Blind zone monitoring method based on multi-factor dynamic change and vehicle control method and system

Abstract

The invention belongs to the field of road vehicle control systems, and relates to a blind area monitoring method based on multi-factor dynamic change and a vehicle control method and system.The blind area monitoring method comprises the steps that the head state of a driver, vehicle motion data and the surrounding environment change condition are collected through a data acquisition module; the multi-source data is sent to a data processing and fusion module for data preprocessing and time-space synchronization, so that data alignment is realized, and meanwhile, multi-source data is fused; then, main blind areas outside the automobile are divided into a blind area in front of the automobile, a blind area behind the automobile, an A-column blind area, a B-column blind area and a C-column blind area, the basic blind area angle of each area is calculated based on the size of an automobile fixing structure and the distance between the automobile fixing structure and a driver, and finally an independent dynamic model of each blind area and a multi-blind-area dynamic linkage model are established; the dynamic angle range of the blind area of each area is calculated based on the multi-blind-area dynamic linkage model, and the accident problem caused by the change of the blind area in the running process of the automobile is solved.

Description

Technical Field

[0001] The present invention belongs to the field of road vehicle control systems, and in particular relates to a blind spot monitoring method based on dynamic changes of multiple factors, a vehicle control method and a system. Background Art

[0002] With the development of the automobile industry, its negative impact on urban road traffic has become increasingly prominent. The increase in the number of cars and the frequent traffic accidents caused by illegal driving behaviors have caused casualties and economic losses, becoming a common problem faced by many cities. From the main causes of the accident: being rear-ended by other vehicles in the blind spot, not paying attention to the side danger when driving at high speed, and the change of blind spot when turning right are the more common types of automobile traffic accidents.

[0003] In order to reduce the occurrence of automobile accidents, relevant departments have taken a series of safety measures, including improving road safety facilities and promoting safe driving behaviors. However, due to the high speed of cars, irregular blind spots, and complex driving conditions, the accident rate has not dropped significantly, and the intelligent blind spot detection device of cars still faces difficult problems to solve. Among them, the detection measures for the dynamic vision blind spots of cars are particularly lacking. Therefore, it is of great significance to strengthen the detection of dynamic vision blind spots of cars.

[0004] At present, in order to solve the problem of automobile blind spot detection, the measures taken are mainly intelligent blind spot detection devices, strengthening professional training, adding monitoring and alarm systems, and implementing humanized design and service improvements. With the rapid development of artificial intelligence technology, intelligent assisted driving technology has gradually become a hot area of ​​research and application. As one of the core technologies of intelligent assisted driving technology, the blind spot detection system (BSD) has made significant progress in sensor technology, algorithm optimization and system integration in recent years. Its core goal is to monitor the unreachable areas around the vehicle (such as A-pillars, rear of the car, inner wheel difference, etc.) in real time through sensors such as radar, cameras, and ultrasonic waves, and combine early warning mechanisms (sound and light prompts or automatic intervention) to reduce the risk of collision. The current technological development presents the following characteristics: sensor technology is dominant, millimeter wave radar has become the mainstream solution due to its strong anti-interference ability and long detection distance (up to 50 meters), but its cost is relatively high; although the camera solution is low-cost, it is easy to fail in harsh environments such as rain, fog, and strong light.

[0005] Chinese patent CN 117818622 A calculates the blind spot angle and generates real-time detection and warning through the driver's head position data and the vehicle pillar position data, and optimizes the detection accuracy by combining the driver's perspective. Chinese patent CN 222329589 U discloses a rearview mirror integrated camera and blind spot detection system, embeds the camera into the rearview mirror bracket, monitors the rear blind spot in real time, and reduces safety hazards when changing lanes or parking through the prompt system. Chinese patent CN 117068049 A invented a low-cost in-vehicle blind spot monitoring method based on a mobile device camera, using the camera of a mobile device (such as a mobile phone or tablet) in the car to cover the blind spot in the cabin, and generates control instructions through image processing. Chinese patent CN 117392833 A combines the camera with cloud data to obtain obstacle speed and position information in turning or extreme weather scenarios, predict the collision time and output warnings, but there is only a single environmental perception solution. Chinese patent CN 118907282 A discloses a blind spot monitoring system with multiple prompts, integrating a monitoring module, a control module and a prompt module, and improving safety through dual sound and light warnings. It is not difficult to find that the existing blind spot monitoring methods still have some problems: (1) Reliance on a single sensor: Most systems only use radar or camera, resulting in incomplete scene coverage. (2) Poor dynamic environment response and insufficient environmental adaptability: Traditional blind spot monitoring mostly relies on static vehicle structure (such as A-pillar, rearview mirror) or a single sensor (such as millimeter wave radar), lacks comprehensive consideration of dynamic factors (vehicle speed, steering angle, driver's line of sight), and cannot dynamically adjust the monitoring range. (3) Lack of human-machine collaborative mechanism, ignoring driver behavior: Existing technologies rarely integrate the driver's driving status, such as the impact of personalized parameters such as head position, line of sight and dynamic vision on blind spots, and cannot meet the blind spot accuracy requirements of future intelligent assisted driving systems. Summary of the invention

[0006] In view of the above-mentioned technical problems and defects, the purpose of the present invention is to provide a blind spot monitoring method based on dynamic changes of multiple factors. The method realizes real-time dynamic modeling of the blind spot range by integrating vehicle motion parameters, environmental perception data and driver behavior characteristics, so as to solve the accident problems caused by changes in blind spots while the car is driving.

[0007] To achieve the above object, the present invention adopts the following technical solution: A blind spot monitoring method based on dynamic changes of multiple factors, the method comprising the following steps: Step 1. The data acquisition module collects the driver's head status, vehicle movement data and surrounding environment changes, and sends them to the data processing and fusion module; Step 2. The data processing and fusion module performs data preprocessing and spatiotemporal synchronization on the raw data obtained from the data acquisition module, realizes data alignment, and fuses multi-source data at the same time; Step 3. Divide the main blind spots outside the car into the front blind spot, the rear blind spot, the A-pillar blind spot, the B-pillar blind spot, and the C-pillar blind spot, and calculate the basic blind spot angle of each area based on the size of the vehicle fixed structure and its distance from the driver; wherein the A-pillar blind spot includes the A-pillar left blind spot and the A-pillar right blind spot, the B-pillar blind spot includes the B-pillar left blind spot and the B-pillar right blind spot, and the C-pillar blind spot includes the C-pillar left blind spot and the C-pillar right blind spot; Step 4. Establish an independent dynamic model for each blind spot and a dynamic linkage model for multiple blind spots, and calculate the dynamic angle range of each blind spot based on the dynamic linkage model for multiple blind spots; wherein, the independent dynamic model for each blind spot is: ; in, Represents the dynamic blind spot angles of different areas of the car at time t, i The values ​​are A left, A right, B left, B right, C left, C right, front, and back, corresponding to A pillar left, A pillar right, B pillar left, B pillar right, C pillar left, C pillar right, front of the vehicle, and back of the vehicle respectively; Represents the basic blind spot angles of different areas of the car; Represents the dynamic correction coefficients related to the angle increments in different areas of the car; Weather compensation factor; is the field of view attenuation angle; is the blind area angle increment; Represents the driver's head steering angle at time t; Represents the driver's line of sight shift information at time t; The multi-blind zone dynamic linkage model is: ; Where: i represents the blind spot area of ​​the car that changes under the influence of multiple factors; j represents the blind spot area affected by the changes of other blind spots; is the coupling coefficient; Represents the dynamic angle range of blind spot j under the influence of other blind spots at time t; the value range of i, j is A left, A right, B left, B right, C left, C right, front, and rear, corresponding to A pillar left, A pillar right, B pillar left, B pillar right, C pillar left, C pillar right, front of the vehicle, and rear of the vehicle respectively.

