Intelligent electronic rearview mirror self-adaptive adjusting system and method

Abstract

The invention discloses an intelligent electronic rearview mirror self-adaptive adjusting system and method, and belongs to the field of rearview mirror adjustment, and the method comprises the steps: when a reversing mode is started, activating millimeter wave radars to scan the environment on the two sides and behind, obtaining the position and distance of an obstacle, and carrying out the height estimation of the obstacle through the millimeter wave radars and LiDAR; an initial rearview mirror angle is obtained, and adjustment is carried out based on the rearview mirror angle caused by the obstacle; using a machine learning algorithm to identify and classify obstacles; based on historical usage data, driver preferences are learned, and a rearview mirror adjustment strategy is intelligently predicted. According to the invention, through accurate algorithm fusion, low obstacles can be accurately detected. The system automatically reduces the angle of the rearview mirror through an algorithm, so that an obstacle appears in a display area of the rearview mirror, it is ensured that a driver can directly see the obstacle through the rearview mirror, and collision or accidents caused by the fact that the low obstacle is not seen are effectively avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of rearview mirror adjustment, and more specifically, particularly relates to an intelligent electronic rearview mirror adaptive adjustment system and method. Background Art

[0002] With the continuous development of intelligent driving technology, driving safety has become an important consideration in automobile design. As a key tool for drivers to observe the road and obstacles behind, rearview mirrors have gradually changed from traditional mechanical rearview mirrors to intelligent electronic rearview mirrors. This intelligent rearview mirror combines image processing technology, sensor data and automatic adjustment system, which not only improves the driver's field of vision and driving experience, but also effectively improves traffic safety. In actual road driving, low obstacles (such as small objects in motion, uneven roads, parking lot obstacles, etc.) are often part of the driver's blind spot, especially when the vehicle speed is high, low obstacles are difficult to observe through conventional rearview mirrors. Traditional rearview mirrors cannot automatically adjust according to these obstacles in real time, resulting in the driver's failure to detect obstacles in time, which may cause traffic accidents. In order to deal with this problem, the intelligent electronic rearview mirror adaptive adjustment system came into being. The system can accurately detect the position and height of low obstacles by combining sensor data such as millimeter wave radar, LiDAR, and camera. Based on these detection results, the system can dynamically adjust the angle of the rearview mirror so that the driver can clearly see the low obstacles and enhance driving safety.

[0003] Although some current intelligent rearview mirror systems have certain automatic adjustment functions, most systems still have the following shortcomings, especially in the detection and adjustment of low obstacles: Existing obstacle detection systems mainly rely on visual sensors (such as cameras) for image recognition or LiDAR point cloud data for obstacle detection. However, the detection of low obstacles is still difficult, especially in more complex environments, such as backlight, night, rain and snow weather, the effect of the camera will be greatly reduced, and LiDAR is limited by the reflective characteristics of the surface of the object, and it is difficult to accurately capture low obstacles. Even if the obstacle is accurately identified, the existing system still faces the problem of slow response to rearview mirror adjustment. Most of the current rearview mirror angle adjustment systems rely on the calculation and adjustment of the vehicle driving state (such as vehicle speed, seat position, etc.) and static conditions, and lack real-time response to dynamic obstacle information. Many existing systems fail to effectively identify low obstacles, and often do not accurately match the height of the low obstacles and the vehicle position. Therefore, low obstacles are often not captured in time in the rearview mirror display area, resulting in the driver's inability to observe the obstacles, increasing the risk of collision. Most smart rearview mirror systems lack the ability to learn and adapt to the driver's personal viewing preferences when adjusting the rearview mirror angle. For example, some drivers may habitually require a larger rearview mirror field of view, while other drivers may prefer a smaller field of view. Existing systems rarely automatically optimize the rearview mirror adjustment strategy based on the driver's historical preferences. Summary of the invention

[0004] In view of the above or existing problems of the adaptive adjustment system and method of the intelligent electronic rearview mirror, the present invention is proposed.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: The embodiment of the present invention provides an intelligent electronic rearview mirror adaptive adjustment method, comprising: when the reversing mode is started, activating the millimeter wave radar to scan the environment on both sides and the rear, obtaining the position and distance of the obstacle, and using the millimeter wave radar and LiDAR to estimate the height of the obstacle; Get the initial rearview mirror angle and adjust the rearview mirror angle based on the obstacle; Use machine learning algorithms to identify and classify obstacles, and when potential obstacles are detected, use early warning mechanisms to alert; Based on historical usage data, it learns driver preferences and makes intelligent predictions on rearview mirror adjustment strategies.

