Risk control method and device based on streaming media rearview mirror, controller and vehicle

Abstract

Embodiments of the present application provide a risk control method and device based on a streaming rearview mirror, a controller and a vehicle. The method is applied to a controller of a vehicle, the vehicle is configured with a streaming rearview mirror, and the streaming rearview mirror includes a physical mirror display mode and a screen display mode; the physical mirror display mode is a default starting mode; the method includes: acquiring real-time rear vehicle information of the vehicle; when it is determined that there is a target vehicle according to the rear vehicle information, controlling the streaming rearview mirror to switch from the physical mirror display mode to the screen display mode; wherein the target vehicle is a rear vehicle that has entered or will enter a display blind area of the physical mirror display mode within a preset time; the screen display mode is used to display an image of a rear area of the vehicle including the display blind area. The method is used to effectively utilize the streaming rearview mirror to improve the driving safety level while taking into account the energy consumption of the whole vehicle.

Description

Technical Field

[0001] This application relates to the field of vehicle control, and more particularly to a method, device, controller, and vehicle for hazard avoidance control based on a streaming media rearview mirror. Background Technology

[0002] With the rapid development of modern intelligent driving technology, lane changing and blind spot monitoring have become core requirements for ensuring driving safety. During driving, drivers need to frequently check rear traffic conditions through their rearview mirrors to complete lane changing maneuvers.

[0003] Traditional rearview mirrors have a fixed blind spot due to their physical reflection angle. When a vehicle enters this blind spot, the driver cannot directly observe it through the mirror. Currently, the application of streaming rearview mirrors effectively solves this problem: when in screen display mode, the streaming rearview mirror can directly show the driver images of the blind spot that are not visible through a physical mirror.

[0004] However, most current streaming rearview mirrors require the driver to manually activate the screen display mode. If the driver forgets to activate the screen display mode, the driver will not be able to observe the blind spot road conditions through the rearview mirror. If the screen display mode is kept on for a long time, it will continuously consume the vehicle's power and increase the overall vehicle energy consumption. Summary of the Invention

[0005] This application provides a method, device, controller, and vehicle for hazard avoidance control based on a streaming media rearview mirror, which aims to improve driving safety while taking into account the energy consumption of the entire vehicle.

[0006] In a first aspect, embodiments of this application provide a hazard avoidance control method based on a streaming media rearview mirror, applied to a vehicle controller, wherein the vehicle is equipped with a streaming media rearview mirror; the streaming media rearview mirror includes a physical mirror display mode and a screen display mode; the physical mirror display mode is a default startup mode; the method includes:

[0007] Real-time acquisition of information about vehicles behind the vehicle;

[0008] When a target vehicle is determined based on the information of the vehicles behind, the streaming media rearview mirror is controlled to switch from the physical mirror display mode to the screen display mode.

[0009] The target vehicle is a vehicle that has entered or has entered the blind spot of the physical mirror display mode within a preset time; the screen display mode is used to display an image of the area behind the vehicle, including the blind spot.

[0010] In one possible implementation, determining the presence of a target vehicle based on the rear vehicle information includes:

[0011] The information about the vehicles behind is input into a pre-trained self-learning model, which is used to predict the driving trend of each vehicle behind included in the information about the vehicles behind.

[0012] The vehicle that indicates a driving trend of entering the display blind spot within a preset time from the output of the self-learning model is identified as the target vehicle.

[0013] In one possible implementation, the method further includes:

[0014] Based on the information about the vehicles behind, determine whether there is a driving risk within the blind spot.

[0015] When a driving risk is determined to exist within the blind spot, the driver is given a risk warning based on the information of the vehicles behind, using the screen display mode of the streaming media rearview mirror.

[0016] In one possible implementation, the risk warning includes at least one of the following: the type of driving risk scenario, the severity of the risk, and recommended risk avoidance measures.

[0017] In one possible implementation, the method further includes:

[0018] Based on the information about the vehicles behind, determine the estimated time of occurrence of the accident that poses the driving risk;

[0019] Based on the predicted time of the accident, determine whether the driving risk is a sudden risk;

[0020] If the driving risk is an unexpected risk, take over the vehicle to control it to perform evasive maneuvers;

[0021] If the driving risk is not an unexpected risk, then when the driver takes the recommended avoidance measures, the driver's driving operation parameters and system configuration parameters will be adjusted accordingly.

[0022] In one possible implementation, the rear vehicle information includes the distance between the vehicle and each rear vehicle, the relative speed, the estimated collision time and azimuth angle, and the rear image data of the vehicle.

[0023] In one possible implementation, the method further includes:

[0024] The association information between the vehicle and the target vehicle is displayed on the streaming rearview mirror;

[0025] The associated information includes at least one of the following: the distance between the vehicle and the target vehicle, their relative speed, and the estimated collision time.

[0026] In one possible implementation, the method further includes:

[0027] When the duration for which no target vehicle is behind the vehicle exceeds a preset duration, the streaming media rearview mirror is controlled to switch from the screen display mode back to the physical mirror display mode.

[0028] Secondly, embodiments of this application provide a hazard avoidance control device based on a streaming media rearview mirror, the device comprising:

[0029] The acquisition module is used to acquire information about vehicles behind the vehicle in real time.

[0030] The first control module is used to control the vehicle's streaming rearview mirror to switch from the physical mirror display mode to the screen display mode when a target vehicle is determined to be present based on the rear vehicle information; the physical mirror display mode is the default startup mode.

[0031] The target vehicle is a vehicle that has entered or has entered the blind spot of the physical mirror display mode within a preset time; the screen display mode is used to display an image of the area behind the vehicle, including the blind spot.