[0008] As a preferred embodiment of the present invention, the coupling coefficient adaptive adjustment rule is: ; in: is the basic coupling strength, is the vehicle speed sensitivity coefficient, v is the speed of the car; is the steering angle attenuation coefficient, is the steering angle of the car.

[0009] As a preferred embodiment of the present invention, the basic blind area angle of the A-pillar blind area The geometric calculation formula is: ; in, Refers to the average width of the A-pillar, Refers to the horizontal distance from the A-pillar to the driver's eyes; the A-pillar includes the left A-pillar and the right A-pillar. The left A-pillar corresponds to the left blind spot of the A-pillar, and the right A-pillar corresponds to the right blind spot of the A-pillar. Basic blind spot angle of B-pillar blind spot The geometric calculation formula is: ; in, Refers to the average width of the B-pillar, Refers to the horizontal distance from the B-pillar to the driver's eyes; the B-pillar includes the left B-pillar and the right B-pillar. The left B-pillar corresponds to the left blind spot of the B-pillar, and the right B-pillar corresponds to the right blind spot of the B-pillar. Basic blind spot angle of C-pillar blind spot The geometric calculation formula is: ; in, Refers to the lateral extension width of the C-pillar. Refers to the horizontal distance from the C-pillar to the driver; the C-pillar includes the left C-pillar and the right C-pillar. The left C-pillar corresponds to the left blind spot of the C-pillar, and the right C-pillar corresponds to the right blind spot of the C-pillar. Basic blind spot angle of the front blind spot The geometric calculation formula is: ; in, Refers to the height of the hood, Refers to the distance from the front of the vehicle to the driver; Basic blind spot angle of the rear blind spot The geometric calculation formula is: ; in, Refers to the height of the bottom edge of the rear window. Refers to the distance from the rear of the vehicle to the driver.

[0010] As a preferred embodiment of the present invention, the expression of the driver's sight shift information is: ; Among them, (m, n) is the original fixation point, ( ) are pupil coordinates; The expression of blind spot angle increment is: ; The expression of the dynamic correction coefficient related to the angle increment of different areas of the car is: ; in, is the reference distance for monitoring blind spot i, is the steering angle of the car, B is the wheelbase of the vehicle; The expression of the field of view attenuation angle is: ; in, is the field of view attenuation angle; is the field of view angle under static conditions; is the attenuation coefficient; DAV is the dynamic visual acuity.

[0011] As a preferred embodiment of the present invention, when calculating the dynamic angle range of the blind spot in each area, an online learning strategy is added to optimize the coupling parameters based on the extended Kalman filter algorithm.

[0012] As a further preferred embodiment of the present invention, the relationship between dynamic visual acuity and speed is: ; in, For static vision, v is the relative speed of the car, k is the attenuation coefficient.

[0013] The present invention also provides a vehicle control method, the method comprising the following steps: Step A. Calculate the dynamic angle range of the blind spot in each area based on the above-mentioned blind spot monitoring method based on dynamic changes of multiple factors; Step B. Determine the linkage risk index of each blind spot according to the data transmitted by the data acquisition module and based on the dynamic angle range calculated in step A, and perform weighted summation of the linkage risk indexes of each blind spot to obtain a global comprehensive risk index; Step C. The risk assessment and classification module determines the risk level based on the global comprehensive risk index, classifies the vehicle according to its risk level, and controls the vehicle at the same time.

[0014] As a preferred embodiment of the present invention, the linkage risk index of each blind spot is The calculation method is: ; in: is the dynamic angle of the blind spot j, is the reference distance for blind spot j monitoring; is the traffic flow density of blind spot j; is the driver reaction time in blind spot j; is the sensor coverage of blind spot j; The global comprehensive risk index is calculated as follows: ; in, is the weight of blind zone j.

[0015] The present invention also provides a vehicle control system, which is used to implement the above-mentioned vehicle control method, including a data acquisition module, a data processing and fusion module, a blind spot independent dynamic model, a multi-blind spot dynamic linkage model, a risk index calculation module, a risk assessment and classification module, and a control module; The data acquisition module is used to collect the driver's head status, the vehicle's own motion data and the surrounding environment changes, send them to the data processing and fusion module, and store them in the database; The data processing and fusion module is used to perform data preprocessing and spatiotemporal synchronization on the original data, realize data alignment, and fuse multi-source data at the same time; The blind spot independent dynamic model is used to calculate the dynamic blind spots in different areas of the car; The multi-blind zone dynamic linkage model is used to calculate the dynamic blind zones of each area under the mutual influence of different areas of the car; The risk index calculation model is used to calculate the linkage risk index of each blind spot, and to obtain a global comprehensive risk index by weighted summation of the linkage risk indexes of each blind spot; The risk assessment and grading module is used to determine the risk level based on the global comprehensive risk index and to grade the risk level by level; The control module is used for early warning and vehicle control according to the risk level.

[0016] As a preferred embodiment of the present invention, the data acquisition module includes a vehicle state perception module, an environment perception module, and a driver behavior adaptation module; wherein the vehicle state perception module acquires the vehicle electronic control unit data through the CAN bus and collects the vehicle kinematic parameters in real time; the environment perception module collects the vehicle surrounding environment parameters in real time through multi-source sensor fusion, and the multi-source sensor includes a millimeter wave radar, an optical radar, and a binocular camera; the driver behavior adaptation module monitors the driver's physiological and behavioral characteristics in real time, and the driver behavior adaptation module includes an eye tracker and a head posture detection unit.

[0017] Advantages and beneficial effects of the present invention: (1) The present invention provides a blind spot monitoring method based on dynamic changes of multiple factors. By integrating vehicle motion parameters, environmental perception data and driver behavior characteristics, real-time dynamic modeling and accurate warning of the blind spot range are achieved. The method obtains vehicle speed, steering angle, acceleration and other parameters in real time through the CAN bus, and calculates the dynamic expansion range of the inner wheel difference blind spot in combination with the wheelbase; detects the type, position and motion state of obstacles in the blind spot through multi-source sensor fusion (including millimeter wave radar, binocular camera, Lidar); uses an eye tracker and a head tracking device to monitor the driver's line of sight, head deflection angle and dynamic visual acuity, and adjusts the warning threshold in a personalized manner; integrates and weights the above parameters through machine learning, calculates the blind spot range in real time, and dynamically generates a blind spot heat map to reduce accidents caused by special circumstances in the blind spot.