[0006] As a preferred solution of the adaptive adjustment method of the intelligent electronic rearview mirror of the present invention, the method of using millimeter wave radar and LiDAR to estimate the height of obstacles includes: Combine the distance information of the millimeter-wave radar with the point cloud data of the LiDAR to calculate the height of the obstacle:

[0007] Among them, h obstacle is the obstacle height, d radar is the distance measured by the millimeter wave radar, d LiDAR is the distance measured by LiDAR data, and offset is the adjustment error compensation.

[0008] As a preferred solution of the adaptive adjustment method of the intelligent electronic rearview mirror of the present invention, the step of obtaining the initial rearview mirror angle includes: According to the driver's seat position, the driver's viewing angle requirements are calculated:

[0009] in, θ initial is the initial rearview mirror angle, seat_height is the seat height, and seat_position is the front and rear position of the seat.

[0010] As a preferred solution of the adaptive adjustment method of the intelligent electronic rearview mirror of the present invention, the adjustment of the rearview mirror angle caused by obstacles includes: When a low obstacle is detected, the system automatically lowers the rearview mirror angle:

[0011] in, θ adjusted Adjusted rearview mirror angle, Δ θ Angle adjusted according to the height and position of obstacles; If the obstacle is less than 50cm high and the obstacle is less than 1m away from the vehicle, the obstacle is judged not to be captured by the rearview mirror and the angle of the rearview mirror is automatically lowered by 5 to 10 degrees; According to the height and position of the obstacle, the angle of the rearview mirror is automatically adjusted, and the reaction time during the adjustment process is reduced through algorithm optimization. The adjustment formula is as follows:

[0012] in, θ init is the initial angle, Δ θ To adjust the amplitude, H obstacle is the height of the obstacle, H threshold The minimum height that affects the field of view.

[0013] As a preferred solution of the adaptive adjustment method of the intelligent electronic rearview mirror of the present invention, the adjustment of the rearview mirror angle caused by obstacles further includes: If the obstacle is within 1m of the vehicle, the system increases the mirror adjustment range to ensure that the driver can see these close obstacles and avoid potential collisions, introducing the influence factor of position:

[0014] Among them, the α adjustment factor can be set according to actual needs, D obstacle is the current distance between the obstacle and the vehicle, D threshold is the distance threshold; If D obstacle Less than D threshold , the system increases the angle of rearview mirror adjustment to ensure that the driver can see these low and close obstacles.

[0015] As a preferred solution of the adaptive adjustment method of the intelligent electronic rearview mirror of the present invention, the method of using a machine learning algorithm to identify and classify obstacles and, when a potential obstacle is detected, providing a warning through an early warning mechanism includes: Collect image datasets containing various obstacle types. Each image includes annotated obstacle categories. Annotate the obstacle categories for each image. Assuming that the input image size is H×W×C, the output image size of the convolution operation is (Hout, Wout, F), where F is the number of convolution kernels. The formula for the convolution operation is:

[0016] in, X is the input image or the output of the previous layer, K is the convolution kernel, b is the bias term, Y is the output feature map; If three types of obstacles are identified, pedestrians, cars, and low obstacles, each image is labeled as one of the categories. During the training process, the convolutional neural network optimizes the weights through back propagation and gradient descent. Use the cross entropy loss function to evaluate the difference between the network’s predictions and the true labels; If the distance between the obstacle and the vehicle is less than the set safety distance threshold, an early warning is triggered:

[0017] Among them, D safe is the safe distance, D vehicle is the current distance between the vehicle and the obstacle, D obstacle is the obstacle detection boundary, if D safe Less than the set threshold Dthreshold , then trigger the warning.

