Blind spot monitoring and alarm methods, electronic equipment, vehicles, media, and software products

Abstract

This application relates to the field of vehicle driving technology, and in particular to a blind spot monitoring and alarm method, electronic device, vehicle, medium, and program product. The method includes: determining that a target obstacle exists in the vehicle's blind spot, wherein the target obstacle meets alarm conditions, including: the target obstacle is not located in a non-drivable area; and performing blind spot monitoring and alarm. It is understood that the alarm conditions for the target obstacle include that it is not located in a non-drivable area. This can directly filter out obstacles that are in the vehicle's blind spot but in a non-drivable area, avoiding false alarms from a large number of obstacles that do not pose a collision risk, thereby improving the accuracy of the alarm.

Description

Technical Field

[0001] This application relates to the field of vehicle driving technology, and in particular to a blind spot monitoring and alarm method, electronic equipment, vehicle, medium, and program product. Background Technology

[0002] Currently, when drivers observe the surrounding traffic environment through external rearview mirrors while driving, there is a certain blind spot. With the promotion of driver assistance technology, some vehicles are equipped with blind spot detection functions. For example, vehicles equipped with blind spot detection (BSD) systems use radars installed on both sides of the rear of the vehicle to detect the traffic environment in a preset monitoring area (i.e., the blind spot) to the side and rear of the vehicle. When the system determines that there is a fast-moving vehicle in the monitoring area, it can alert the driver of the current vehicle through audible and visual alarms or dashboard prompts, requiring them to avoid the vehicle.

[0003] However, existing blind spot monitoring functions rely on radar-collected detection data to check for vehicles in blind spots, but cannot accurately determine whether a vehicle in the blind spot poses a collision risk to the current vehicle. When a vehicle frequently triggers warnings for the blind spot, and the driver realizes that the vehicle in the blind spot does not pose a collision risk, it affects the driver's experience. In particular, if the vehicle in the blind spot does not pose a collision risk, repeated warnings may cause the driver to become less vigilant, greatly increasing the likelihood of a collision. Summary of the Invention

[0004] This application provides a blind spot monitoring and alarm method, electronic device, vehicle, medium, and program product to improve the accuracy of blind spot monitoring alarms.

[0005] Firstly, a blind spot monitoring and alarm method is provided, the method comprising: determining that there is a target obstacle in the vehicle's monitoring blind spot, wherein the target obstacle meets alarm conditions, the alarm conditions including: the target obstacle is not located in a non-drivable area; and performing blind spot monitoring and alarm.

[0006] Understandably, the alarm conditions for target obstacles include that the target obstacle is not located in a non-drivable area. This can directly filter out obstacles that are in the vehicle's blind spot but in a non-drivable area, thus avoiding a large number of false alarms for obstacles that do not pose a collision risk, thereby improving the accuracy of the alarm.

[0007] In one possible implementation of the first aspect, the non-drivable area includes: a physical barrier area and a custom-defined no-driving area, wherein the physical barrier area includes: the area outside the physical fence closest to the vehicle, and the area in the lane where the vehicle is located that is less than or equal to a first preset distance from the physical fence, and the physical fence includes at least one of the following: curb, guardrail, water-filled barrier, fence; the custom-defined no-driving area includes: the area outside the nearest double solid line of the vehicle, and the area that is greater than or equal to a second preset distance from the nearest double solid line.

[0008] Understandably, obstacles in physical blocking areas and custom no-driving zones are areas where there is no risk of collision with the vehicle. If the target obstacle is not in the no-driving zone, no alarm will be triggered, thus filtering out obstacles in the no-driving zone, avoiding false alarms, and improving the accuracy of alarms.

[0009] In one possible implementation of the first aspect, determining that a target obstacle exists in the vehicle's monitoring blind spot includes: acquiring vehicle information and perceived obstacles around the vehicle; generating the vehicle's monitoring blind spot based on the vehicle information, and selecting preliminary obstacles that meet alarm conditions from the perceived obstacles around the vehicle; and determining that a target obstacle exists in the vehicle's monitoring blind spot based on the preliminary obstacles and the monitoring blind spot.

[0010] In one possible implementation of the first aspect, generating a vehicle monitoring blind spot based on vehicle information includes: identifying the vehicle's driving state type based on the vehicle information; generating a vehicle monitoring blind spot according to the driving state type and a preset blind spot generation method corresponding to the driving state type, wherein the geometric parameters of the generated monitoring blind spot are different for different driving state types.

