that the target has indeed intruded into the warning area, it indicates a potential security threat around the vehicle, such as vehicle collisions or theft. At this time, a target intrusion alarm is issued. This can be achieved through in-vehicle or external speakers to alert the driver or surrounding personnel; by displaying alarm information on the dashboard or central control screen; by connecting the vehicle system to the driver's mobile phone to send an alarm notification to the driver's phone to alert them to the abnormal situation; and by automatically activating the camera recording function to record the entire intrusion process and save it as a video file for later review and evidence preservation. The main purpose of issuing the alarm is to alert the driver or surrounding personnel to potential security threats around the vehicle and to take necessary preventative measures in a timely manner. Car owners can be informed of any unusual situations around their vehicle immediately, preventing potential losses and accidents, and ensuring the safety of the vehicle and its contents.

[0076] In this embodiment, by dividing the target area according to the degree of image distortion and selecting different detection methods, the error caused by fisheye camera image distortion is reduced, and the intrusion of the target is accurately detected. This not only prevents common security threats such as vehicle scratches, door opening accidents, and property theft, but also detects other potential anomalies, such as suspicious persons loitering around the vehicle. This improves the accuracy and reliability of detection, enhances user experience, and strengthens vehicle security.

[0077] The following embodiments provide a detailed explanation of how to determine whether a target has intruded into a warning area, ensuring effective monitoring of the vehicle's surrounding environment under various conditions. In response to determining that the target area is a region in the monitored image where the area of ​​distortion is less than or equal to a preset percentage, the relative position of the target and the vehicle is determined based on the target area to determine whether the target has intruded into the warning area, including:

[0078] Determine whether the target has intruded into the warning area based on the position of the lower left / right corner of the target's bounding box relative to the vehicle's warning area;

[0079] In practice, the location of the target intrusion is determined based on the position of the lower left / right corner of the target bounding box or the position of the lower boundary of the target bounding box. First, the position of the center point of the target bounding box is determined. When the center point of the target bounding box is in the preset area on the left side of the monitoring image (when the rearview mirror is folded, the preset area on the left side of the monitoring image can be set to the left half of the monitoring image, as shown in part S3 of Figure 5), it is determined whether the lower right corner of the target bounding box is in the vehicle's warning area. If the lower right corner of the target bounding box is determined to be in the vehicle's warning area, it indicates that the target is too close to the vehicle, and the target intrusion is determined. When the center point of the target bounding box is determined to be in the preset area on the right side of the monitoring image (when the rearview mirror is folded, the preset area on the right side of the monitoring image can be set to the right half of the monitoring image, as shown in part S4 of Figure 6), it is determined whether the lower left corner of the target bounding box is in the vehicle's warning area. If the lower left corner of the target bounding box is determined to be in the vehicle's warning area (i.e., the target detection algorithm detects the target vehicle and selects the vehicle through the target detection box, and the lower left corner of the target bounding box is in the vehicle's warning area), it indicates that the target is too close to the vehicle, and the target intrusion is determined. If it is determined that the lower left / right corner of the target bounding box is not within the vehicle's warning zone, then it is determined that there is no target intrusion.

[0080] Alternatively, determine whether the target has intruded into the warning area based on the position of the lower left / right corner of the target's bounding box and the lower boundary of the target's bounding box relative to the vehicle's warning area;

[0081] In practice, the first step is to determine whether a target has intruded based on the position of its lower left / right corner. If the lower left / right corner of the target's bounding box is not within the vehicle's surveillance area, the position of the lower boundary of the target's bounding box is used to determine if the target has intruded. This involves checking if the lower boundary of the target's bounding box intersects with both the upper and lower boundaries of the surveillance area. If the lower boundary of the target's bounding box intersects with both the upper and lower boundaries of the surveillance area (as shown in Figure 7), it indicates that the target is too close to the vehicle, and intrusion is confirmed. This ensures the security monitoring of the vehicle's surrounding environment.

[0082] Alternatively, the location of the target's lower bounding box relative to the vehicle's warning area can be used to determine whether the target has intruded into the warning area.