[0032] In one possible implementation, the first control module is specifically used for:

[0033] The information about the vehicles behind is input into a pre-trained self-learning model, which is used to predict the driving trend of each vehicle behind included in the information about the vehicles behind.

[0034] The vehicle that indicates a driving trend of entering the display blind spot within a preset time from the output of the self-learning model is identified as the target vehicle.

[0035] In one possible implementation, the device further includes:

[0036] The first determining module is used to determine whether there is a driving risk within the display blind spot based on the information of the vehicles behind;

[0037] The alert module is used to alert the driver of the driving risk by means of the screen display mode of the streaming media rearview mirror, based on the information of the vehicles behind, when the driving risk is determined to exist in the blind spot.

[0038] In one possible implementation, the risk warning includes at least one of the following: the type of driving risk scenario, the severity of the risk, and recommended risk avoidance measures.

[0039] In one possible implementation, the device further includes:

[0040] The second determining module is used to determine the expected time of the accident of the driving risk based on the information of the vehicles behind;

[0041] The third determining module is used to determine whether the driving risk is a sudden risk based on the expected time of the accident.

[0042] The control module is used to take over the vehicle to control the vehicle to perform avoidance operations if the driving risk is a sudden risk.

[0043] If the driving risk is not an unexpected risk, then when the driver takes the recommended avoidance measures, the driver's driving operation parameters and system configuration parameters will be adjusted accordingly.

[0044] In one possible implementation, the rear vehicle information includes the distance between the vehicle and each rear vehicle, the relative speed, the estimated collision time and azimuth angle, and the rear image data of the vehicle.

[0045] In one possible implementation, the device further includes:

[0046] The display module is used to display the association information between the vehicle and the target vehicle on the streaming media rearview mirror;

[0047] The associated information includes at least one of the following: the distance between the vehicle and the target vehicle, their relative speed, and the estimated collision time.

[0048] In one possible implementation, the device further includes:

[0049] The third control module is used to control the streaming media rearview mirror to switch from the screen display mode back to the physical mirror display mode when the duration for which there is no target vehicle behind the vehicle exceeds a preset duration.

[0050] Thirdly, embodiments of this application provide a controller, including: a memory and a processor;

[0051] The memory stores computer-executed instructions;

[0052] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0053] Fourthly, embodiments of this application provide a vehicle, including a vehicle body, a streaming media rearview mirror, and the controller described in the third aspect;

[0054] The streaming media rearview mirror includes a physical mirror display mode and a screen display mode; the physical mirror display mode is the default startup mode; the screen display mode is used to display an image of the area behind the vehicle, including the blind spot of the physical mirror display mode.

[0055] Fifthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0056] Sixthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0057] The hazard avoidance control method, device, controller, and vehicle based on streaming media rearview mirror provided in this application embodiment acquires real-time information about vehicles behind the vehicle. When it is determined that a target vehicle has entered or will enter the blind spot of the physical mirror display mode within a preset time, the streaming media rearview mirror is controlled to switch from the physical mirror display mode to a screen display mode for displaying images of the area behind the vehicle, including the blind spot. This allows for timely adjustment of the rearview information presentation method in response to changes in the relationship between the rear vehicle and the blind spot, improving the flexibility of the streaming media rearview mirror's display mode switching. As a result, it achieves the effect of effectively utilizing the streaming media rearview mirror to improve driving safety while also considering the energy consumption of the entire vehicle. Attached Figure Description

[0058] 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.

[0059] Figure 1 A flowchart illustrating a risk avoidance control method based on a streaming media rearview mirror, provided in Embodiment 1 of this application;

[0060] Figure 2 This is a schematic diagram of the display of the streaming media rearview mirror provided in Embodiment 1 of this application;

[0061] Figure 3 This is a flowchart illustrating a risk avoidance control method based on a streaming media rearview mirror, provided in Embodiment 3 of this application.

[0062] Figure 4 A schematic diagram of a safety control device based on a streaming media rearview mirror provided in Embodiment 4 of this application;

[0063] Figure 5A schematic diagram of a safety control device based on a streaming media rearview mirror provided in Embodiment 5 of this application;

[0064] Figure 6 This is a schematic diagram of the structure of a controller provided in Embodiment Six of this application.

[0065] The accompanying drawings illustrate 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 particular embodiments. Detailed Implementation

[0066] 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.

[0067] Regarding the aforementioned background technology, the inventors considered setting the physical mirror display mode of the streaming rearview mirror as the default startup mode and proposed switching the display mode to screen display mode only when a vehicle behind is detected entering the blind spot of the vehicle's physical mirror, thus providing the driver with a real-time view of the blind spot. Alternatively, considering that activating the screen display after a vehicle has entered the blind spot leaves the driver with limited time to react and still poses a certain safety risk, the inventors also proposed switching the display mode to screen display mode when a vehicle is detected entering the blind spot of the vehicle's physical mirror within a preset time, thereby achieving the purpose of presenting the blind spot image in advance. In summary, both of the above solutions proposed by the inventors can eliminate the limitation of manual start-stop, achieving control of device power consumption while ensuring driving safety.

[0068] It should be noted that the hazard avoidance control method based on streaming media rearview mirror provided in this application can be executed by a controller in the vehicle. Specifically, the controller can be a body controller, or a driver assistance domain controller, blind spot monitoring controller, etc. This application does not limit the specific subject that executes the method.

[0069] 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 now be described with reference to the accompanying drawings.