[0018] As a preferred solution of the adaptive adjustment method of the intelligent electronic rearview mirror of the present invention, the method of learning the driver's preference based on historical usage data and making intelligent predictions on the rearview mirror adjustment strategy includes: The driver's historical adjustment data is used as labels, and the environment and driving status data are used as features for training. The trained model is used to predict the driver's rearview mirror adjustment preference under the current environmental conditions and vehicle status in real time. The environmental conditions and vehicle status are obtained in real time, and the features that affect the rearview mirror adjustment are extracted from the real-time data and input into the prediction model. Based on the prediction results, the display mode, brightness and angle settings of the rearview mirror are automatically adjusted. According to the lighting and weather conditions, the display mode is automatically switched to increase the brightness and contrast at night or in low light conditions to avoid being too dark or too bright.

[0019] An intelligent electronic rearview mirror adaptive adjustment method system includes: an obstacle detection module, which is used to activate the millimeter wave radar to scan the environment on both sides and the rear when the reverse mode is started, obtain the position and distance of the obstacle, and use the millimeter wave radar and LiDAR to estimate the height of the obstacle; A rearview mirror adjustment module, used to obtain an initial rearview mirror angle and adjust the rearview mirror angle based on the obstacle; The classification warning module is used to identify and classify obstacles using machine learning algorithms. When potential obstacles are detected, warning mechanisms are used to provide reminders. Intelligent algorithm module, used to learn driver preferences based on historical usage data and make intelligent predictions on rearview mirror adjustment strategies.

[0020] A computing device, comprising: at least one processor, memory, and input-output unit; The memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the steps of the intelligent electronic rearview mirror adaptive adjustment method.

[0021] A computer-readable storage medium includes instructions, which, when executed on a computer, enable the computer to execute the steps of a method for adaptively adjusting an intelligent electronic rearview mirror.

[0022] The beneficial effects of the present invention are as follows: the present invention combines the data of millimeter-wave radar and LiDAR sensors, and through precise algorithm fusion, can accurately detect low obstacles. Low obstacles are often in the driver's blind spot, and it is difficult for traditional rearview mirrors to effectively capture them. Through the combined use of millimeter-wave radar and LiDAR, the system can make up for the limitations of visual sensors and single sensors, and achieve high-precision recognition of low obstacles. The system can calculate and automatically adjust the angle of the rearview mirror in real time according to the height, position and distance of the low obstacle. When a low obstacle is detected, the system automatically lowers the angle of the rearview mirror through an algorithm so that the obstacle appears in the display area of ​​the rearview mirror, ensuring that the driver can directly see the obstacle through the rearview mirror. This dynamic adjustment can reduce the driver's blind spot and effectively avoid collisions or accidents caused by low obstacles not being seen. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0024] Figure 1 The present invention provides a flowchart of an adaptive adjustment method for an intelligent electronic rearview mirror.

[0025] Figure 2 A schematic diagram of the structure of an intelligent electronic rearview mirror adaptive adjustment system provided in an embodiment of the present invention.

[0026] Figure 3 A schematic structural diagram of a medium according to an embodiment of the present invention is schematically shown.

[0027] Figure 4 A schematic diagram of the structure of a computing device according to an embodiment of the present invention is schematically shown.

[0028] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0029] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0030] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0031] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0032] Example Reference below Figure 1 , Figure 1 This is a flow chart of a method for adaptively adjusting an intelligent electronic rearview mirror provided by an embodiment of the present invention. It should be noted that the embodiments of the present invention can be applied to any applicable scenario.

[0033] Figure 1 The process of the adaptive adjustment method of the intelligent electronic rearview mirror provided by an embodiment of the present invention shown in the figure includes: S1: When the reverse mode is activated, the millimeter-wave radar is activated to scan the environment on both sides and the rear to obtain the position and distance of obstacles, and the millimeter-wave radar and LiDAR are used to estimate the height of obstacles.

[0034] Preferably, the distance information of the millimeter wave radar is combined with the point cloud data of the LiDAR to calculate the height of the obstacle:

[0035] Among them, h obstacle is the obstacle height, d radar is the distance measured by the millimeter wave radar, d LiDAR is the distance measured by LiDAR data, and offset is the adjustment error compensation.