[0083] In practice, the location of the lower boundary of the target bounding box can be used to determine whether the target has intruded. That is, it is determined whether the lower boundary of the target bounding box intersects with the upper and lower boundaries of the warning area at the same time. If it is determined that the lower boundary of the target bounding box intersects with the upper and lower boundaries of the warning area at the same time (as shown in Figure 7), it indicates that the target is too close to the vehicle and the target intrusion is determined.

[0084] In this embodiment, the detection is improved by determining the position of the target bounding box using its lower left / right corner or lower boundary. When the lower left / right corner of the target bounding box is insufficient to determine if an intrusion has occurred, the lower boundary is used for determination. This ensures the utilization of the monitored image and improves detection accuracy and comprehensiveness, enhancing user experience and vehicle safety.

[0085] The following embodiments describe in detail how to determine whether a target has intruded into a warning area based on the position of the lower left / right corner and lower boundary of the target's bounding box relative to the vehicle's warning area, ensuring that all potential intrusion threats can be detected in a timely manner. Determining whether a target has intruded into a warning area based on the position of the lower left / right corner and lower boundary of the target's bounding box relative to the vehicle's warning area includes:

[0086] In response to determining the warning zone of the lower left / right corner of the target bounding box where no intruding vehicles are located, it is determined whether the lower boundary of the target bounding box intersects with both the upper and lower boundaries of the warning zone.

[0087] In practice, when it is determined that no target intrusion was detected based on the position of the lower left / right corner of the target bounding box (i.e., the lower left or right corner of the target bounding box did not enter the warning zone), it is necessary to further determine whether the lower boundary of the target bounding box intersects with both the upper and lower boundaries of the warning zone simultaneously. Even if the corner of the target does not enter the warning zone, its lower boundary may still intersect with the warning zone, thus constituting a potential intrusion threat. The lower boundary of the target bounding box refers to its bottom edge. If the lower boundary of the target bounding box intersects with both the upper and lower boundaries of the warning zone simultaneously, then a target intrusion is determined. If the lower boundary does not intersect with both the upper and lower boundaries of the warning zone simultaneously, then the target has not intruded.

[0088] In response to the determination that the lower boundary of the target bounding box intersects with both the upper and lower boundaries of the warning area, the target intrusion warning area is determined.

[0089] In practice, when the lower boundary of the target bounding box intersects simultaneously with both the upper and lower boundaries of the warning area, it indicates that the target is too close to the vehicle, confirming intrusion and triggering an alarm to alert the vehicle owner to the potential security threat. This ensures the accuracy and reliability of target location determination, improves the accuracy of intrusion detection, and ensures secure monitoring of the vehicle's surrounding environment.

[0090] In this embodiment, by determining whether the lower boundary of the target bounding box intersects both the upper and lower boundaries of the warning area, it is possible to detect targets whose bounding box corners do not enter the warning area but may still pose a threat. This ensures that even if the corners of the target bounding box do not enter the warning area, its lower boundary may still intersect with the warning area, thus constituting a potential intrusion threat, and that all potential intrusion threats can be detected in a timely manner.

[0091] The following embodiments detail how to determine whether a target has intruded into a warning area based on the position of the lower boundary of the target's bounding box relative to the vehicle's warning area, improving the comprehensiveness and accuracy of detection and reducing false alarms and false negatives. The monitoring image includes a pre-defined central area; determining whether a target has intruded into the warning area based on the position of the lower boundary of the target's bounding box relative to the vehicle's warning area includes:

[0092] In response to determining that the center point of the target bounding box is located in the middle preset area of ​​the monitoring image, the folding state of the vehicle's rearview mirror is determined when acquiring the monitoring image outside the vehicle.