[0070] Figure 1 This is a flowchart illustrating a hazard avoidance control method based on a streaming media rearview mirror, provided in Embodiment 1 of this application. In this embodiment, the vehicle to which the method is applied needs to be equipped with a streaming media rearview mirror, and the physical mirror display mode of the streaming media rearview mirror is the default startup mode (i.e., after the vehicle is started, the display mode of the streaming media rearview mirror is the physical mirror display mode). Figure 1 As shown, the method provided in Embodiment 1 of this application includes:

[0071] S101: Real-time acquisition of information about vehicles behind the vehicle.

[0072] In this step, after the vehicle is powered on, the controller needs to acquire real-time information about vehicles behind the vehicle to provide a data basis for monitoring the situation of vehicles behind. This information refers to the information of vehicles whose vehicles are behind the vehicle, including their spatial position and motion status.

[0073] In practical applications, after the vehicle is powered on, the controller initiates the blind spot avoidance control task and collects the above-mentioned information about vehicles behind the vehicle through the vehicle's sensor devices (such as rear-view camera, millimeter-wave radar, ultrasonic sensor, side rear-angle radar, etc.) at preset intervals.

[0074] In one possible implementation, the rear vehicle information in this application includes the distance, relative speed, estimated time to collision (TTC), and azimuth angle between the vehicle and each rear vehicle, as well as rear image data of the vehicle. The azimuth angle refers to the horizontal angle formed by the rear vehicle relative to the longitudinal centerline (the longitudinal axis of the vehicle's reference coordinate system) within the vehicle's horizontal plane.

[0075] In practical implementation, distance, relative speed, estimated collision time, and azimuth angle can all be estimated by millimeter-wave radar, visual ranging module, or a fusion of the two. Millimeter-wave radar is suitable for low-light scenarios such as rain, fog, and night, while visual ranging is suitable for providing richer target appearance information. The fusion of the two can reduce the error of a single sensor. The rear image data can be acquired by a wide-angle camera, a fisheye camera, or a multi-camera stitching module.

[0076] Optionally, the rear vehicle information may also include other vehicle information obtained by processing the distance, relative speed, TTC and azimuth angle between the vehicle and each rear vehicle in multiple cycles, as well as the rear image data of the vehicle. For example, the radar azimuth angle at the same moment can be associated and matched with the image feature points to track the changing trend of the azimuth angle and the inter-frame offset trajectory of the feature points within multiple frames of data, and calculate the driving direction of the rear vehicle. The driving direction can reflect the changing trend of the vehicle's lateral displacement.

[0077] By using the above data as information about vehicles behind, the controller can simultaneously grasp the spatial position, movement trend, and visual scene of the target behind, thereby improving the accuracy of target vehicle judgment. Since distance, relative speed, and estimated collision time reflect dynamic approach relationships, and azimuth angle reflects the lateral orientation and lateral displacement trend of the vehicle behind relative to the vehicle itself, rear image data can provide intuitive verification. Furthermore, it is worth noting that this information combination can provide a reliable basis for subsequent rearview mirror display mode switching.

[0078] S102: When a target vehicle is identified based on the information of vehicles behind, the streaming media rearview mirror is switched from physical mirror display mode to screen display mode.

[0079] It should be noted that in the implementation of this solution, the streaming rearview mirror includes a physical mirror display mode and a screen display mode, with the physical mirror display mode being the default startup mode. This streaming rearview mirror can be the vehicle's left, right, or center rearview mirror.

[0080] In detail, the physical mirror display mode refers to a display mode that presents the rear view based on the principle of optical reflection; the screen display mode refers to a display mode that uses a camera unit to capture image data of the blind spots, including those in the physical mirror display mode, and outputs the image to the display screen built into the streaming media rearview mirror. By making the physical mirror display mode the default startup mode, the power consumption caused by prolonged screen operation can be reduced, while also conforming to the traditional usage habits of drivers.

[0081] In this step, the target vehicle is the key object for triggering the display mode switch. The controller needs to determine in real time whether the target vehicle is behind the vehicle based on the rear vehicle information, and when the presence of the target vehicle is confirmed, control the streaming rearview mirror to switch from physical mirror display mode to screen display mode, so that the streaming camera can display the image of the area behind the vehicle to the driver through the built-in display screen.

[0082] The image of the area behind the vehicle includes the blind spot of the physical mirror display mode. The blind spot refers to the area behind the vehicle that the driver cannot directly observe through the physical mirror due to the limitations of the physical structure and optical reflection angle of the mirror.

[0083] In some implementations, the target vehicle is the vehicle behind that has entered the blind spot of the physical mirror display mode. In other words, it can detect in real time whether there is a target vehicle behind the vehicle that has entered the display blind spot, and when a target vehicle that has entered the display blind spot is detected, it controls the streaming media rearview mirror to switch from physical mirror display mode to screen display mode.

[0084] For example, based on the information of vehicles behind, the relative spatial area of ​​each vehicle behind can be analyzed, and vehicles whose relative spatial area overlaps with the pre-defined blind spot of this vehicle can be identified as target vehicles. Here, the relative spatial area refers to the spatial range calculated by using the vehicle's body reference coordinate system as the calculation reference and combining the physical contours and dimensions of the vehicles behind; the blind spot can be pre-defined based on the installation angle, mirror size, and vehicle attitude parameters of the rearview mirrors, and its area is also established under the body reference coordinate system.

[0085] Furthermore, in some implementations, the target vehicle is a vehicle that enters the blind spot of the physical mirror display mode within a preset time. That is, it can detect in real time whether there is a target vehicle that is expected to enter the blind spot within the preset time, based on information about vehicles behind. When a target vehicle is detected that is expected to enter the blind spot, the streaming rearview mirror is controlled to switch from physical mirror display mode to screen display mode. The preset time can be determined and calibrated according to the actual application; this application does not impose any restrictions on it, such as 0.5s, 1s, etc.