[0036] Furthermore, when reversing in the garage, the vehicle uses millimeter-wave radar and LiDAR sensors to detect surrounding obstacles in real time. The system first uses the millimeter-wave radar to obtain the horizontal distance of the obstacle on the left side of the vehicle (for example, 5m), and at the same time, the LiDAR scan detects the vertical distance of the obstacle (for example, 3m). The height of the obstacle is calculated using the above formula: h obstacle =2.56 meters The system uses this information to determine that the obstacle is a high wall or structure, and then adjusts the angle of the rearview mirror to avoid collision.

[0037] Furthermore, the millimeter-wave radar provides accurate distance data, while the LiDAR helps the system accurately detect low obstacles (such as curbs, low fences, etc.). For example, the radar measures the horizontal distance to the obstacle as 3m, while the LiDAR measures the vertical distance to the obstacle as 1m. The calculation formula is: h obstacle =0.7 meters This indicates that the obstacle is low, and the system decides whether to adjust the rearview mirror or activate the warning mechanism based on the height and position of the obstacle.

[0038] S2: Obtain an initial rearview mirror angle and adjust the rearview mirror angle based on the obstacle.

[0039] Preferably, the driver's viewing angle requirement is calculated based on the driver's seat position:

[0040] in, θ initial is the initial rearview mirror angle, seat_height is the seat height, and seat_position is the front and rear position of the seat.

[0041] Preferably, when a low obstacle is detected, the system automatically lowers the rearview mirror angle:

[0042] in, θ adjusted Adjusted rearview mirror angle, Δ θ Angle adjusted according to the height and position of obstacles; If the obstacle is less than 50cm high and the obstacle is less than 1m away from the vehicle, the obstacle is judged not to be captured by the rearview mirror and the angle of the rearview mirror is automatically lowered by 5 to 10°; According to the height and position of the obstacle, the angle of the rearview mirror is automatically adjusted, and the reaction time during the adjustment process is reduced through algorithm optimization. The adjustment formula is as follows:

[0043] in, θ init is the initial angle, Δ θ To adjust the amplitude, H obstacle is the height of the obstacle, H threshold The minimum height that affects the field of view.

[0044] Preferably, if the obstacle is within 1m of the vehicle, the system increases the adjustment range of the rearview mirror to ensure that the driver can see these close obstacles to avoid potential collisions, introducing the influencing factor of position:

[0045] Among them, the α adjustment factor can be set according to actual needs, D obstacleis the current distance between the obstacle and the vehicle, D threshold is the distance threshold; If D obstacle Less than D threshold , the system increases the angle of rearview mirror adjustment to ensure that the driver can see these low and close obstacles.

[0046] Furthermore, assuming that the initial rearview mirror angle θ initial =5°, the seat height is 1.2m (relative to the ground), the seat front and rear position is 0.5m, the seat height reference value = 1.0m, the seat front and rear position reference value = 0.0m (the seat is located in the middle position); The coefficient k1 = 2° / m, which indicates the effect of seat height change per meter on the rearview mirror angle; The coefficient k2 = 3° / m, which indicates the effect of the change in the front and rear position of the seat on the rearview mirror angle per meter; The calculation results are: f(seat_height,seat_position)=2⋅(1.2-1.0)+3⋅(0.5-0)=2⋅0.2+3⋅0.5=0.4+1.5=1.9°; Therefore, the adjusted rearview mirror angle is: θ adjusted =θ initial +f(seat_height,seat_position)=5°+1.9°=6.9°.

[0047] Furthermore, assuming that the initial rearview mirror angle θ init =5°, the obstacle height threshold H is set threshold =0.5 m, the height of the detected obstacle H obstacle =0.3 m, the obstacle is 0.8 m away from the vehicle, Adjustment coefficient k=10, calculation process: Determine whether adjustment is needed: Because the obstacle height H obstacle =0.3 m is less than 50 cm, and the obstacle distance is less than 1 m, it is determined that the rearview mirror angle needs to be adjusted.