[0018] (2) The present invention can effectively monitor the dynamic blind spots of a car in real time and provide graded warnings, which can solve the accident problems caused by changes in blind spots during driving to a certain extent and bring positive impacts to autonomous driving.

[0019] (3) The blind spot monitoring method based on multi-factor dynamic changes provided by the present invention can improve the safety of automobile driving and avoid major traffic accidents with tragic consequences. By real-time monitoring of the vehicle body status, changes in the surrounding environment and the driver's head characteristics, the system can respond to potential conflicts and improve services in a timely manner. It has the advantages of real-time, accuracy, personalized services and data-driven decision-making, and is expected to bring great changes and development to the autonomous driving industry.

[0020] (4) When determining the blind spot, the present invention considers the impact of the driver's driving status (such as head position, line of sight direction, dynamic vision and other personalized parameters) on the blind spot, and comprehensively considers and models the dynamic factors (vehicle speed, steering angle, driver's line of sight). The blind spot monitoring range can be dynamically adjusted, and the environmental adaptability is strong, meeting the blind spot accuracy requirements of future intelligent assisted driving systems.

[0021] (5) The linkage model designed by the present invention when determining blind spots solves the fundamental problem that traditional static models cannot adapt to changes in vehicle speed, steering, and driver behavior through dynamic coupling of multiple blind spots and expansion calculation of inner wheel difference, and significantly improves the warning accuracy in complex scenarios (turning, high speed, rain and fog).

[0022] (6) The present invention makes the system adaptive by adding an online learning mechanism, which can continuously improve the model based on actual driving feedback, reduce the false alarm rate and enhance the generalization ability across vehicle models and environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] By referring to the following description in conjunction with the accompanying drawings, and with a more comprehensive understanding of the present invention, other objects and results of the present invention will become more apparent and easy to understand. In the accompanying drawings: Figure 1 This is a schematic diagram of the blind spot of a car according to the present invention; Figure 2 A flow chart of a blind spot monitoring method based on dynamic changes of multiple factors provided by the present invention; Figure 3 A flow chart of the vehicle control method provided by the present invention; Figure 4 This is a structural block diagram of the vehicle control system provided by the present invention. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the technical solution and advantages of the present invention, the present application is described in detail below in conjunction with the accompanying drawings, but it is not intended to limit the protection scope of the present invention.

[0025] Embodiment 1:

[0026] like Figure 1 , Figure 2 As shown, this embodiment provides a blind spot monitoring method based on dynamic changes of multiple factors, and the method includes the following steps: Step 1. The data acquisition module collects the driver's head status, vehicle movement data and surrounding environment changes, and sends them to the data processing and fusion module; Step 2. The data processing and fusion module performs data preprocessing and spatiotemporal synchronization on the raw data obtained from the data acquisition module, realizes data alignment, and fuses multi-source data at the same time; Step 3. Divide the main blind spots outside the car into the front blind spot, the rear blind spot (the rear blind spot), the A-pillar blind spot, the B-pillar blind spot, and the C-pillar blind spot, and calculate the basic blind spot angle of each area based on the size of the vehicle fixed structure and its distance from the driver; among which, the A-pillar blind spot includes the A-pillar left blind spot and the A-pillar right blind spot, the B-pillar blind spot includes the B-pillar left blind spot and the B-pillar right blind spot, and the C-pillar blind spot includes the C-pillar left blind spot and the C-pillar right blind spot; Step 4. Establish an independent dynamic model for each blind spot and a dynamic linkage model for multiple blind spots, and calculate the dynamic angle range of each blind spot based on the dynamic linkage model for multiple blind spots; wherein, the independent dynamic model for each blind spot is: ; in, Represents the dynamic blind spot angles of different areas of the car at time t, i The values ​​are A left, A right, B left, B right, C left, C right, front, and back, corresponding to A pillar left, A pillar right, B pillar left, B pillar right, C pillar left, C pillar right, front of the vehicle, and back of the vehicle respectively; Represents the basic blind spot angles of different areas of the car; Represents the dynamic correction coefficients related to the angle increments in different areas of the car; Weather compensation factor; is the field of view attenuation angle; is the blind area angle increment; Represents the driver's head steering angle at time t; Represents the driver's line of sight shift information at time t; The multi-blind zone dynamic linkage model is: ; Where: i represents the blind spot area of ​​the car that changes under the influence of multiple factors; j represents the blind spot area affected by the changes of other blind spots; is the coupling coefficient; Represents the dynamic angle range of blind spot j under the influence of other blind spots at time t (the value range of i, j is A left, A right, B left, B right, C left, C right, front, and rear, corresponding to A pillar left, A pillar right, B pillar left, B pillar right, C pillar left, C pillar right, front of the vehicle, and rear of the vehicle respectively).

[0027] In this embodiment, the coupling coefficient adaptive adjustment rule is: ; in: is the basic coupling strength, obtained by fitting multiple experimental data. For details, see the attached Figure 1 and Table 1; is the vehicle speed sensitivity coefficient, and its value is 0.05; v is the speed of the car; is the steering angle attenuation coefficient, which is 0.1; is the steering angle of the car.

[0028] Table 1: Basic coupling strength coefficients Experimental calibration value table

[0029] In this embodiment, the data acquisition module is used to collect the driver's head state and the vehicle's own motion data and the surrounding environment changes, send them to the data processing and fusion module, and store them in the database; the data acquisition module includes a vehicle state perception module, an environment perception module, and a driver behavior adaptation module; Among them, the vehicle state perception module obtains vehicle ECU (electronic control unit) data through the CAN bus and collects vehicle kinematic parameters in real time. The vehicle kinematic parameters include vehicle speed, steering angle, acceleration, wheelbase, etc.; the vehicle kinematic parameters provide parameters for the calculation of blind spots caused by reduced dynamic visual acuity in subsequent high-speed driving conditions and the inner wheel difference expansion blind spot.

[0030] The environment perception module collects the vehicle's surrounding environment parameters in real time, including weather conditions, obstacles, etc. Specifically, the environment perception module detects the type, position and motion state of obstacles in the blind spot through multi-source sensor fusion; the multi-source sensors include millimeter-wave radar (77GHz), optical radar (LiDAR), and binocular camera; among them, the millimeter-wave radar is responsible for detecting the obstacle distance (0.1-150 meters), relative speed (±200 km / h), and azimuth (±60°), which is suitable for rainy and foggy weather and night scenes; LiDAR: Generates high-precision 3D point clouds (300,000 points / second, accuracy ±3cm) for building dense environment models and identifying low-reflectivity targets (such as black cones).