[0086] For example, the controller can, for each vehicle behind, make a preliminary estimate of the future position area of ​​the vehicle behind within a preset time using a linear motion algorithm (such as a uniform speed model) based on the longitudinal distance and relative speed of the vehicle behind in the vehicle information, and correct the position area using the lateral displacement change trend of the vehicle behind, so as to obtain the target position area. When the target position area falls within the display blind zone range pre-calibrated by the vehicle, it is identified as the target vehicle.

[0087] As another example, the controller may also pre-calibrate the adjacent edge area outside the display blind spot, and when it is determined that a vehicle behind has entered the adjacent edge area, identify the vehicle behind as the target vehicle. The method for determining whether a vehicle behind has entered the adjacent edge area can refer to the method for determining whether a vehicle behind has entered the display blind spot in the aforementioned implementation, or it can be implemented through a pre-trained model (such as a neural network model).

[0088] This implementation predicts the driving trends of vehicles behind the driver to enable advance switching of the display mode, providing the driver with real-time images of blind spots and giving the driver ample time for observation and operation, thereby further improving driving safety.

[0089] In addition, in practical applications, once the streaming rearview mirror is switched to screen display mode, the controller can call the image stream collected by the wide-angle rear camera (such as a camera installed near the license plate on the rear side of the vehicle) or the electronic rearview module. After distortion correction, brightness compensation, dynamic range enhancement and cropping and splicing, a visual image covering the blind spot area of ​​the physical mirror is generated, and the streaming rearview mirror is driven to output through its built-in display screen.

[0090] In some applications, physical mirror display modes can be further divided into single physical mirror display modes and screen-integrated physical mirror display modes. The single physical mirror display mode refers to a mode that relies solely on the physical mirror of the streaming rearview mirror to present the rear view through optical reflection. The screen-integrated physical mirror display mode refers to an augmented reality-based fusion display mode, specifically enhancing the reflective visibility of the physical mirror by combining image display with physical optical reflection. For example, a camera can capture the view that drivers and passengers can see from the physical rearview mirror, and the captured rear image can be cropped and adapted accordingly, thereby using the camera-captured image to enhance the field of view and sharpness of the physical mirror reflection. In specific applications, the single physical mirror display mode and the screen-integrated physical mirror display mode can be freely switched based on driving environmental conditions (such as lighting data, weather data), and this application does not impose specific restrictions on the mode switching methods between the sub-modes of the physical mirror display mode.

[0091] Figure 2 This is a schematic diagram of the display of a streaming media rearview mirror provided in Embodiment 1 of this application; as shown Figure 2 As shown, 01 represents the display interface of the streaming rearview mirror, 02 represents the vehicle behind, and 03 represents the vehicle itself. (a) is a schematic diagram of the display screen of the streaming rearview mirror in the physical mirror display mode. It can be seen that in this mode, most of the vehicle body of the vehicle behind cannot be displayed in the rearview mirror. (b) is a schematic diagram of the display screen of the streaming rearview mirror in the screen display mode. It can be seen that in this mode, the vehicle behind that is in the blind spot can be fully displayed in the rearview mirror.

[0092] Understandably, in practical applications, the left, right, and center rearview mirrors of a vehicle can all be configured with streaming media rearview mirrors. Combining the installation location, original physical field of view boundaries, and monitoring range of each rearview mirror, the blind spots of the entire vehicle are divided into zones, and the calibration and parameter storage for each rearview mirror's dedicated blind spot are completed offline. After the vehicle is powered on, the controller can obtain real-time information about vehicles behind the vehicle. For each rearview mirror, when it is determined that there is a target vehicle in the mirror, it controls the mirror to switch from physical mirror display mode to screen display mode. The target vehicle is a vehicle that has entered or has entered the blind spot of the mirror's physical mirror display mode within a preset time.

[0093] In addition, optionally, to further save device power consumption, the controller can also make timing judgments based on the information of vehicles behind: when the continuous duration of no target vehicle behind the vehicle exceeds the preset duration, the controller controls the streaming media rearview mirror to switch from screen display mode back to physical mirror display mode.

[0094] The preset duration can be determined based on the vehicle's requirements for energy efficiency and safety, or it can be dynamically determined based on the vehicle's speed. This application does not impose specific limitations on this. For example, the preset duration could be 10s, 15s, or 18s.

[0095] The hazard avoidance control method based on streaming media rearview mirror provided in this application embodiment acquires real-time information about vehicles behind the vehicle. When it is determined that a target vehicle has entered or will enter the blind spot of the physical mirror display mode within a preset time, the streaming media rearview mirror is controlled to switch from the physical mirror display mode to a screen display mode for displaying images of the area behind the vehicle, including the blind spot. This allows for timely adjustment of the presentation of rearview information based on changes in the relationship between the rear vehicle and the blind spot, improving the flexibility of the streaming media rearview mirror's display mode switching. As a result, the method effectively utilizes the streaming media rearview mirror to improve driving safety while also considering the energy consumption of the entire vehicle.

[0096] Furthermore, Embodiment 2 of this application provides a risk avoidance control method based on a streaming media rearview mirror. Building upon the above embodiments, and specifically addressing the scheme of targeting vehicles entering the blind spot within a preset time frame as the target vehicle, this application will further explain the implementation of "determining the presence of a target vehicle based on rear vehicle information" in step S102, including the following steps 2.1 to 2.2:

[0097] Step 2.1: Input the information of vehicles behind into the pre-trained self-learning model. The self-learning model is used to predict the driving trend of each vehicle behind included in the information of vehicles behind.