[0011] In one possible implementation of the first aspect, the driving state type includes at least one of the following: driving on continuous curves and driving on non-continuous curves.

[0012] In one possible implementation of the first aspect, when the driving state type is non-continuous curve driving, the preset blind spot generation method includes: determining the rectangular boundary coordinates of the monitoring blind spot based on the distance from the rear axle to the B-pillar of the vehicle, the preset safe forward extension distance, the vehicle width, and the preset blind spot lateral extension distance; and generating monitoring blind spots located on both sides of the vehicle based on the rectangular boundary coordinates.

[0013] In one possible implementation of the first aspect, when the driving state type is continuous curve driving, a preset blind spot generation method is included: obtaining the sector parameters of the first monitoring blind spot according to the turning radius and width of the vehicle and a preset annular sector calculation method, wherein the sector parameters include the inner arc length, the outer arc length and the sector angle; and generating monitoring blind spots located on both sides of the vehicle according to the sector parameters.

[0014] In one possible implementation of the first aspect, the alarm conditions further include at least one of the following: the type of the target obstacle is a vehicle; the speed of the target obstacle meets a preset speed threshold; the heading angle difference between the target obstacle and the vehicle is less than a preset heading angle difference; and the perception duration corresponding to the target obstacle reaches a preset perception duration.

[0015] Understandably, the alarm conditions for target obstacles restrict the type, speed, and heading angle of the target obstacles that need to be alarmed. This allows us to identify obstacles that pose a greater risk of collision to the vehicle if they move faster and their heading is the same as the vehicle's. Alarming when there are obstacles that pose a greater risk of collision to the vehicle can improve the effectiveness of the alarm.

[0016] In one possible implementation of the first aspect, determining that a target obstacle exists in the vehicle's monitoring blind spot based on preliminary obstacle selection and monitoring blind spot includes: acquiring preliminary obstacle selection; selecting candidate obstacles located in a candidate monitoring area from the preliminary obstacle selection; wherein the range of the candidate monitoring area is larger than the monitoring blind spot, and the candidate monitoring area includes the monitoring blind spot; and determining the target obstacle from the candidate obstacles.

[0017] In one possible implementation of the first aspect, determining the target obstacle from the candidate obstacles includes: when the number of candidate obstacles is equal to 1, if the candidate obstacle is located within the vehicle's monitoring blind spot, designating the candidate obstacle as the target obstacle; or, if the candidate obstacle is located within the vehicle's monitoring blind spot and the candidate obstacle meets the collision time condition, designating the candidate obstacle as the target obstacle.

[0018] In one possible implementation of the first aspect, determining the target obstacle from the candidate obstacles includes: when the number of candidate obstacles is greater than or equal to 2, and there is a through obstacle among the candidate obstacles that satisfies the sandwich passage condition, the through obstacle that is closest to the vehicle in longitudinal distance or has the shortest collision time and is located in the monitoring blind zone is selected as the target obstacle; or, the through obstacle that is closest to the vehicle in longitudinal distance or has the shortest collision time, is located in the monitoring blind zone, and whose collision with the vehicle satisfies the collision time condition is selected as the target obstacle.

[0019] In one possible implementation of the first aspect, determining the target obstacle from the candidate obstacles includes: when the number of candidate obstacles is greater than or equal to 2 and the sandwich passage condition is not met, selecting the candidate obstacle that is closest to the vehicle in longitudinal distance or has the shortest collision time and is located in the monitoring blind zone as the target obstacle; or, selecting the candidate obstacle that is closest to the vehicle in longitudinal distance or has the shortest collision time, is located in the monitoring blind zone, and whose collision with the vehicle meets the collision time condition as the target obstacle.

[0020] In one possible implementation of the first aspect, the sandwich passage condition includes: the width of the candidate obstacle is less than the lateral clearance distance between the vehicle and the nearest longitudinal candidate obstacle; the position of the candidate obstacle is located within the lateral interval corresponding to the clearance between the two nearest outer edges of the vehicle body and the nearest longitudinal candidate obstacle; the candidate obstacle has a tendency to move closer to the vehicle; and the candidate obstacle remains stable relative to the tendency to move closer to the vehicle.