[0031] Binocular camera: RGB image acquisition (1920×1080 resolution) + parallax ranging (accuracy ±5cm), supporting target classification (YOLOv5, mAP 85%) and lane line detection.

[0032] The driver behavior adaptation module monitors the driver's physiological and behavioral characteristics in real time, including the driver's line of sight, head deflection angle and dynamic visual acuity; the driver behavior adaptation module includes an eye tracker, a head posture detection unit, and a calibration auxiliary device; wherein the eye tracker adopts Tobii Pro Glasses 3, with a sampling rate of 120Hz, an accuracy of ±0.5°, supports dynamic visual acuity (DVA) measurement, and captures the driver's gaze point position ( )、Pupil position( ) and diameter changes to evaluate the blind area; The head posture detection unit includes a 9-axis IMU integrated in the seat headrest and a wide-angle infrared camera installed in the car. The 9-axis IMU is used to detect the head deflection angle (±1° accuracy) and nodding / shaking frequency; the wide-angle infrared camera is used to assist in calibrating the head position and compensate for the IMU cumulative error; the calibration auxiliary equipment includes an LED calibration board, which is installed in the A-pillar, instrument panel and other positions in the car to provide reference points with known spatial coordinates, and is responsible for regularly calibrating the coordinate system alignment error between the eye tracker and the head posture detection unit.

[0033] The data processing and fusion module is used to process and optimize the data collected by each sensor and fuse multi-sensor parameters.

[0034] In this embodiment, the vehicle body state data (vehicle motion data), driver data (driver head state) and surrounding environment state data received by the data acquisition module are pre-processed and synchronized in time and space. Since the data format, sampling frequency, coordinate system and timestamp of different sensors may be different, data alignment must be achieved through standardization processing to provide consistent input for the subsequent fusion algorithm.

[0035] Specifically, for the data obtained through the CAN bus, the acceleration and angular velocity data output by the IMU (Inertial Measurement Unit) are denoised through Kalman filtering (KF) to reduce the error caused by vehicle body vibration; i. Define state variables: Input the state to be estimated as vehicle speed v and steering angle , the state vector for: ; Among them, k represents the discrete time step, corresponding to the sampling time of the CAN bus, , Represents the vehicle speed and steering angle at discrete time step k.

[0036] ii. Establish process model: ; in, and represents the state before and after the unit discrete time step, is process noise, which follows Gaussian distribution , is the state transition matrix, is the process noise covariance matrix; iii. Establish observation model, CAN bus directly measures vehicle speed and steering angle, observation equation With the observation matrix for: , ; Among them, the observation noise , obeys Gaussian distribution , represents the sensor noise; is the observation noise covariance matrix.

[0037] iv. Noise covariance matrix design: ; : Uncertainty of vehicle speed model; : Measurement noise variance of vehicle speed sensor.

[0038] : Uncertainty in the steering angle model; : Measurement noise variance of the steering angle sensor.

[0039] v. Kalman filter implementation steps: (1) Initialization (initial state and the error covariance matrix estimate): ; in, and Indicates the initial speed and steering angle of the car; and represents the error covariance between the initial vehicle speed and the initial steering angle estimate; (2) Predict the state and error covariance matrix based on the model: ; ; in, Represents the optimal estimated state at time k-1 Predict the prior state at time k; Represents the covariance of the optimal estimated state at time k-1 Predict the covariance of the prior state at time k; represents the transpose of the state transfer matrix F; (3) Fusion of observation data: Calculate the Kalman gain: ; in, is the Kalman gain matrix, is the transposed matrix of the observation matrix H; Status Update: ; in, is the posterior state estimate at time k; Covariance update: ; in, is the posterior state error covariance matrix at time k; vi. Parameter tuning and implementation details: Noise covariance adjustment: If the filtering result is too dependent on the model (significant lag), increase N or decrease Q; If the filtered result follows the observation too closely (insufficient noise suppression), decrease N or increase Q.

[0040] The data obtained by the millimeter wave radar (77GHz) is preprocessed in the following way: i. Noise filtering: Set the SNR threshold to remove invalid points with SNR < 10 dB; Filter out targets with speeds outside a reasonable range (e.g. v> 180km / h); ii. Use DBSCAN algorithm to perform target clustering: iii. Coordinate conversion: Convert Cartesian coordinates to polar coordinates.

[0041] The data obtained by LiDAR is preprocessed in the following way: i. Input: original 3D point cloud (300,000 points / second, including coordinates (x, y, z) and reflection intensity); ii. Ground point removal: Use the RANSAC algorithm to fit the ground plane equation , remove point; iii. Outlier filtering: Statistical filtering, removing outliers with a distance greater than the mean point; iv. Target segmentation: Set the threshold to 0.3m through Euclidean clustering to separate the obstacle point cloud clusters: (1) Building a search structure: storing the point cloud into a KD-Tree to accelerate neighbor queries; (2) Clustering core process: 2.1 Initialize the empty cluster list and unprocessed point queue; 2.2 Randomly select seed points and create new clusters; 2.3 Search all neighboring points within the radius r=0.3m of the seed point; 2.4 Add the neighboring points to the current cluster and push them into the queue; 2.5 Recursively process the points in the queue until no new points are added; 2.6 When the number of cluster points is greater than or equal to the threshold (e.g. 50 points), it is saved as a valid obstacle; (3) Post-processing: 3.1 Filter out small clusters (such as points < 50, which may be noise); 3.2 Output the point cloud cluster and bounding box of each obstacle.

[0042] v. Coordinate transformation: Convert the LiDAR coordinate system to the vehicle coordinate system (apply the external parameter matrix ).

[0043] The data obtained by the binocular camera is preprocessed in the following way: i. Image enhancement: Enhance details in low-light areas through CLAHE; ii. Distortion correction: Use the intrinsic parameter matrix K and distortion coefficient D to correct lens distortion; iii. Object detection: Output the object category (pedestrian / vehicle) and 2D bounding box through the YOLOv5 model; iv. Coordinate mapping: The 2D bounding box is projected to the vehicle coordinate system using the inverse perspective transformation (IPM).

[0044] The data obtained by the eye tracker is preprocessed in the following way: i. Input: original gaze point (m, n); ii. Noise filtering: Use median filtering, set the window size to 5 frames, and remove coordinate jumps caused by blinking; iii. Line of sight vector calculation: Unit vector conversion: ; in,( ) is the pupil coordinate, Represents the driver's line of sight shift information at time t; iv. Coordinate system conversion: Convert the eye tracker coordinate system to the vehicle coordinate system (apply the external parameter matrix ).

[0045] The data obtained by the head posture detection unit is preprocessed in the following way: i. Input: 9-axis IMU raw data (acceleration , angular velocity , sampling rate 100Hz); ii. Attitude solution: using quaternion update algorithm for analysis; iii. Coordinate system conversion: Convert the head coordinate system to the vehicle coordinate system (apply the external parameter matrix ).