[0098] Step 2.2: Identify the vehicles that drive into the blind spot within a preset time in the output of the first self-learning model as the target vehicles.

[0099] In the two steps described above, the self-learning model can be used to predict the relative spatial areas that a vehicle behind can reach at various future times. Correspondingly, the controller can identify vehicles behind whose relative spatial areas overlap with the vehicle's blind spot within a preset time period as target vehicles. Alternatively, the self-learning model can also be used to predict whether a vehicle behind will enter the vehicle's blind spot within a preset time period and directly output the determination result. Correspondingly, the controller can directly indicate the vehicles behind that will enter the vehicle's blind spot within a preset time period as target vehicles.

[0100] It should be noted that the "preset time" in this step should be the same as the "preset time" defined in step S102 of Embodiment 1, so that the target vehicle can be directly identified based on the model output results.

[0101] As a specific example, the self-learning model can be constructed using a neural network model and / or a time-series prediction model, and trained on labeled blind-spot entry samples and normal samples, so that it can directly output the judgment result of whether each rear vehicle has entered the display blind spot of the vehicle within a subsequent preset time based on the real-time input rear vehicle information.

[0102] Among them, the blind spot entry sample refers to the marked historical vehicle operation sample that will enter the blind spot of this vehicle within a preset time; the normal sample refers to the marked historical vehicle operation sample that will not enter the blind spot of this vehicle within a preset time, such as when following the vehicle normally or leaving the lane.

[0103] In practical implementation, after collecting information about vehicles behind the vehicle, the controller organizes it into a data tensor that matches the input format of the self-learning model and feeds it into the model for inference. This model can employ a neural network structure jointly trained based on image features and motion features. It extracts vehicle position features from the rear image through a convolutional network, and then combines this with a temporal network or regression module to analyze vehicle driving trends, thereby outputting a confidence level or prediction label indicating whether each rear vehicle will enter the blind spot of the vehicle within a preset time period. The controller filters out target vehicles based on the model's output and uses them as the trigger for switching the streaming rearview mirror display mode. In practical applications, this model can also be continuously updated by incorporating historical rear vehicle information to continuously improve recognition accuracy; this embodiment does not limit this aspect.

[0104] The hazard avoidance control method based on streaming media rearview mirror provided in this application no longer relies solely on whether a rear vehicle has entered the blind spot for triggering. Instead, it determines the target vehicle based on trend prediction within a preset time period, providing a basis for activating the screen display mode in advance. Therefore, it can improve the foresight and timeliness of blind spot warnings and reduce the observation lag caused by a rear vehicle suddenly entering the blind spot. At the same time, the judgment method based on the self-learning model can be continuously optimized as the training samples increase, reducing missed detections and false judgments caused by simple threshold judgments, thereby improving the reliability and applicability of hazard avoidance control.

[0105] Furthermore, Figure 3 This is a flowchart illustrating a risk avoidance control method based on a streaming media rearview mirror, as provided in Embodiment 3 of this application. Figure 3 As shown, based on the above embodiments, the method provided in this application further includes the following:

[0106] S201: Based on information about vehicles behind, determine whether there is a driving risk within the blind spot.

[0107] In this step, the controller can also determine in real time whether there is a driving risk within the blind spot based on information about vehicles behind. Driving risk describes the potential risk state within the blind spot that could affect driving safety, and its determination can be based on information such as the distance between the vehicle behind and the vehicle, relative speed, TTC (Total Traffic Control), and the trend of lateral displacement changes of the vehicle.

[0108] In its implementation, after receiving information about vehicles behind, the controller first performs a fusion analysis of the distance, speed, azimuth angle, and trajectory changes of the vehicles behind to determine whether there is a driving risk within the vehicle's blind spot. For example, if there is a vehicle behind in the blind spot with a TTC (Time To Call) below a preset time threshold, the controller can determine that there is a driving risk in that blind spot. Similarly, if the vehicle in front is preparing to change lanes, a vehicle behind is rapidly approaching, or the lateral distance between the vehicle behind and the vehicle is less than a preset safe distance, the controller can determine that there is a driving risk within the blind spot.

[0109] S202: When a driving risk is determined to exist in the blind spot, the driver is given a risk warning through the screen display mode of the streaming rearview mirror based on the information of vehicles behind.

[0110] In this step, when the controller determines that there is a driving risk within the blind spot, it will provide a risk warning to the driver through the screen display mode of the streaming rearview mirror. This risk warning refers to the driver outputting a reminder message, the content of which can be presented through icons, text, highlighted colors, or audio-visual linkage on the streaming rearview mirror screen display mode, so that the driver can promptly identify dangerous situations behind them.

[0111] In one possible implementation, the risk warning includes at least one of the following: the type of driving risk scenario, the severity of the risk, and recommended risk avoidance measures.

[0112] Among them, the risk scenario type is used to characterize the specific situation corresponding to the driving risk in the blind spot, which can help drivers quickly identify the source of the risk; the risk severity is used to characterize the danger level of the driving risk, indicating the strength of the current risk's impact on the safety of changing lanes, merging, or following other vehicles; the recommended avoidance measures are used to output operational suggestions that match the identified risks, so that drivers can take timely avoidance actions such as slowing down, keeping the lane, suspending lane changes, or observing vehicles behind them based on the prompts.

[0113] The aforementioned risk scenario types, risk severity, and recommended risk avoidance measures can be output individually or in combination. The specific output content is generated by the controller based on the information of vehicles behind and the risk assessment results, and presented to the driver through the screen display mode of the streaming media rearview mirror.