[0093] In practice, the intermediate preset area is usually set in the middle third of the monitoring image. When the center point of the target bounding box is determined to be in the intermediate preset area of ​​the monitoring image, the folding state of the vehicle's rearview mirror is determined when collecting the monitoring image outside the vehicle. The rearview mirror is usually installed on both sides of the vehicle and equipped with a fisheye camera to collect the monitoring image outside the vehicle. The folding state of the vehicle's rearview mirror will directly affect the acquisition angle of the fisheye camera. When the rearview mirror is in the open state, the collected monitoring image is shown in Figure 3. In the figure, the upper boundary of the warning area is basically parallel to the lower edge of the monitoring image, and the upper boundary of the warning area is on the side away from the vehicle, while the lower boundary of the warning area is on the side closer to the vehicle. When the rearview mirror is in the folding state, the collected monitoring image is shown in Figure 4. In the figure, the upper boundary of the warning area is at a certain angle to the lower edge of the monitoring image, and the upper boundary of the warning area is on the side away from the vehicle, while the lower boundary of the warning area is on the side closer to the vehicle. When the center point of the target bounding box is located in the middle of the preset area of ​​the monitoring image, it is usually impossible to accurately determine whether the target has intruded based on the position of the lower left / right corner of the target bounding box. It is necessary to determine the folding state of the vehicle's rearview mirror when the monitoring image outside the vehicle is acquired, and to determine the strategy for judging whether the target has intruded based on the folding state of the vehicle's rearview mirror.

[0094] In response to determining that the rearview mirror is in an open state, determine whether the center segment of the lower boundary of the target bounding box is within the vehicle's warning zone;

[0095] In practice, when the rearview mirror is not folded, it is possible to more accurately determine whether the target has intruded by judging whether the lower boundary center segment of the target bounding box is within the vehicle's warning zone. First, the coordinate values ​​of all points of the lower boundary center segment of the target bounding box are extracted. If the coordinate value of any point of the lower boundary center segment is within the warning zone, it is determined that the lower boundary center segment has entered the warning zone.

[0096] In response to determining that the lower boundary center segment of the target bounding box is within the vehicle's warning zone, the target intrusion is identified.

[0097] In practice, it is determined whether the center segment of the lower boundary of the target bounding box is within the vehicle's warning zone. If it is determined that the center segment of the lower boundary of the target bounding box is within the vehicle's warning zone, it indicates that the target is too close to the vehicle, thus confirming target intrusion. This improves the comprehensiveness and accuracy of intrusion detection, ensuring the security monitoring of the vehicle's surrounding environment.

[0098] In this embodiment, by setting a preset central region in the monitoring image, with the center point of the target bounding box located within this region, the vehicle's rearview mirror is folded when the external monitoring image is acquired. If the mirror is not folded, the system determines whether the target has intruded by judging whether the center segment of the lower boundary of the target bounding box is within the vehicle's warning zone. This ensures that even if the target is located in the central region of the monitoring image, it can accurately determine whether it constitutes an intrusion threat, ensuring that all potential intrusion threats can be detected in a timely manner. This significantly improves the comprehensiveness and accuracy of detection, reduces false alarms and false negatives, and enhances real-time response capabilities and user experience.

[0099] The following embodiments provide a detailed explanation of determining whether a target has intruded based on the position of the lower left / right corner of the target bounding box, in order to more accurately determine the target's positional relationship in the monitoring image and improve the accuracy and reliability of target position determination. The monitoring image includes a preset area on the left and a preset area on the right; determining whether a target has intruded into the warning area based on the position of the lower left / right corner of the target's bounding box relative to the vehicle's warning area includes:

[0100] In response to determining that the center point of the target bounding box is located in the preset area on the left side of the monitoring image, it is determined whether the lower right corner of the target bounding box is within the vehicle's warning area;

[0101] In practice, the warning zone is used to determine whether a target poses a threat to the vehicle. The size and location of the warning zone can be configured according to actual needs. When the center point of the target bounding box is determined to be within the preset area on the left side of the monitoring image, the coordinates (xmax, ymin) of the lower right corner of the target bounding box can be extracted. The coordinates of the lower right corner are compared with the boundary coordinates of the warning zone. If both the xmax and ymax coordinates of the lower right corner are within the range of the warning zone, then the lower right corner is determined to have entered the warning zone.

[0102] In response to the determination that the lower right corner of the target bounding box is within the vehicle's warning zone, the target intrusion is confirmed;

[0103] In practice, if the lower right corner of the target's bounding box is determined to be within the vehicle's warning zone, it indicates that the target is too close to the vehicle, confirming an intrusion. An intrusion alarm is then issued to alert the vehicle owner to the potential security threat. This ensures the accuracy and reliability of target location determination, improves the accuracy of intrusion detection, and ensures secure monitoring of the vehicle's surroundings.