[0048] Calculate the adjustment: Δθ=10⋅(0.3-0.5)=10⋅(-0.2)=-2° Because the height of the obstacle is less than the threshold H threshold =0.5 m, so the angle is adjusted downward; Adjusted rearview mirror angle: θ adjusted =5∘+(-2°)=3° Therefore, the angle of the rearview mirror is adjusted to 3°.

[0049] Furthermore, the system detects the presence of low obstacles through millimeter-wave radar, LiDAR or camera, assuming that: D obstacle =0.8m (the obstacle is 0.8m away from the rear of the vehicle); D threshold =1m (the distance threshold is set to 1m); According to the formula, assuming the adjustment factor α=1.2, then: Δθ distance =1.2×0.2=0.24°; This indicates that the angle of the rearview mirror needs to be increased by about 0.24° so that the driver can see obstacles that are closer to the vehicle; the system automatically adjusts the angle of the rearview mirror by 0.24° to ensure that the obstacle is within the field of view, thereby avoiding a collision.

[0050] S3: Use machine learning algorithms to identify and classify obstacles, and when potential obstacles are detected, an early warning mechanism will be used to provide reminders.

[0051] Preferably, an image dataset containing various obstacle types is collected, each image includes a marked obstacle category, and the obstacle category is annotated for each image. Assuming that the input image size is H×W×C, the output image size of the convolution operation is (Hout, Wout, F), where F is the number of convolution kernels, and the formula for the convolution operation is:

[0052] in, X is the input image or the output of the previous layer, K is the convolution kernel, b is the bias term, Y is the output feature map; If three types of obstacles are identified, pedestrians, cars, and low obstacles, each image is labeled as one of the categories. During the training process, the convolutional neural network optimizes the weights through back propagation and gradient descent. Use the cross entropy loss function to evaluate the difference between the network’s predictions and the true labels; If the distance between the obstacle and the vehicle is less than the set safety distance threshold, an early warning is triggered:

[0053] Among them, D safe is the safe distance, D vehicle is the current distance between the vehicle and the obstacle, D obstacle is the obstacle detection boundary, if D safe Less than the set threshold D threshold , then trigger the warning.

[0054] Furthermore, assume that a batch of image data containing pedestrians, cars, and low obstacles has been collected.

[0055] The label of each image is the category of the obstacle, and the label value is {0: pedestrian, 1: car, 2: low obstacle}.

[0056] Step 2: Train the CNN Using the labeled data set, the convolutional neural network model is trained, and the network learns the characteristics of obstacles so that it can correctly classify pedestrians, cars, and low obstacles.

[0057] Step 3: Identify and classify Input an image, and CNN will output a class probability value. For example, output pedestrian: 0.1, car: 0.85, low obstacle: 0.05; Based on the maximum probability value, the system classifies the image as a "car".

[0058] Step 4: Calculate the safe distance and trigger an alert Assume that the detected obstacle is a "car", the distance between the vehicle and the obstacle is Dvehicle=0.8 m, and set the safety distance threshold D threshold =1.0 m, According to the formula, Dsafe=0.8, Dsafe=0.8m<1.0m. Therefore, when the safety distance is less than the threshold, the system will trigger an early warning.

[0059] S4: Based on historical usage data, learn driver preferences and make intelligent predictions on rearview mirror adjustment strategies.

[0060] Preferably, the driver's historical adjustment data is used as a label, and the environment and driving state data are used as features for training. The trained model is used to predict the driver's rearview mirror adjustment preference under the current environmental conditions and vehicle state in real time, and the environmental conditions and vehicle state are obtained in real time. Features that affect the rearview mirror adjustment are extracted from the real-time data and input into the prediction model; Based on the prediction results, the display mode, brightness and angle settings of the rearview mirror are automatically adjusted. According to the lighting and weather conditions, the display mode is automatically switched to increase the brightness and contrast at night or in low light conditions to avoid being too dark or too bright.

[0061] Furthermore, the historical data is cleaned and processed, including removing outliers, filling missing data, etc. The environmental data and driving status data are normalized so that they can be scaled uniformly when input into the model.