[0114] In its implementation, after determining that a driving risk exists within the blind spot, the controller comprehensively analyzes the information of vehicles behind, mapping the analysis results to preset risk scenario types, such as a vehicle rapidly approaching from behind, a vehicle behind being in the side / rear blind spot, a vehicle behind preparing to overtake, or a vehicle behind colliding with the driver in lane-changing conflict. Simultaneously, the controller categorizes the risks and outputs the corresponding risk severity using text, icons, colors, or combinations of information, allowing the driver to intuitively distinguish between general warnings, higher-risk warnings, and emergency risk warnings. For recommended avoidance measures, the controller can generate corresponding avoidance suggestions based on the risk scenario type and risk severity, displaying them in the rear view interface in screen display mode, thus providing clear operational guidance without increasing the driver's additional judgment burden.

[0115] In this solution, risk warning information is displayed synchronously with the rear view image, and the warning content can be dynamically updated based on the risk status. When the movement of vehicles behind changes, the controller reassesses the risk scenario type and severity, and adjusts the displayed content of recommended avoidance measures to ensure that the warning information always matches the current blind spot risk. This approach allows drivers to obtain clear risk semantic information while observing the rear view image, thereby improving the efficiency of identifying blind spot risks in complex road environments and the timeliness of avoidance responses.

[0116] Optionally, during the notification process, different notification intensities can be switched according to the risk level, allowing drivers to quickly perceive risks while maintaining rear visibility.

[0117] By incorporating at least one of the following into more targeted prompts—risk scenario type, risk severity, and recommended risk avoidance measures—the understandability and feasibility of the prompts can be improved, thereby further ensuring driving safety.

[0118] In one possible implementation, the method provided in this application embodiment may further include: displaying the association information between the vehicle and the target vehicle on a streaming rearview mirror; wherein the association information includes at least one of the distance between the vehicle and the target vehicle, the relative speed, and the estimated collision time.

[0119] In this implementation, the correlation information between the target vehicle and the driver can also be displayed synchronously in the streaming rearview mirror, enabling the driver to obtain visual images and risk quantification information in the same observation area at the same time, ensuring the driver's convenience in obtaining information about the blind spot behind.

[0120] In its implementation, after identifying the target vehicle, the controller outputs the corresponding associated information to the display area of ​​the streaming rearview mirror in the form of text, icons, numerical bars, or combined prompts. It then associates the target vehicle with its associated information, allowing the driver to quickly establish the correspondence between the target object and the risk status. For example, the specific display area of ​​the associated information in the streaming rearview mirror can be referenced... Figure 2 The area where "xxx" is located, for example, Figure 2 The “xxx” in the text can include the distance, relative speed, and TTC between the following vehicle 02 and this vehicle 03.

[0121] Distance can be displayed in meters, relative speed in kilometers per hour or meters per second, and estimated collision time in seconds, allowing drivers to intuitively assess changes in risk. In practical applications, this display interface can also adapt and adjust font size, color contrast, and prompt position according to ambient light and vehicle speed; however, this embodiment does not limit these adjustments.

[0122] In addition, in practical applications, the association information between the vehicle and each vehicle behind it can also be displayed in the streaming rearview mirror, but this application does not limit this.

[0123] By synchronously displaying the correlation information between the vehicle and the target vehicle in the streaming rearview mirror, the spatial relationship, motion relationship and risk sequence of the target behind can be directly presented to the driver through the streaming rearview mirror and the image of the vehicle area behind. This allows the driver to directly obtain information, thereby improving the efficiency of identifying vehicles in the blind spot and the timeliness of lane change decisions, while reducing the risk of collisions caused by information dispersion or delayed judgment.

[0124] S203: Based on information about vehicles behind, determine the estimated time of an accident that could cause a traffic risk.

[0125] The estimated time of accident occurrence is used to characterize the point in time when the risk associated with following vehicles may develop into an accident. In this step, the controller can determine the estimated time of accident occurrence of the driving risk based on one or more of the following vehicle information, such as the distance between the following vehicle and the vehicle, relative speed, TTC, and the vehicle's current azimuth angle.

[0126] S204: Determine whether the driving risk is a sudden risk based on the expected time of the accident.

[0127] If the driving risk is an unexpected risk, proceed to step S205; if the driving risk is not an unexpected risk, proceed to step S206.

[0128] Among these, "emergency risk" refers to a high-urgency risk where the expected occurrence time of an accident is short and immediate action is required. In this step, the controller can determine this risk based on a preset accident occurrence time threshold. For example, if the expected accident occurrence time is less than the preset threshold, the driving risk is classified as an emergency risk; if the expected accident occurrence time is greater than or equal to the preset threshold, the driving risk is classified as not an emergency risk.

[0129] S205: Take over the vehicle to control it and perform evasive maneuvers.

[0130] In this context, "taking over the vehicle" refers to the direct intervention of the vehicle controller in steering, braking, or drive control to enable the vehicle to perform evasive maneuvers. These evasive maneuvers may include deceleration, lane keeping, slight lateral correction to the safe side, or emergency braking.

[0131] In practice, when the controller determines that the driving risk is a sudden risk, it will send a linkage command to the braking system, steering actuator and power control unit to take over the vehicle and suppress dangerous lane change or rear-end collision trends according to the risk avoidance strategy calculated based on the current driving conditions or preset.

[0132] S206: When the driver performs evasive action in accordance with the recommended evasive action measures, assist in correcting the driver's driving operation parameters and system configuration parameters.