[0104] In response to determining that the center point of the target bounding box is located in the preset area on the right side of the monitoring image, it is determined whether the lower left corner of the target bounding box is within the vehicle's warning area;

[0105] In practice, when the center point of the target bounding box is determined to be within a preset area on the right side of the monitoring image, the coordinates (xmin, ymin) of the lower left corner of the target bounding box can be extracted. The coordinates of the lower left corner are then compared with the boundary coordinates of the warning area. If both the xmin and ymin coordinates of the lower left corner are within the warning area, then the lower left corner is determined to have entered the warning area.

[0106] In response to the determination that the lower left corner of the target bounding box is within the vehicle's warning zone, the intrusion of the target is confirmed.

[0107] In practice, if the lower left corner of the target's bounding box is determined to be within the vehicle's warning zone, it indicates that the target is too close to the vehicle, confirming target intrusion. An intrusion alarm is then issued to alert the vehicle owner to the potential security threat. This ensures the accuracy and reliability of target location determination, improves the accuracy of intrusion detection, and ensures secure monitoring of the vehicle's surrounding environment.

[0108] In this embodiment, by determining the position of the center point of the target bounding box, the positional relationship of the target in the monitoring image can be more accurately determined, which helps to improve the accuracy and reliability of target position determination. Within different target areas, determination is made based on the lower left / right corner position of the target bounding box, significantly improving the accuracy and reliability of detection, reducing false alarms and false negatives, and enhancing user experience and vehicle safety.

[0109] In some embodiments, in response to determining that the target area is a region in the monitored image where the area of ​​distorted image is greater than a preset percentage, the relative position of the target and the vehicle is determined based on the target area where the target is located, in order to determine whether the target has intruded into the warning area, including:

[0110] Determine the relative distance between the target and the vehicle;

[0111] In response to determining that the relative distance is less than or equal to a preset distance, the target intrusion warning zone is determined.

[0112] In practice, if the target area is determined to be a region in the monitoring image where the area of ​​distortion is greater than a preset percentage (as shown in Figure 8, the center point of the target bounding box is located in the target area of ​​the monitoring image), the relative distance between the target and the vehicle is determined. High-precision distance measurement data can be provided by the vehicle's radar sensor, thereby improving the accuracy of target location determination and more accurately determining whether the target has intruded. When the relative distance is determined to be less than or equal to a preset distance (for example, the preset distance can be set to 20cm), it indicates that the target is too close to the vehicle, and the target intrusion warning zone is determined.

[0113] In response to determining that the relative distance is greater than a preset distance, it is determined that the target has not been invaded.

[0114] In practice, if the relative distance between the target and the vehicle is greater than a preset distance, it indicates that the target is far enough away from the vehicle, and therefore the target is deemed not to have intruded. This ensures the accuracy and reliability of intrusion detection by providing a quantitative standard through distance judgment to confirm whether a target poses a threat to the vehicle, thus ensuring the security monitoring of the vehicle's surrounding environment.

[0115] In this embodiment, relative distance is used to determine whether a target has intruded, reducing false positives and false negatives caused by judgment errors due to image distortion. Relative distance provides a quantitative standard for confirming whether a target poses a threat to the vehicle, ensuring the objectivity and consistency of the judgment and improving the reliability of intrusion detection; it also ensures that any potential intrusion threat can be detected in a timely manner and that necessary supporting evidence is provided.

[0116] In some embodiments, the method further includes:

[0117] In response to target detection, determine the area of ​​the target bounding box;

[0118] In practice, target detection algorithms are used to identify targets in the monitored images. These algorithms generate target bounding boxes, which describe the target's location and extent within the image. After detecting the target and generating the bounding box, the area of ​​the bounding box is calculated. The size of the bounding box reflects the target's size in the image. A larger bounding box area generally indicates that the target is closer to the fisheye camera, while a smaller bounding box area indicates that the target is farther away.

[0119] In response to determining that the area is less than or equal to a preset area, the relative distance between the target and the vehicle is determined; in response to determining that the relative distance is less than or equal to a preset distance, the target intrusion warning zone is determined.