[0021] In one possible implementation of the first aspect, the tendency of a candidate obstacle to move closer to the vehicle is determined by the following method: when the longitudinal velocity of the candidate obstacle is greater than the longitudinal velocity of the vehicle and the lateral distance between the candidate obstacle and the vehicle is less than a lateral distance threshold, the tendency of the candidate obstacle to move closer to the vehicle is determined by the following method: when the number of tracking frames of the candidate obstacle is greater than a preset number of tracking frames, the velocity confidence of the candidate obstacle is greater than a confidence threshold, and the velocity magnitude of the candidate obstacle is greater than a velocity magnitude threshold, the tendency of the candidate obstacle to move closer to the vehicle is determined to be stable.

[0022] In one possible implementation of the first aspect, the collision time condition includes: when the vehicle is not turning or making a U-turn, the collision time from the candidate obstacle to the vehicle is less than or equal to a collision time threshold; when the vehicle is turning or making a U-turn, the collision time from the candidate obstacle to the vehicle is less than or equal to a collision time extension threshold, wherein the collision time extension threshold is greater than the collision time threshold.

[0023] Understandably, when a vehicle is turning or making a U-turn, the vehicle speed is relatively slow, and the risk of collision between the vehicle and the obstacle is low. Increasing the collision time between the obstacle and the vehicle to be less than or equal to the collision time extension threshold can prevent redundant alarms from being triggered.

[0024] In one possible implementation of the first aspect, blind spot monitoring alarm includes: when a vehicle intends to change lanes, increasing the alarm level for blind spot monitoring alarm of the vehicle; and issuing an alarm according to the alarm method corresponding to the increased alarm level.

[0025] In a second aspect, an electronic device is provided, comprising: a memory for storing instructions; and at least one processor for executing the instructions to cause the electronic device to implement the blind spot monitoring and alarm method of the first aspect and any of the various possible implementations of the first aspect.

[0026] Thirdly, a vehicle is provided that stores instructions, which are executed on the vehicle, enabling the vehicle to implement the blind spot monitoring and alarm method described in the first aspect and any of the various possible implementations of the first aspect.

[0027] Fourthly, a computer-readable storage medium is provided, on which instructions are stored, which, when executed on a computer, cause the computer to perform the blind zone monitoring and alarm method described in the first aspect and any of the various possible implementations of the first aspect.

[0028] Fifthly, a computer program product is provided, which, when run on a device, enables the device to implement the blind zone monitoring and alarm method described in the first aspect and any of the various possible implementations of the first aspect. Attached Figure Description

[0029] Figure 1 According to some embodiments of this application, a driving schematic diagram of a vehicle 100 is shown.

[0030] Figure 2 According to some embodiments of this application, a flowchart of a blind spot monitoring and alarm method is shown.

[0031] Figure 3A According to some embodiments of this application, a schematic diagram of a specific process for determining the presence of a target obstacle in the monitoring blind spot of a vehicle is shown.

[0032] Figure 3B According to some embodiments of this application, a schematic diagram of a specific process for generating vehicle monitoring blind spots based on vehicle information is shown.

[0033] Figure 3C According to some embodiments of this application, a schematic diagram of a ring-shaped sector-shaped monitoring blind zone is shown.

[0034] Figure 4 According to some embodiments of this application, a flowchart of another blind spot monitoring and alarm method is shown.

[0035] Figure 5 According to some embodiments of this application, a schematic diagram of a sandwich passage scenario is shown.

[0036] Figure 6 According to some embodiments of this application, another schematic diagram of a sandwich passage scenario is shown.

[0037] Figure 7 According to some embodiments of this application, a schematic diagram of the structure of an electronic device 10' is shown.

[0038] Figure 8 According to some embodiments of this application, a structural schematic diagram of a vehicle 100 is shown. Detailed Implementation

[0039] The illustrative embodiments of this application include, but are not limited to, blind spot monitoring and alarm methods, electronic devices, vehicles, media, and program products.

[0040] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0041] Figure 1 According to some embodiments of this application, a driving schematic diagram of a vehicle 100 is shown. For example... Figure 1 As shown, when vehicle 100 is driving on the road, its Blind Spot Detection (BSD) system can detect surrounding obstacles. When vehicle 100 detects a fast-moving vehicle 200 in the BSD blind spot M1 using its corner radar, it will alert the driver of the vehicle to the presence of a vehicle in the blind spot through audible and visual alarms or dashboard prompts, requiring the driver to avoid the vehicle.