[0046] This embodiment unifies the coordinate systems of the millimeter-wave radar, LiDAR, binocular camera, eye tracker, and 9-axis IMU to the vehicle coordinate system through the external parameter calibration method, uses a checkerboard calibration plate, and calculates the external parameter matrix between sensors through feature point matching.

[0047] In addition, in this embodiment, the spatiotemporal synchronization of data aims to align the timestamps and coordinate systems of multi-sensor data to ensure the fusion accuracy. Specifically, the hardware and software synchronize the time in two bits. The hardware provides the global UTC time (accuracy ±1ms) through the GPS timestamp, and the PXIe-6674T timing module is used to achieve μs-level time synchronization with a delay of <1ms. The software uses the interpolation alignment method to linearly interpolate the low-frequency data (LiDAR 10Hz) to generate sampling points synchronized with the high-frequency data (eye tracker 120Hz).

[0048] It should be noted that the above preprocessing method provided in this embodiment is only for illustration, and those skilled in the art may also adopt other methods to preprocess the acquired raw data. The preprocessing method of the raw data and the time-space synchronization method are not the key points of the present invention.

[0049] In this embodiment, the main blind spots on the outside of the car are divided into the front blind spot, the rear blind spot, the A-pillar blind spot (left and right), the B-pillar blind spot (left and right), and the C-pillar blind spot (left and right); multi-sensor data fusion is the core link of automobile blind spot monitoring, combining the advantages of radar (strong anti-interference), LiDAR (high-precision 3D modeling), and camera (target classification), covering the entire scene, and calculating the overall blind spot size through multi-blind spot coupling dynamic linkage, and predicting and correcting it through extended Kalman filtering; multi-blind spot coupling linkage calculation is combined with extended Kalman filtering (EKF) to optimize the blind spot calculation, thereby improving the accuracy, robustness and scene adaptability of the blind spot calculation.

[0050] Coordinate system selection: Establish a polar coordinate system with the vehicle's center of mass as the origin, with the horizontal direction as the polar axis and the vertical direction as the height axis, covering a 360° range.

[0051] In this embodiment, the basic blind area angle It is the static occlusion angle determined by the vehicle's fixed structure (such as the front, rear, A / B / C pillars, etc.). The geometric model method is calculated based on the size of the vehicle's fixed structure and its horizontal distance from the driver's eyes. The specific calculation method is as follows: iA-pillar blind spot: The A-pillar is the pillar between the windshield and the left and right front doors, and is located between the engine compartment and the passenger compartment. Due to the existence of the A-pillar, when the driver turns left or right, part of his vision will be blocked and he will not be able to see the area behind the A-pillar, thus forming an A-pillar blind spot; the basic blind spot angle of the A-pillar blind spot The geometric calculation formula is: ; in, Refers to the average width of the A-pillar, which is approximately between 0.1-0.15 m. Refers to the horizontal distance from the A-pillar to the driver's eyes; the A-pillar includes the left A-pillar and the right A-pillar. The left A-pillar corresponds to the left blind spot of the A-pillar, and the right A-pillar corresponds to the right blind spot of the A-pillar. The reference range is 6°-12° (for sedans), right blind spot of A-pillar The reference range is 5°-8° (sedan).

[0052] ii. B-pillar blind spot: The B-pillar is located between the front and rear seats in the cockpit and is a vertical pillar between the doors on both sides. When the vehicle is driving, especially when changing lanes or turning, the B-pillar will block the driver's view of the vehicle coming from behind, forming a B-pillar blind spot. Basic blind spot angle of the B-pillar blind spot The geometric calculation formula is: ; in, Refers to the average width of the B-pillar, which is approximately between 0.1-0.12 m. Refers to the horizontal distance from the B-pillar to the driver's eyes; the B-pillar includes the left B-pillar and the right B-pillar. The left B-pillar corresponds to the left blind spot of the B-pillar, and the right B-pillar corresponds to the right blind spot of the B-pillar. The left blind spot of the B-pillar The reference range is 5°-8° (for sedans), right blind spot of the B-pillar The reference range is 3°-5° (sedan).

[0053] iii. C-pillar blind spot: The C-pillar is located on both sides of the rear headrests and is the pillar between the rear windshield and the rear door. The existence of the C-pillar will block the driver's rear view to a certain extent, forming a C-pillar blind spot. Basic blind spot angle of the C-pillar blind spot The geometric calculation formula is: ; in, Refers to the lateral extension width of the C-pillar, which is approximately between 0.2-0.3 m. Refers to the horizontal distance from the C-pillar to the driver; the C-pillar includes the left C-pillar and the right C-pillar. The left C-pillar corresponds to the left blind spot of the C-pillar, and the right C-pillar corresponds to the right blind spot of the C-pillar. Left blind spot of the C-pillar The reference range is 12°-20° (for sedans), right blind spot of the C-pillar The reference range is 10°-15° (sedan), and it is more significant for MPV / SUV models.

[0054] iv. Front blind spot: The front blind spot refers to the area below the front of the vehicle that the driver cannot directly see when sitting in the driver's seat. The geometric calculation formula is: ; in, Refers to the height of the hood, which is approximately between 0.8-1.2 m. Refers to the distance from the front of the vehicle to the driver. The reference range is 15°-25° (3-4 meters longitudinally in the blind spot of the front of the SUV) and 10°-18° (sedan).

[0055] v. Rear blind spot: The rear blind spot refers to the area below the rear of the vehicle that the driver cannot see through the rearview mirror or direct observation. Basic blind spot angle of the rear blind spot The geometric calculation formula is: ; in, Refers to the height of the bottom edge of the rear window, which is approximately between 0.5-0.8 m. Refers to the distance from the rear of the vehicle to the driver. The reference range is 20°-30° (covering the area within 5 meters of the rear of the vehicle).

[0056] In this embodiment, the inner wheel difference blind spot expansion calculation plays a key role in the automobile blind spot calculation. Its core is to dynamically correct the changes in the blind spot range caused by vehicle turning, thereby improving the accuracy and safety of blind spot monitoring. By real-time analysis of vehicle steering parameters (such as steering angle, wheelbase), the blind spot boundary is dynamically adjusted to solve the problem that the traditional static model cannot reflect the expansion of the blind spot when turning.

[0057] Inner wheel difference length The calculation formula is: ; in, is the steering angle of the car, and B is the wheelbase of the vehicle.

[0058] Blind zone i angle increment The calculation formula is: ; in, is the reference distance for monitoring blind area i, when When the blind spot angle increment The calculation formula can be simplified as: ; Will and Substitute the relationship into the steering angle correction coefficient : Simplifying via trigonometric identities : ; Reference distance for blind spot monitoring , blind zone i angle increment It can be approximated as: ; This gives the correction factor: ; The larger the inner wheel difference length, the further the rear wheel trajectory deviates from the front wheel when turning, and the wider the blind spot coverage.