[0120] In practice, when the determined area is less than or equal to a preset area (the preset area is a threshold set according to the specific application scenario and vehicle security requirements to distinguish between near and far targets; for example, the preset area can be set to one-third of the monitored image area), it indicates that the target is far from the fisheye camera, possibly located at the rear of the vehicle. In this case, the accuracy of detecting whether the target has intruded based on the target's bounding box position is poor. Therefore, it is necessary to determine the relative distance between the target and the vehicle and detect whether the target has intruded based on the relative distance. When the determined relative distance is less than or equal to a preset distance (for example, the preset distance can be set to 20cm), it indicates that the target is too close to the vehicle, and a target intrusion warning zone is determined.

[0121] In this embodiment, the distance to the target can be preliminarily determined by calculating the area of ​​the target bounding box. A larger bounding box area generally indicates that the target is closer to the camera, while a smaller bounding box area indicates that the target is farther away. Using the area of ​​the target bounding box as an auxiliary judgment criterion improves the accuracy and reliability of target location determination. An appropriate detection method is selected based on the area size to quickly determine whether the target has intruded. This significantly improves the accuracy and reliability of detection, reduces false alarms and false negatives, and enhances real-time response capabilities and user experience.

[0122] In some embodiments, the vehicle further includes a fisheye camera disposed at the front of the vehicle and a fisheye camera disposed at the rear of the vehicle; the method further includes:

[0123] Obtain distortion information from the monitoring image, identify multiple target regions with different distortion degrees in the monitoring image based on the distortion information, and perform target detection on the monitoring image;

[0124] In response to the detection of a target, at least one target region is determined where the target is located;

[0125] Based on the target area where the target is located, determine the relative position between the target and the vehicle to determine whether the target has intruded into the warning area.

[0126] In practice, since the monitoring images captured by the fisheye cameras at the front and rear of the vehicle (as shown in Figure 9; and the fisheye camera at the rear of the vehicle in Figure 10) have similar viewing angles to the monitoring images captured by the fisheye cameras on the rearview mirrors when the rearview mirrors are not folded, and the positions of the warning areas in the monitoring images are similar, when it is determined that the center point of the target detection box is located in the target area of ​​the monitoring image (the target area is the area in the monitoring image where the area of ​​the distorted image is less than or equal to a preset percentage), the detection is directly based on the lower left / right corner of the target bounding box. The position of the lower boundary center segment of the target bounding box relative to the warning area determines whether a target has intruded. If the center point of the target bounding box is within a preset area on the left side of the monitoring image, it is determined whether the lower right corner of the target bounding box is within the vehicle's warning area. If the lower right corner of the target bounding box is within the vehicle's warning area, it indicates that the target is too close to the vehicle, confirming intrusion. If the center point of the target bounding box is within a preset area on the right side of the monitoring image, it is determined whether the lower left corner of the target bounding box is within the vehicle's warning area. If the lower left corner of the target bounding box is within the vehicle's warning area, it indicates that the target is too close to the vehicle, confirming intrusion. The monitoring image also includes a preset middle area. If the center point of the target bounding box is within the preset middle area of ​​the monitoring image, it is determined whether the lower boundary center segment of the target bounding box is within the vehicle's warning area. If the lower boundary center segment of the target bounding box is within the vehicle's warning area, it indicates that the target is too close to the vehicle, confirming intrusion. This improves the comprehensiveness and accuracy of intrusion detection, ensuring secure monitoring of the vehicle's surrounding environment.

[0127] In this embodiment, by installing fisheye cameras at both the front and rear of the vehicle, a 360-degree field of view can be provided, covering all key areas in front of and behind the vehicle. This 360-degree monitoring ensures there are no blind spots around the vehicle, enabling the timely detection of any potential intrusion threats. This significantly improves the comprehensiveness and accuracy of detection, reduces false alarms and false negatives, and enhances real-time response capabilities and user experience. It ensures that any potential intrusion threats can be detected promptly.

[0128] It should be noted that the method in this embodiment can be executed by a single device, such as a computer or server. The method can also be applied in a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method in this embodiment, and the multiple devices will interact with each other to complete the method.