[0133] Among them, the driver's driving operation parameters are used to characterize control quantities related to driving behavior, such as steering force, braking force, lane change target trajectory, and throttle opening, while the system configuration parameters are used to characterize operating parameters such as vehicle acceleration ratio. The acceleration ratio refers to the increase in vehicle speed corresponding to the same throttle pedal input.

[0134] In this step, when the controller determines that the driving risk is not an emergency risk, it does not directly take over the vehicle. Instead, it adjusts the above parameters based on the information of vehicles behind and the expected time of the accident, so as to assist in correcting the driver's operating intentions.

[0135] In practice, the controller can adjust the driver's driving operation parameters and system configuration parameters based on information about vehicles behind, the expected duration of the accident, and real-time driving conditions. For example, by combining the risk of approaching vehicles behind and the remaining time for avoidance, the acceleration ratio can be increased while the driver keeps the accelerator pedal travel unchanged, thereby improving the vehicle's acceleration capability and helping the vehicle to quickly move away from the risk source behind.

[0136] Optionally, if the initial assessment determines that the driving risk is not an immediate risk, but the driver fails to implement the recommended avoidance measures, the driving risk is upgraded to an immediate risk, and the driver takes over the vehicle to perform avoidance maneuvers. This method balances driver autonomy with driving safety, preventing accidents caused by driver delays.

[0137] Optionally, when it is determined that there is a driving risk in the blind spot, the risk situation of the vehicle (such as risk type, risk level and the avoidance measures to be taken) can also be sent to the following vehicles through communication technology (such as Vehicle to Everything (V2X) technology) to further reduce rear-end collisions caused by emergency braking and other avoidance control.

[0138] Through steps S203 to S206 above, the vehicle can finely distinguish rear risks based on the time dimension and take two types of response methods: automatic takeover and auxiliary correction. This improves the timeliness of handling emergency risks, reduces the probability of collisions, avoids excessive intervention in non-emergency risks, ensures driving continuity, and achieves the effect of improving the adaptability of the controller to avoidance control under different conditions.

[0139] The hazard avoidance control method based on a streaming media rearview mirror provided in this application monitors and displays in real time whether there are driving risks in blind spots. Based on the actual risk situation, the streaming media rearview mirror displays information including the type of driving risk scenario, the severity of the risk, recommended avoidance measures, and related information about vehicles behind, providing a reference for the driver's driving behavior. Furthermore, since the prompts are directly displayed on the screen of the streaming media rearview mirror, the driver does not need to switch to a separate observation terminal to receive relevant prompts while viewing the rear image, thereby improving the recognition efficiency and timeliness of response in blind spot scenarios. In addition, this embodiment also determines the suddenness of driving risks and adopts different blind spot risk response measures accordingly, achieving the effect of improving the adaptability of hazard avoidance control under different operating conditions.

[0140] Figure 4 This is a schematic diagram of the structure of a safety control device based on a streaming media rearview mirror provided in Embodiment 4 of this application, as shown below. Figure 4 As shown, the hazard avoidance control device 30 based on streaming media rearview mirror provided in this embodiment includes:

[0141] The acquisition module 301 is used to acquire real-time information about vehicles behind the vehicle.

[0142] The first control module 302 is used to control the streaming media rearview mirror of the vehicle to switch from physical mirror display mode to screen display mode when the target vehicle is determined to be present based on the vehicle information behind; the physical mirror display mode is the default startup mode.

[0143] The target vehicle is the vehicle behind which has entered or has entered the blind spot of the physical mirror display mode within a preset time; the screen display mode is used to display an image of the area behind the vehicle, including the blind spot.

[0144] The hazard avoidance control device 30 based on streaming media rearview mirror 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.

[0145] Figure 5 This is a schematic diagram of the structure of a safety control device based on a streaming media rearview mirror provided in Embodiment 5 of this application, as shown below. Figure 5 As shown, based on the above embodiments, the hazard avoidance control device 30 based on streaming media rearview mirror provided in this embodiment further includes:

[0146] The first determining module 303 is used to determine whether there is a driving risk in the display blind spot based on the information of the vehicles behind;

[0147] The warning module 304 is used to provide risk warnings to the driver through the screen display mode of the streaming media rearview mirror when it is determined that there is a driving risk in the blind spot.

[0148] The second determining module 305 is used to determine the expected time of occurrence of a traffic accident based on the information of vehicles behind;

[0149] The third determination module 306 is used to determine whether the driving risk is a sudden risk based on the expected time of the accident.

[0150] The second control module 307 is used to take over the vehicle to control the vehicle to perform risk avoidance operations if the driving risk is a sudden risk.

[0151] If the driving risk is not an unexpected risk, then when the driver takes the recommended avoidance measures, the system will assist in correcting the driver's driving operation parameters and system configuration parameters.

[0152] Display module 308 is used to display the association information between the vehicle and the target vehicle on the streaming media rearview mirror;

[0153] The associated information includes at least one of the following: the distance between the vehicle and the target vehicle, their relative speed, and the estimated time of collision.

[0154] The third control module 309 is used to control the streaming media rearview mirror to switch from screen display mode back to physical mirror display mode when the duration for which there is no target vehicle behind the vehicle exceeds a preset duration.

[0155] In one possible implementation, the first control module 302 is specifically used for:

[0156] The information of vehicles behind is input into a pre-trained self-learning model, which is used to predict the driving trend of each vehicle behind included in the information of vehicles behind.

[0157] The vehicle that indicates a driving trend of entering the blind spot within a preset time in the output of the self-learning model is identified as the target vehicle.

[0158] In one possible implementation, the risk warning includes at least one of the following: the type of driving risk scenario, the severity of the risk, and recommended risk avoidance measures.