[0062] Use random forest or support vector machine (SVM) for training. Choose a classification or regression model that is appropriate for the task. Loss function and optimization: If the mirror adjustment value is a continuous value (such as angle, brightness), use mean square error (MSE) as the loss function to optimize the model's predictive ability. If the mirror adjustment is a discrete category (such as "night mode", "day mode"), use the cross entropy loss function for optimization.

[0063] The data is divided into a training set and a test set, the model is trained and its performance on the test set is evaluated. The cross-validation method is used to improve the generalization ability of the model. Based on the sensor data obtained in real time, the feature vector Xcurrent of the current environment and driving state is extracted.

[0064] Xcurrent is input into the trained model, and the adjustment preferences of the rearview mirror (yadjusted, including display mode, brightness, angle, etc.) are output. Based on the adjustment preferences output by the model, the system automatically adjusts the display mode, brightness, contrast and angle of the rearview mirror to optimize the driver's field of view experience.

[0065] During training, the model learns the relationship between the environment data and the driving state data and the driver's historical adjustments:

[0066] When predicting, input the current environment and vehicle status:

[0067] Brightness adjustment:

[0068] Among them, L ambient is the ambient light intensity, L threshold is the illumination threshold, v vehicle It's the car speed.

[0069] Angle adjustment:

[0070] Adjust the rearview mirror angle according to factors such as the height of the obstacle, the distance between the vehicle and the obstacle, and the ambient light intensity.

[0071] After introducing the method of the exemplary embodiment of the present invention, next, refer to Figure 2 An intelligent electronic rearview mirror adaptive adjustment method system according to an exemplary embodiment of the present invention is described, and the system includes: The obstacle detection module is used to activate the millimeter-wave radar to scan the environment on both sides and behind when the reverse mode is started, obtain the location and distance of the obstacle, and use the millimeter-wave radar and LiDAR to estimate the height of the obstacle; A rearview mirror adjustment module, used to obtain an initial rearview mirror angle and adjust the rearview mirror angle based on the obstacle; The classification warning module is used to identify and classify obstacles using machine learning algorithms. When potential obstacles are detected, warning mechanisms are used to provide reminders. Intelligent algorithm module, used to learn driver preferences based on historical usage data and make intelligent predictions on rearview mirror adjustment strategies.

[0072] After introducing the method and apparatus of the exemplary embodiment of the present invention, next, reference is made to Figure 3 For a description of a computer-readable storage medium according to an exemplary embodiment of the present invention, please refer to Figure 3 , the computer-readable storage medium shown is a CD 30, on which a computer program (i.e., a program product) is stored. When the computer program is executed by the processor, the steps recorded in the above method implementation are implemented. For example, when the reversing mode is started, the millimeter-wave radar is activated to scan the environment on both sides and the rear, the position and distance of the obstacle are obtained, and the height of the obstacle is estimated using the millimeter-wave radar and LiDAR; the initial rearview mirror angle is obtained, and the rearview mirror angle caused by the obstacle is adjusted; the obstacles are identified and classified using a machine learning algorithm, and when a potential obstacle is detected, an early warning mechanism is used to remind; based on historical usage data, the driver's preferences are learned, and the rearview mirror adjustment strategy is intelligently predicted; the specific implementation method of each step is not repeated here.

[0073] It should be noted that examples of the computer-readable storage medium may also 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 optical or magnetic storage media, which are not listed here one by one.

[0074] After introducing the method, apparatus and medium of the exemplary embodiments of the present invention, next, reference is made to Figure 4 A computing device for adaptively adjusting a smart electronic rearview mirror according to an exemplary embodiment of the present invention.

[0075] Figure 4 A block diagram of an exemplary computing device 40 suitable for implementing embodiments of the present invention is shown, and the computing device 40 may be a computer system or a server. Figure 4 The computing device 40 shown is only an example and should not bring any limitation to the functionality and scope of use of the embodiments of the present invention.

[0076] like Figure 4As shown, the components of the computing device 40 may include, but are not limited to: one or more processors or processing units 401 , a system memory 402 , and a bus 403 connecting different system components (including the system memory 402 and the processing unit 401 ).

[0077] The computing device 40 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computing device 40, including volatile and non-volatile media, removable and non-removable media.