[0059] In this embodiment, the reference distance r for each blind spot monitoring can be determined according to the model of the sensor actually used. Table 2 shows the recommended values ​​of the reference distance r in different scenarios. The recommended values ​​are set with reference to the requirements of international standards such as ISO 17387 for blind spot monitoring systems.

[0060] Table 2 Recommended values ​​of reference distance r for blind spot monitoring in different scenarios

[0061] In this embodiment, dynamic visual acuity (DVA) refers to the ability to clearly identify the details of an object in motion (such as when the subject or the target is moving), usually expressed as the minimum discernible visual angle (degrees of angle) or the level of the visual acuity chart. It mainly affects the ability to process information simultaneously in a dynamic environment. The geometric relationship between dynamic visual acuity (DAV) and the visual field range is analyzed as follows: Speed ​​and dynamic vision attenuation curve: ;

[0062] in: is static visual acuity (refer to the international standard visual acuity chart), v is the relative speed of the car (km / h), k is the attenuation coefficient, and the reference value is 0.02.

[0063] The relationship between the dynamic vision attenuation curve and the visual field attenuation angle is: ; in: is the field of view attenuation angle; is the field of view angle under static conditions; is the attenuation coefficient, which is 0.9 (based on the calibration value of the ISO 15007-2 standard dynamic vision experiment), indicating the compression ratio of the visual field due to the decrease in DVA. Table 3 shows the relationship between the driver's visual field attenuation and the driving speed, taking the driver's basic visual field angle of 180° and static vision of 1.0 as an example.

[0064] Table 3 Relationship between driver's field of vision attenuation and vehicle speed Driving speed (km / h) Field of view attenuation (°) 10 29.19 20 53.11 30 72.73 40 88.81 50 102.00 60 112.81 70 121.67 80 128.94 90 134.89 100 139.78 110 143.78 120 147.06 130 149.75

[0065] In this embodiment, the driver's sight line vector conversion formula is: ; in:( ) is the pupil coordinate, ( m , n ) is the position of the eye gaze point, Represents the driver's line of sight shift information at time t; Driver's head steering angle at time t It is collected and processed by the head posture detection unit.

[0066] In this embodiment, the independent dynamic model of each blind spot and the dynamic linkage model of multiple blind spots are designed as follows: Mathematical model for basic calculation of blind area: ; in: Represents the basic blind area angle; Represents the reference value of the dynamic correction coefficient, where , , , .

[0067] Compensation for environmental factors, introduction of weather compensation coefficient (1.0 for sunny days, 1.2 for rainy and foggy days, dimensionless), corrected blind spot angle: ;

[0068] in, is the corrected blind spot angle, Represents the blind spot angle before correction; Independent dynamic model for each blind area: ; in: Represents the dynamic blind spot angles of different areas of the car at time t, i The values ​​are A left, A right, B left, B right, C left, C right, front, and back, corresponding to A pillar left, A pillar right, B pillar left, B pillar right, C pillar left, C pillar right, front of the vehicle, and back of the vehicle respectively; Represents the basic blind spot angles of different areas of the car; Represents the dynamic correction coefficient related to the attenuation of the vision of different areas of the car due to speed, Represents the dynamic correction coefficient related to the angle increment of different areas of the car, Represents the dynamic correction coefficient related to the driver's head steering angle in different areas of the car, Represents the dynamic correction factor related to the driver's sight direction in different areas of the car; Weather compensation factor; Adjust parameters according to actual conditions: For the A-pillar blind spot, the vehicle speed v Influence the forward movement of the gaze point through Corrected to 0.08 ° / km / h, steering angle Small impact, Set to 0.

[0069] For the blind spot in front of the vehicle, the speed v Influence the forward movement of the gaze point through Corrected to 0.15 ° / km / h, the front blind spot is not sensitive to the steering angle, Set to 0.

[0070] The rear blind spot is mainly determined by the rear window structure and is less affected by dynamic factors, which can be simplified as follows: .

[0071] After adjustment, each blind area has independent dynamic models: ; Multi-blind zone dynamic linkage model: ; Where: i represents the blind spot area of ​​the car that changes under the influence of multiple factors; j represents the blind spot area affected by the changes of other blind spots; : coupling coefficient; Represents the dynamic angle range of blind spot j under the influence of other blind spots at time t (the value range of i, j is A left, A right, B left, B right, C left, C right, front, and rear, corresponding to A pillar left, A pillar right, B pillar left, B pillar right, C pillar left, C pillar right, front of the vehicle, and rear of the vehicle respectively).

[0072] Furthermore, in this embodiment, the blind spot calculation is optimized by combining multi-blind spot coupling linkage calculation with extended Kalman filter (EKF), thereby improving the accuracy, robustness and scene adaptability of the blind spot calculation: a. State vector expansion: ;

[0073] in: is the speed of the car; is the steering angle of the car; The position of the fixation point in the direction of eye gaze; The driver's head steering angle; d represents the vector dimension.

[0074] b. Establish process model: State transfer equation: ; in: Represents the blind spot angles of different areas of the car in the latter state; Represents the blind spot angle expansion range under different influences in the previous state; is the field of view attenuation angle in state k, is the blind area angle increment in state k, is the driver's head steering angle in state k, is the driver's sight shift information in state k, Represents process noise and follows a Gaussian distribution , is the process noise covariance matrix; ; in, is the variance of each parameter; c. Establish observation model: Observation equation: ; in, is the observation noise, which follows a Gaussian distribution , represents the sensor noise, is the observation noise covariance matrix.

[0075] d. Extended Kalman filter implementation steps: (1) Prediction stage Extended Equation of State Predicts: ; in, Represents the optimal estimated state at time k-1 Predict the prior state at time k; is the process noise; is a nonlinear state transfer function; ; in, is the control input vector, which is acceleration, vehicle steering angular velocity, head and eye steering angular velocity; S is the parameter matrix , is the time step.

[0076] At each step k, the nonlinear function and Performing a first-order Taylor expansion, we can obtain exist The Jacobian matrix of exist The Jacobian matrix of : , ;in represent right Find the partial derivative, represent right Find the partial derivative.

[0077] Error covariance prediction: ; in, represents the process noise, Represents the covariance of the optimal estimated state at time k-1 Predict the covariance of the prior state at time k; (2) Update phase: Calculate the Kalman gain: ; in, represents the observation noise; Status Update: ; Covariance update: ; Dynamic coupling parameter optimization: adding online learning strategy: , ; in, represents the change in coupling coefficient, represent right Find partial derivatives, learning rate =0.01, constraints: .

[0078] Embodiment 2: like Figure 3 As shown, this embodiment provides a vehicle control method, the method comprising the following steps: Step A. Calculate the dynamic angle range of the blind spot in each area based on the blind spot monitoring method of Example 1; Step B. Determine the risk index of each blind spot according to the data transmitted by the data acquisition module and based on the dynamic angle range calculated in step A, and perform weighted summation of the linkage risk indexes of each blind spot to obtain a global comprehensive risk index; Step C. The risk assessment and classification module determines the risk level based on the global comprehensive risk index, classifies the vehicle according to its risk level, and controls the vehicle at the same time.