[0159] In one possible implementation, the rear vehicle information includes the distance between the vehicle and each vehicle behind it, the relative speed, the estimated collision time and azimuth angle, and rear image data of the vehicle.

[0160] The hazard avoidance control device 30 based on streaming media rearview mirror 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.

[0161] Figure 6 This is a schematic diagram of the structure of a controller provided in Embodiment Six of this application. Figure 6 As shown, the controller 40 provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the controller 40 further includes a communication component 403. The processor 401, memory 402, and communication component 403 are connected via a bus 404.

[0162] In a specific implementation, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to perform the above-described method.

[0163] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0164] 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.

[0165] The memory may include read-only memory and random access memory. The memory may be volatile or non-volatile, or may include both. Non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which serves as an external cache. Many forms of RAM are available by way of example, but not limitation. Examples include Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Sync Link DRAM (SLDRAM), and Direct Rambus RAM (DR RAM).

[0166] 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.

[0167] This application also provides a vehicle, including a vehicle body, a streaming rearview mirror, and the aforementioned controller;

[0168] The streaming rearview mirror includes a physical mirror display mode and a screen display mode; the physical mirror display mode is the default startup mode; the screen display mode is used to display images of the area behind the vehicle, including the blind spot displayed in the physical mirror display mode.

[0169] This application also provides a computer program product, including a computer program that, when executed, implements the above-described method.

[0170] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed, implement the above-described method.

[0171] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as SRAM, EEPROM, EPROM, PROM, 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.

[0172] 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 within an ASIC. Alternatively, the processor and the readable storage medium can exist as discrete components in a device.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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, ROM, RAM, magnetic disks, or optical disks.

[0177] 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.

[0178] The above embodiments are merely preferred embodiments provided to fully illustrate the present invention, and the scope of protection of the present invention is not limited thereto. Equivalent substitutions or modifications made by those skilled in the art based on the present invention are all within the scope of protection of the present invention.

[0179] 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 risk avoidance control method based on a streaming media rearview mirror, characterized in that, A controller for use in a vehicle equipped with a streaming rearview mirror; The streaming media rearview mirror includes a physical mirror display mode and a screen display mode; the physical mirror display mode is the default startup mode; the method includes: Real-time acquisition of information about vehicles behind the vehicle; When a target vehicle is determined based on the information of the vehicles behind, the streaming media rearview mirror is controlled to switch from the physical mirror display mode to the screen display mode. The target vehicle is a vehicle that has entered or has entered the blind spot of the physical mirror display mode within a preset time; the screen display mode is used to display an image of the area behind the vehicle, including the blind spot.

2. The method according to claim 1, characterized in that, The step of determining the presence of a target vehicle based on the information of vehicles behind includes: The information about the vehicles behind is input into a pre-trained self-learning model, which is used to predict the driving trend of each vehicle behind included in the information about the vehicles behind. The vehicle that indicates a driving trend of entering the display blind spot within a preset time from the output of the self-learning model is identified as the target vehicle.

3. The method according to claim 1, characterized in that, The method further includes: Based on the information about the vehicles behind, determine whether there is a driving risk within the blind spot. When a driving risk is determined to exist within the blind spot, the driver is given a risk warning based on the information of the vehicles behind, using the screen display mode of the streaming media rearview mirror.

4. The method according to claim 3, characterized in that, The risk warning includes at least one of the following: the type of driving risk scenario, the severity of the risk, and recommended risk avoidance measures.

5. The method according to claim 4, characterized in that, The method further includes: Based on the information about the vehicles behind, determine the estimated time of occurrence of the accident that poses the driving risk; Based on the predicted time of the accident, determine whether the driving risk is a sudden risk; If the driving risk is an unexpected risk, take over the vehicle to control it to perform evasive maneuvers; If the driving risk is not an unexpected risk, then when the driver takes the recommended avoidance measures, the driver's driving operation parameters and system configuration parameters will be adjusted accordingly.

6. The method according to any one of claims 1 to 5, characterized in that, The rear vehicle information includes the distance between the vehicle and each vehicle behind it, the relative speed, the estimated collision time and azimuth angle, and the rear image data of the vehicle.

7. The method according to claim 6, characterized in that, The method further includes: The association information between the vehicle and the target vehicle is displayed on the streaming rearview mirror; The associated information includes at least one of the following: the distance between the vehicle and the target vehicle, their relative speed, and the estimated collision time.

8. The method according to any one of claims 1 to 5, characterized in that, The method further includes: When the duration for which no target vehicle is behind the vehicle exceeds a preset duration, the streaming media rearview mirror is controlled to switch from the screen display mode back to the physical mirror display mode.

9. A hazard avoidance control device based on a streaming media rearview mirror, characterized in that, The device includes: The acquisition module is used to acquire information about vehicles behind the vehicle in real time. The first control module is used to control the vehicle's streaming rearview mirror to switch from the physical mirror display mode to the screen display mode when a target vehicle is determined to be present based on the rear vehicle information; the physical mirror display mode is the default startup mode. The target vehicle is a vehicle that has entered or has entered the blind spot of the physical mirror display mode within a preset time; the screen display mode is used to display an image of the area behind the vehicle, including the blind spot.

10. A controller, 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 1-8.

11. A vehicle, characterized in that, Includes the vehicle body, the streaming rearview mirror, and the controller as described in claim 10; The streaming media rearview mirror includes a physical mirror display mode and a screen display mode; the physical mirror display mode is the default startup mode; the screen display mode is used to display an image of the area behind the vehicle, including the blind spot of the physical mirror display mode.

12. 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 1-8.

13. 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 1-8.

Images