[0129] It should be noted that the above description describes some embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0130] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides a vehicle control device.

[0131] Referring to Figure 11, the vehicle control device includes:

[0132] The acquisition module 701 is configured to acquire distortion information of the monitoring image, determine multiple target regions with different distortion degrees in the monitoring image based on the distortion information, and perform target detection on the monitoring image;

[0133] The determination module 702 is configured to determine at least one target region where the target is located in response to the detection of a target;

[0134] The detection module 703 is configured to determine the relative position of the target and the vehicle based on the target area where the target is located, so as to determine whether the target has intruded into the warning area;

[0135] The warning zone is used to determine whether the target poses a safety threat to the vehicle.

[0136] Furthermore, the detection module 703 is specifically used for:

[0137] Determine whether the target has intruded into the warning zone based on the position of the target's bottom left / bottom right corner relative to the vehicle's warning zone; or,

[0138] Determine whether a target has intruded into the warning zone based on the position of the target's bottom left / right corner and the bottom boundary of the target's bounding box relative to the vehicle's warning zone; or,

[0139] Whether a target has intruded into the warning zone is determined by the position of the lower boundary of the target's bounding box relative to the vehicle's warning zone.

[0140] Furthermore, the judgment module 702 is specifically used for:

[0141] In response to determining the warning zone of the lower left / right corner of the target bounding box where no intruding vehicles are located, it is determined whether the lower boundary of the target bounding box intersects with both the upper and lower boundaries of the warning zone.

[0142] In response to the determination that the lower boundary of the target bounding box intersects with both the upper and lower boundaries of the warning area, the target intrusion warning area is determined.

[0143] Furthermore, the detection module 703 is also specifically used for:

[0144] In response to determining that the center point of the target bounding box is located in the middle preset area of ​​the monitoring image, the folding state of the vehicle's rearview mirror is determined when acquiring the monitoring image outside the vehicle.

[0145] In response to determining that the rearview mirror is in an open state, determine whether the center segment of the lower boundary of the target bounding box is within the vehicle's warning zone;

[0146] In response to determining that the lower boundary center segment of the target bounding box is within the vehicle's warning zone, the target intrusion warning zone is determined.

[0147] Furthermore, the detection module 703 is also specifically used for:

[0148] Extract the coordinates of all points in the center segment of the lower boundary of the target bounding box;

[0149] In response to determining that the coordinates of any point on the lower boundary center segment are within the warning area, the lower boundary center segment of the target bounding box is determined to be within the vehicle's warning area.

[0150] Furthermore, the detection module 703 is also specifically used for:

[0151] In response to determining that the center point of the target bounding box is located in the preset area on the left side of the monitoring image, it is determined whether the lower right corner of the target bounding box is within the vehicle's warning area;

[0152] In response to determining that the lower right corner of the target bounding box is within the vehicle's warning zone, the target intrusion warning zone is determined.

[0153] Furthermore, the detection module 703 is also specifically used for:

[0154] In response to determining that the center point of the target bounding box is located in the preset area on the right side of the monitoring image, it is determined whether the lower left corner of the target bounding box is within the vehicle's warning area;

[0155] In response to determining that the lower left corner of the target bounding box is within the vehicle's warning zone, the target intrusion warning zone is determined.

[0156] Furthermore, the detection module 703 is also specifically used for:

[0157] Extract the coordinates of the bottom left corner of the target bounding box;

[0158] Compare the coordinates of the lower left corner with the boundary coordinates of the warning area;

[0159] In response to determining that the coordinates of the lower left corner of the target bounding box are within the boundary coordinates of the warning area, the lower left corner of the target bounding box is determined to be within the vehicle's warning area.

[0160] Furthermore, the detection module 703 is also specifically used for:

[0161] Determine the relative distance between the target and the vehicle;

[0162] In response to determining that the relative distance is less than or equal to a preset distance, the target intrusion warning zone is determined.

[0163] Furthermore, the detection module 703 is also specifically used for:

[0164] In response to determining that the relative distance is greater than a preset distance, it is determined that the target has not intruded into the warning area.