[0079] This embodiment adopts the calculation method of the blind spot risk index of the SAE J2804 standard, and integrates it with the multi-blind spot risk index model to optimize it into a partition risk index model. The specific steps are as follows: The SAE J2804 standard defines the calculation method of the blind spot risk index, and its core formula is: ; Among them: blind spot area refers to the blind spot coverage area calculated by the model (unit: m2); traffic flow density refers to the number of potential obstacles in the blind spot per unit time (unit: number / second); driver reaction time refers to the time from sensing danger to taking action (unit: second); sensor coverage rate refers to the proportion of the sensor's effective detection range to the total blind spot area (unit: %).

[0080] Fusion optimization of multiple blind zone risk index models: (1) Calculation of the risk index for each blind spot (left of A-pillar, right of A-pillar, left of B-pillar, right of B-pillar, left of C-pillar, right of C-pillar, front of the vehicle, and rear of the vehicle) : ; in: is the dynamic angle of blind spot j (calculated based on linkage model), is the reference distance for blind spot j monitoring; is the traffic flow density of blind spot j (number of obstacles / second); is the driver reaction time in blind spot j (extended when distracted); is the sensor coverage of blind spot j (reduced in rainy and foggy weather).

[0081] (2) Comprehensive risk index: The weighted sum of the blind area linkage risk indexes is used to obtain the global comprehensive risk index: ; in, is the weight of blind spot j; the specific weight distribution is: A-pillar (left and right) blind spot: (The risk is significant when turning); Blind spot in front of the vehicle: (Low-speed scenes are of high importance); B and C pillars (left and right), rear blind spot: (Relies on active observation by the driver).

[0082] In this embodiment, based on the comprehensive risk index Determine the risk level, classify it and issue warnings, while controlling the vehicle, as follows: like If the range is 1.0-2.0, the risk level is considered to be level 1. At this time, the LED warning light inside the vehicle is controlled to flash at a frequency of 2Hz, and an audible and visual prompt is given to alert the driver; like If the range is 2.0-3.0, the risk level is considered to be level 2, and the vehicle's steering wheel is controlled to vibrate at an intensity of 5Hz. At the same time, a voice announcement is made saying "the blind spot on one side is dangerous"; like If the range is >3.0, the risk level is considered to be level 3 (emergency warning). At this time, the automatic brake pre-charge (shortening the braking distance by 0.5 meters) and forced lane keeping are performed. This method can effectively control the scale of the conflict in a timely manner, avoid major traffic accidents, and reduce casualties. In addition, after the emergency brake is triggered, if the driver presses the accelerator pedal >50%, the braking intervention will be terminated immediately.

[0083] Embodiment 3:

[0084] like Figure 4 As shown, this embodiment provides a vehicle control system, the system includes a data acquisition module, a data processing and fusion module, a blind spot independent dynamic model, a multi-blind spot dynamic linkage model, a risk index calculation module, a risk assessment and classification module, and a control module; The data acquisition module is used to collect the driver's head state, the vehicle's own motion data and the surrounding environment changes, send them to the data processing and fusion module, and store them in the database; the data acquisition module includes a vehicle state perception module, an environment perception module, and a driver behavior adaptation module; The vehicle state perception module acquires vehicle ECU (electronic control unit) data through the CAN bus and collects vehicle kinematic parameters in real time; the environment perception module collects vehicle surrounding environment parameters in real time through multi-source sensor fusion, and the multi-source sensor includes millimeter wave radar (77GHz), optical radar (LiDAR), and binocular camera; the driver behavior adaptation module monitors the driver's physiological and behavioral characteristics in real time, and the driver behavior adaptation module includes an eye tracker and a head posture detection unit (head tracking device); The data processing and fusion module is used to perform data preprocessing and spatiotemporal synchronization on the original data, realize data alignment, and fuse multi-source data at the same time; The blind spot independent dynamic model is used to calculate the dynamic blind spots in different areas of the car; The multi-blind zone dynamic linkage model is used to calculate the dynamic blind zones of each area under the mutual influence of different areas of the car; The risk index calculation model is used to calculate the linkage risk index of each blind spot, and to obtain a global comprehensive risk index by weighted summation of the linkage risk indexes of each blind spot; The risk assessment and grading module is used to determine the risk level based on the global comprehensive risk index and to grade the risk level by level; The control module is used for early warning and vehicle control according to the risk level.

[0085] The present invention also provides an electronic device, comprising: one or more processors and a memory; wherein the memory is used to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned vehicle control method.

[0086] The present invention also provides a computer-readable medium having a computer program stored thereon, wherein the computer program implements the above-mentioned vehicle control method when executed by a processor.

[0087] Those skilled in the art will appreciate that all or part of the functions of the various methods / modules in the above embodiments may be implemented by hardware or by computer programs. When all or part of the functions in the above embodiments are implemented by computer programs, the program may be stored in a computer-readable storage medium, which may include: a read-only memory, a random access memory, a disk, an optical disk, a hard disk, etc. The program is executed by a computer to implement the above functions. For example, the program is stored in the memory of the device, and when the program in the memory is executed by the processor, all or part of the above functions can be implemented.

[0088] In addition, when all or part of the functions in the above-mentioned embodiments are implemented by means of a computer program, the program can also be stored in a storage medium such as a server, another computer, a disk, an optical disk, a flash drive or a mobile hard disk, and saved to the memory of a local device by downloading or copying, or the system of the local device is updated. When the program in the memory is executed by the processor, all or part of the functions in the above-mentioned embodiments can be implemented.

[0089] The above specific examples are used to illustrate the present invention, which is only used to help understand the present invention and is not intended to limit the present invention. For those skilled in the art of the present invention, according to the idea of ​​the present invention, some simple deductions, deformations or substitutions can be made. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A blind spot monitoring method based on dynamic changes of multiple factors, characterized in that: The method comprises the following steps: Step 1. The data acquisition module collects the driver's head status, vehicle movement data and surrounding environment changes, and sends them to the data processing and fusion module; Step 2. The data processing and fusion module performs data preprocessing and spatiotemporal synchronization on the raw data obtained from the data acquisition module, realizes data alignment, and fuses multi-source data at the same time; Step 3. Divide the main blind spots outside the car into the front blind spot, the rear blind spot, the A-pillar blind spot, the B-pillar blind spot, and the C-pillar blind spot, and calculate the basic blind spot angle of each area based on the size of the vehicle fixed structure and its distance from the driver; wherein the A-pillar blind spot includes the A-pillar left blind spot and the A-pillar right blind spot, the B-pillar blind spot includes the B-pillar left blind spot and the B-pillar right blind spot, and the C-pillar blind spot includes the C-pillar left blind spot and the C-pillar right blind spot; Step 4. Establish an independent dynamic model for each blind spot and a dynamic linkage model for multiple blind spots, and calculate the dynamic angle range of each blind spot based on the dynamic linkage model for multiple blind spots; wherein, the independent dynamic model for each blind spot is: ； in, Represents the dynamic blind spot angles of different areas of the car at time t, i The values ​​are A left, A right, B left, B right, C left, C right, front, and back, corresponding to A pillar left, A pillar right, B pillar left, B pillar right, C pillar left, C pillar right, front of the vehicle, and back of the vehicle respectively; Represents the basic blind spot angles of different areas of the car; Represents the dynamic correction coefficients related to the angle increments in different areas of the car; Weather compensation factor; is the field of view attenuation angle; is the blind area angle increment; Represents the driver's head steering angle at time t; Represents the driver's line of sight shift information at time t; The multi-blind zone dynamic linkage model is: ； Where: i represents the blind spot area of ​​the car that changes under the influence of multiple factors; j represents the blind spot area affected by the changes of other blind spots; is the coupling coefficient; Represents the dynamic angle range of blind spot j under the influence of other blind spots at time t; the value range of i, j is A left, A right, B left, B right, C left, C right, front, and rear, corresponding to A pillar left, A pillar right, B pillar left, B pillar right, C pillar left, C pillar right, front of the vehicle, and rear of the vehicle respectively.