[0078] The system memory 402 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 4021 and / or cache memory 4022. The computing device 40 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the ROM 4023 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 is not shown in the Figure 4 As shown in FIG. 4 , a disk drive for reading and writing a removable non-volatile disk (e.g., a “floppy disk”) and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 403 via one or more data medium interfaces. System memory 402 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of various embodiments of the present invention.

[0079] A program / utility 4025 having a set (at least one) of program modules 4024 may be stored, for example, in system memory 402, and such program modules 4024 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 4024 generally perform the functions and / or methods of the embodiments described herein.

[0080] The computing device 40 may also communicate with one or more external devices 404 (e.g., a keyboard, a pointing device, a display, etc.). Such communication may be performed via an input / output (I / O) interface 405. Furthermore, the computing device 40 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 406. Figure 4 As shown, the network adapter 406 communicates with other modules (such as the processing unit 401, etc.) of the computing device 40 via the bus 403. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with computing device 40 .

[0081] The processing unit 401 executes various functional applications and data processing by running the programs stored in the system memory 402. For example, when the reverse mode is started, the millimeter wave radar is activated to scan the environment on both sides and the rear, obtain the position and distance of the obstacle, and use the millimeter wave radar and LiDAR to estimate the height of the obstacle; obtain the initial rearview mirror angle, and adjust the rearview mirror angle based on the obstacle. Obstacles are identified and classified using machine learning algorithms. When potential obstacles are detected, warnings are issued through an early warning mechanism. Based on historical usage data, driver preferences are learned and the rearview mirror adjustment strategy is intelligently predicted. The specific implementation methods of each step will not be repeated here. It should be noted that although several units / modules or sub-units / sub-modules of a synchronous escape wiring device based on multiple commodity flows are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more units / modules described above may be concretized in one unit / module. Conversely, the features and functions of one unit / module described above may be further divided to be concretized by multiple units / modules.

[0082] In the description of the present invention, it should be noted that the terms “first”, “second” and “third” are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0083] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0084] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0085] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0086] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0087] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that can be executed by a processor. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., various media that can store program codes.

[0088] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

[0089] In addition, although the operations of the method of the present invention are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

Claims

1. A method for adaptively adjusting an intelligent electronic rearview mirror, characterized in that: include: When the reverse mode is activated, the millimeter-wave radar is activated to scan the environment on both sides and behind to obtain the location and distance of obstacles, and the millimeter-wave radar and LiDAR are used to estimate the height of obstacles; Get the initial rearview mirror angle and adjust the rearview mirror angle based on the obstacle; Use machine learning algorithms to identify and classify obstacles, and when potential obstacles are detected, use early warning mechanisms to alert; Based on historical usage data, it learns driver preferences and makes intelligent predictions on rearview mirror adjustment strategies.

2. The method for adaptively adjusting an intelligent electronic rearview mirror according to claim 1, characterized in that: The use of millimeter wave radar and LiDAR to estimate the height of obstacles includes: Combine the distance information of the millimeter-wave radar with the point cloud data of the LiDAR to calculate the height of the obstacle: ； Among them, h obstacle is the obstacle height, d radar is the distance measured by the millimeter wave radar, d LiDAR is the distance measured by LiDAR data, and offset is the adjustment error compensation.

3. The method for adaptively adjusting an intelligent electronic rearview mirror according to claim 1, characterized in that: The obtaining of the initial rearview mirror angle comprises: According to the driver's seat position, the driver's viewing angle requirements are calculated: ； in, θ initial is the initial rearview mirror angle, seat_height is the seat height, and seat_position is the front and rear position of the seat.

4. The method for self-adapting an intelligent electronic rearview mirror according to claim 1, characterized in that: The adjusting of the rearview mirror angle caused by the obstacle includes: When a low obstacle is detected, the system automatically lowers the rearview mirror angle: ； in, θ adjusted Adjusted rearview mirror angle, Δ θ Angle adjusted according to the height and position of obstacles; If the obstacle is less than 50cm high and the obstacle is less than 1m away from the vehicle, the obstacle is judged not to be captured by the rearview mirror and the angle of the rearview mirror is automatically lowered by 5 to 10 degrees; According to the height and position of the obstacle, the angle of the rearview mirror is automatically adjusted, and the reaction time during the adjustment process is reduced through algorithm optimization. The formula for automatically adjusting the angle of the rearview mirror is as follows: ； in, θ init is the initial angle, Δ θ To adjust the amplitude, H obstacle is the height of the obstacle, H threshold The minimum height that affects the field of view.