[0165] Furthermore, the detection module 703 is also specifically used for:

[0166] In response to target detection, determine the area of ​​the target bounding box;

[0167] In response to determining that the area is less than or equal to a preset area, the relative distance between the target and the vehicle is determined; in response to determining that the relative distance is less than or equal to a preset distance, the target intrusion warning zone is determined.

[0168] Furthermore, the judgment module 702 is also specifically used for:

[0169] By determining the location of the center point of the target bounding box, at least one target region is identified.

[0170] Furthermore, the acquisition module 701 is also specifically used for:

[0171] After acquiring monitoring images outside the vehicle, the process also includes a preprocessing procedure for the monitoring images, which includes at least one of the following: image denoising, brightness adjustment, and contrast enhancement.

[0172] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing this application, the functions of each module can be implemented in one or more software and / or hardware.

[0173] The apparatus of the above embodiments is used to implement the corresponding vehicle control method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0174] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle control method of any of the above embodiments.

[0175] Figure 12 shows a more specific hardware structure diagram of an electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0176] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0177] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0178] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0179] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0180] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0181] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0182] The electronic devices described above are used to implement the corresponding vehicle control methods in any of the foregoing embodiments and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0183] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides a non-transitory computer-readable storage medium that stores computer instructions for causing a computer to execute the vehicle control method of any of the above embodiments.

[0184] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0185] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the vehicle control method of any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0186] Based on the same concept, corresponding to any of the above embodiments, this application also provides a computer program product, including computer program instructions, which, when run on a computer, cause the computer to perform the method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0187] It is understood that before using the technical solutions of the various embodiments in this disclosure, users will be informed of the type, scope of use, and usage scenarios of the personal information involved in an appropriate manner, and user authorization will be obtained.

[0188] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose, based on the prompt message, whether to provide personal information to the software or hardware such as electronic devices, applications, servers, or storage media performing the operations of this disclosed technical solution.

[0189] As an optional but not limited implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0190] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0191] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application is limited to these examples; under the concept of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in detail for the sake of brevity.

[0192] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0193] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0194] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the claims of this application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.

Claims

1. A vehicle control method, characterized in that, The vehicle's rearview mirror is equipped with a camera to capture monitoring images outside the vehicle, the monitoring images including a warning area; the method includes: Obtain distortion information of the monitoring image, determine multiple target regions with different distortion degrees in the monitoring image based on the distortion information, and perform target detection on the monitoring image; In response to the detection of a target, at least one target region is determined where the target is located; Based on the target area where the target is located, the relative position between the target and the vehicle is determined to determine whether the target has intruded into the warning area; The warning zone is used to determine whether the target poses a safety threat to the vehicle.

2. The vehicle control method according to claim 1, characterized in that, In response to determining that the target area is a region in the monitored image where the area of ​​distorted image is less than or equal to a preset percentage, the step of determining the relative position of the target and the vehicle based on the target area where the target is located, to determine whether the target has intruded into the warning area, includes: Whether the target has intruded into the warning area is determined based on the position of the lower left / right corner of the target's bounding box relative to the vehicle's warning area; or, Whether the target has intruded into the warning area is determined based on the position of the lower left / right corner and the lower boundary of the target's bounding box relative to the vehicle's warning area; or, Whether the target has intruded into the warning area is determined based on the position of the lower boundary of the target's bounding box relative to the vehicle's warning area.

3. The vehicle control method according to claim 2, characterized in that, The step of determining whether the target has intruded into the warning area based on the position of the lower left / right corner and the lower boundary of the target's bounding box relative to the vehicle's warning area includes: In response to determining the warning area of ​​the lower left / right corner of the target bounding box where no intruding vehicle is located, it is determined whether the lower boundary of the target bounding box intersects with both the upper and lower boundaries of the warning area simultaneously. In response to determining that the lower boundary of the target bounding box intersects with both the upper and lower boundaries of the warning area, the target intrusion warning area is determined.