2. The method for monitoring blind spots based on dynamic changes of multiple factors according to claim 1 is characterized in that: The adaptive adjustment rule of coupling coefficient is: ； in: is the basic coupling strength, is the vehicle speed sensitivity coefficient, v is the speed of the car; is the steering angle attenuation coefficient, is the steering angle of the car.

3. The blind spot monitoring method based on multi-factor dynamic changes according to claim 1 is characterized in that: Basic blind spot angle of A-pillar blind spot The geometric calculation formula is: ； in, Refers to the average width of the A-pillar, Refers to the horizontal distance from the A-pillar to the driver's eyes; the A-pillar includes the left A-pillar and the right A-pillar. The left A-pillar corresponds to the left blind spot of the A-pillar, and the right A-pillar corresponds to the right blind spot of the A-pillar. Basic blind spot angle of B-pillar blind spot The geometric calculation formula is: ； in, Refers to the average width of the B-pillar, Refers to the horizontal distance from the B-pillar to the driver's eyes; the B-pillar includes the left B-pillar and the right B-pillar. The left B-pillar corresponds to the left blind spot of the B-pillar, and the right B-pillar corresponds to the right blind spot of the B-pillar. Basic blind spot angle of C-pillar blind spot The geometric calculation formula is: ； in, Refers to the lateral extension width of the C-pillar. Refers to the horizontal distance from the C-pillar to the driver; the C-pillar includes the left C-pillar and the right C-pillar. The left C-pillar corresponds to the left blind spot of the C-pillar, and the right C-pillar corresponds to the right blind spot of the C-pillar. Basic blind spot angle of the front blind spot The geometric calculation formula is: ； in, Refers to the height of the hood, Refers to the distance from the front of the vehicle to the driver; Basic blind spot angle of the rear blind spot The geometric calculation formula is: ； in, Refers to the height of the bottom edge of the rear window. Refers to the distance from the rear of the vehicle to the driver.

4. The method for monitoring blind spots based on dynamic changes of multiple factors according to claim 1 is characterized in that: The expression of the driver's sight shift information is: ； Among them, (m, n) is the original fixation point, ( ) are pupil coordinates; The expression of blind spot angle increment is: ； The expression of the dynamic correction coefficient related to the angle increment of different areas of the car is: ； in, is the reference distance for monitoring blind spot i, is the steering angle of the car, B is the wheelbase of the vehicle; The expression of the field of view attenuation angle is: ； in, is the field of view attenuation angle; is the field of view angle under static conditions; is the attenuation coefficient; DAV is the dynamic visual acuity.

5. The method for monitoring blind spots based on dynamic changes of multiple factors according to claim 1 is characterized in that: When calculating the dynamic angle range of the blind spots in each area, an online learning strategy is added to optimize the coupling parameters based on the extended Kalman filter algorithm.

6. The method for monitoring blind spots based on dynamic changes of multiple factors according to claim 4 is characterized in that: The relationship between dynamic visual acuity and speed is: ； in, For static vision, v is the relative speed of the car, k is the attenuation coefficient.

7. A vehicle control method, characterized in that: The method comprises the following steps: Step A. Calculate the dynamic angle range of the blind spot in each area based on the blind spot monitoring method based on multi-factor dynamic changes according to any one of claims 1 to 6; Step B. Determine the linkage risk index of each blind spot according to the data transmitted by the data acquisition module and based on the dynamic angle range calculated in step A, and perform weighted summation of the linkage risk indexes of each blind spot to obtain a global comprehensive risk index; Step C. The risk assessment and classification module determines the risk level based on the global comprehensive risk index, classifies the vehicle according to its risk level, and controls the vehicle at the same time.

8. A vehicle control method according to claim 7, characterized in that: The linkage risk index for each blind spot The calculation method is: ； in: is the dynamic angle of the blind spot j, is the reference distance for blind spot j monitoring; is the traffic flow density of blind spot j; is the driver reaction time in blind spot j; is the sensor coverage of blind spot j; The global comprehensive risk index is calculated as follows: ； in, is the weight of blind zone j.

9. A vehicle control system, characterized in that: The control system is used to implement the vehicle control method according to claim 7 or 8, including a data acquisition module, a data processing and fusion module, a blind spot independent dynamic model, a multi-blind spot dynamic linkage model, a risk index calculation module, a risk assessment and classification module, and a control module; The data acquisition module is used to collect the driver's head status, the vehicle's own motion data and the surrounding environment changes, send them to the data processing and fusion module, and store them in the database; The data processing and fusion module is used to perform data preprocessing and spatiotemporal synchronization on the original data, realize data alignment, and fuse multi-source data at the same time; The blind spot independent dynamic model is used to calculate the dynamic blind spots in different areas of the car; The multi-blind zone dynamic linkage model is used to calculate the dynamic blind zones of each area under the mutual influence of different areas of the car; The risk index calculation model is used to calculate the linkage risk index of each blind spot, and to obtain a global comprehensive risk index by weighted summation of the linkage risk indexes of each blind spot; The risk assessment and grading module is used to determine the risk level based on the global comprehensive risk index and to grade the risk level by level; The control module is used for early warning and vehicle control according to the risk level.

10. A vehicle control system according to claim 9, characterized in that: The data acquisition module includes a vehicle state perception module, an environment perception module, and a driver behavior adaptation module; wherein the vehicle state perception module obtains the vehicle electronic control unit data through the CAN bus and collects the vehicle kinematic parameters in real time; the environment perception module collects the vehicle surrounding environment parameters in real time through multi-source sensor fusion, and the multi-source sensor includes a millimeter wave radar, an optical radar, and a binocular camera; the driver behavior adaptation module monitors the driver's physiological and behavioral characteristics in real time, and the driver behavior adaptation module includes an eye tracker and a head posture detection unit.

Images