5. The method for self-adapting an intelligent electronic rearview mirror according to claim 1, characterized in that: The adjusting of the rearview mirror angle based on the obstacle also includes: If the obstacle is within 1m of the vehicle, the system increases the mirror adjustment range to ensure that the driver can see these close obstacles and avoid potential collisions, introducing the influence factor of position: ； Among them, the α adjustment factor can be set according to actual needs, D obstacle is the current distance between the obstacle and the vehicle, D threshold is the distance threshold; If D obstacle Less than D threshold , the system increases the angle of rearview mirror adjustment to ensure that the driver can see these low and close obstacles.

6. The method for self-adapting an intelligent electronic rearview mirror according to claim 1, characterized in that: The machine learning algorithm is used to identify and classify obstacles. When a potential obstacle is detected, an early warning mechanism is used to warn, including: Collect image datasets containing various obstacle types. Each image includes annotated obstacle categories. Annotate the obstacle categories for each image. Assuming that the input image size is H×W×C, the output image size of the convolution operation is (Hout, Wout, F), where F is the number of convolution kernels. The formula for the convolution operation is: ； in, X is the input image or the output of the previous layer, K is the convolution kernel, b is the bias term, Y is the output feature map; If three types of obstacles are identified, pedestrians, cars, and low obstacles, each image is labeled as one of the categories. During the training process, the convolutional neural network optimizes the weights through back propagation and gradient descent. Use the cross entropy loss function to evaluate the difference between the network’s predictions and the true labels; If the distance between the obstacle and the vehicle is less than the set safety distance threshold, an early warning is triggered: ； Among them, D safe is the safe distance, D vehicle is the current distance between the vehicle and the obstacle, D obstacle is the obstacle detection boundary, if D safe Less than the set threshold D threshold , then trigger the warning.

7. The method for self-adapting an intelligent electronic rearview mirror according to claim 1, characterized in that: The method of learning driver preferences based on historical usage data and making intelligent predictions on rearview mirror adjustment strategies includes: The driver's historical adjustment data is used as labels, and the environment and driving status data are used as features for training. The trained model is used to predict the driver's rearview mirror adjustment preference under the current environmental conditions and vehicle status in real time. The environmental conditions and vehicle status are obtained in real time, and the features that affect the rearview mirror adjustment are extracted from the real-time data and input into the prediction model. Based on the prediction results, the display mode, brightness and angle settings of the rearview mirror are automatically adjusted. According to the lighting and weather conditions, the display mode is automatically switched to increase the brightness and contrast at night or in low light conditions to avoid being too dark or too bright.

8. An intelligent electronic rearview mirror adaptive adjustment system, characterized in that: include: The obstacle detection module is used to activate the millimeter-wave radar to scan the environment on both sides and behind when the reverse mode is started, obtain the location and distance of the obstacle, and use the millimeter-wave radar and LiDAR to estimate the height of the obstacle; A rearview mirror adjustment module, used to obtain an initial rearview mirror angle and adjust the rearview mirror angle based on the obstacle; The classification warning module is used to identify and classify obstacles using machine learning algorithms. When potential obstacles are detected, warning mechanisms are used to provide reminders. Intelligent algorithm module, used to learn driver preferences based on historical usage data and make intelligent predictions on rearview mirror adjustment strategies.

9. A computing device, comprising: at least one processor, memory, and input-output unit; The memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the steps of the adaptive adjustment method of the intelligent electronic rearview mirror as described in any one of claims 1 to 7.

10. A computer-readable storage medium comprising instructions, which, when executed on a computer, enables the computer to execute the steps of the adaptive adjustment method of an intelligent electronic rearview mirror as claimed in any one of claims 1 to 7.

Images