4. The vehicle control method according to claim 2, characterized in that, The monitoring image includes a preset central region; determining whether the target has intruded into the warning area based on the position of the lower boundary of the target's bounding box relative to the vehicle's warning area includes: In response to determining that the center point of the target bounding box is located in the middle preset area of ​​the monitoring image, the folding state of the vehicle's rearview mirror is determined when acquiring the monitoring image outside the vehicle. In response to determining that the rearview mirror is in an open state, it is determined whether the center segment of the lower boundary of the target bounding box is within the warning area of ​​the vehicle; In response to determining that the lower boundary center segment of the target bounding box is within the vehicle's warning zone, the target intrusion warning zone is determined.

5. The vehicle control method according to claim 4, characterized in that, When the rearview mirror is in the open position, determining that the lower boundary center segment of the target bounding box is within the vehicle's warning zone includes: Extract the coordinate values ​​of all points in the lower boundary center segment of the target bounding box; In response to determining that the coordinates of any point on the lower boundary center segment are within the warning area, the lower boundary center segment of the target bounding box is determined to be within the warning area of ​​the vehicle.

6. The vehicle control method according to claim 2, characterized in that, The monitoring image includes a preset area on the left and a preset area on the right; determining whether the target has intruded into the warning area based on the position of the lower left / right corner of the target's bounding box relative to the vehicle's warning area includes: In response to determining that the center point of the target bounding box is located in the preset area on the left side of the monitoring image, it is determined whether the lower right corner of the target bounding box is within the warning area of ​​the vehicle; In response to determining that the lower right corner of the target bounding box is within the vehicle's warning area, the target intrusion warning area is determined.

7. The vehicle control method according to claim 2, characterized in that, The monitoring image includes a preset area on the left and a preset area on the right; determining whether the target has intruded into the warning area based on the position of the lower left / right corner of the target's bounding box relative to the vehicle's warning area includes: In response to determining that the center point of the target bounding box is located in the preset area on the right side of the monitoring image, it is determined whether the lower left corner of the target bounding box is within the warning area of ​​the vehicle; In response to determining that the lower left corner of the target bounding box is within the vehicle's warning area, the target intrusion warning area is determined.

8. The vehicle control method according to claim 7, characterized in that, Determining that the lower left corner of the target bounding box is within the vehicle's warning zone includes: Extract the coordinates of the lower left corner of the target bounding box; Compare the coordinates of the lower left corner with the boundary coordinates of the warning area; In response to determining that the coordinates of the lower left corner of the target bounding box are within the boundary coordinate range of the warning area, it is determined that the lower left corner of the target bounding box is within the warning area of ​​the vehicle.

9. The vehicle control method according to claim 2, characterized in that, In response to determining that the target area is a region in the monitored image where the proportion of distorted image area is greater than a preset proportion, the step of determining the relative position of the target and the vehicle based on the target area where the target is located, in order to determine whether the target has intruded into the warning area, includes: Determine the relative distance between the target and the vehicle; In response to determining that the relative distance is less than or equal to a preset distance, it is determined that the target has intruded into the warning area.

10. The vehicle control method according to claim 2, characterized in that, In response to determining that the target area is a region in the monitored image where the proportion of distorted image area is greater than a preset proportion, the step of determining the relative position of the target and the vehicle based on the target area where the target is located, in order to determine whether the target has intruded into the warning area, includes: Determine the relative distance between the target and the vehicle; In response to determining that the relative distance is less than or equal to a preset distance, it is determined that the target has intruded into the warning area.

11. The vehicle control method according to claim 1, characterized in that, The method further includes: In response to target detection, determine the area of ​​the target bounding box; In response to determining that the area is less than or equal to a preset area, the relative distance between the target and the vehicle is determined; in response to determining that the relative distance is less than or equal to a preset distance, the target is determined to have intruded into the warning area.

12. The vehicle control method according to claim 1, characterized in that, The determination of at least one target area where the target is located includes: By determining the location of the center point of the target bounding box, at least one target region in which the target is located is determined.

13. The vehicle control method according to claim 1, characterized in that, After acquiring monitoring images outside the vehicle, the process also includes a preprocessing procedure for the monitoring images, which includes at least one of image denoising, brightness adjustment, and contrast enhancement.

14. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 13.

15. A vehicle, characterized in that, The vehicle includes the electronic equipment as described in claim 14.

Images