[0042] However, since vehicle 200 and vehicle 100 are separated by a fence Z1, a collision between vehicle 200 and vehicle 100 is impossible. Therefore, false alarms will occur, affecting the driver's experience. When vehicle 100 frequently triggers the alarm, the driver will become less vigilant, making a collision highly likely.

[0043] Therefore, to address the aforementioned problems, this application provides a blind spot monitoring and alarm method. In this method, a target obstacle is identified within the vehicle's blind spot, and this target obstacle meets alarm conditions, including that the target obstacle is not located in a non-drivable area. Blind spot monitoring and alarming are then performed. This method filters out obstacles that are within the vehicle's blind spot but in a non-drivable area, avoiding false alarms from numerous obstacles that do not pose a collision risk, thereby improving the accuracy of the alarm.

[0044] Figure 2 According to some embodiments of this application, a flowchart of a blind spot monitoring and alarm method is shown. The method is illustrated using a vehicle-mounted infotainment system as an example. The specific steps are as follows:

[0045] S201, It is determined that there is a target obstacle in the vehicle's monitoring blind spot, wherein the target obstacle meets the alarm conditions, including: the target obstacle is not located in a non-drivable area.

[0046] In addition, in some embodiments, the alarm conditions include at least one of the following: the type of the target obstacle is a vehicle; the speed of the target obstacle meets a preset speed threshold; the heading angle difference between the target obstacle and the vehicle is less than a preset heading angle difference; and the perception duration corresponding to the target obstacle reaches a preset perception duration.

[0047] The non-driving areas include: physical blocking areas and custom-defined no-driving areas. The physical blocking areas include: areas outside the physical fence closest to the vehicle, and areas where the distance to the physical fence is less than or equal to a first preset distance. The physical fence includes at least one of the following: curb, guardrail, water-filled barrier, and fence. The custom-defined no-driving areas include: areas outside the double solid lines closest to the vehicle, and areas where the distance to the nearest double solid lines is greater than or equal to a second preset distance.

[0048] Understandably, obstacles in physically blocked areas and custom-defined no-driving zones do not pose a collision risk to the vehicle. If the target obstacle is not in a no-driving zone, no alarm will be triggered, thus filtering out obstacles in no-driving zones, avoiding false alarms, and improving alarm accuracy.

[0049] Understandably, the alarm conditions for target obstacles restrict the type, speed, and heading angle of the target obstacle requiring an alarm. This allows for the identification of obstacles that move at high speeds and whose heading aligns with the vehicle, posing a significant collision risk. Alarming when such obstacles are present improves the effectiveness of the alarm. Furthermore, identifying the target obstacle as a vehicle eliminates obstacles such as pedestrians that pose little risk; ensuring the target obstacle's speed meets a preset speed threshold eliminates stationary, risk-free obstacles; ensuring the heading angle difference between the target obstacle and the vehicle is less than a preset heading angle difference eliminates vehicles traveling in the opposite direction; and ensuring the obstacle perception time reaches a preset duration prevents interference from rain, snow, and flying insects from being mistaken for obstacles.

[0050] S202, perform blind spot monitoring and alarm.

[0051] In some embodiments, when a vehicle intends to change lanes, the alarm level for blind spot monitoring is increased; and an alarm is triggered according to the alarm method corresponding to the increased alarm level. When a vehicle does not intend to change lanes, the alarm level for blind spot monitoring is maintained; and an alarm is triggered according to the alarm method corresponding to the maintained alarm level.

[0052] Understandably, when a vehicle intends to change lanes (for example, the vehicle is crossing the line laterally but the turn signal is not activated), and a high safety hazard is identified, the alarm level is raised to ensure user safety.

[0053] The following describes how the non-drivable area in S201 is generated.

[0054] In some embodiments, coordinate data of physical fences such as curbs, guardrails, water barriers, and fences, as well as boundaries such as solid lines and double solid lines, are obtained. Boundary lines are fitted based on the boundary coordinate data, and non-drivable areas are generated based on the fitted boundary lines.

[0055] (1) The boundary line is obtained by fitting.

[0056] For example, the following formula (1) shows a boundary line obtained by polynomial fitting. It can be understood that the boundary line obtained by fitting can usually be approximated as a smooth curve.

[0057] Formula (1);

[0058] in, This represents the boundary line of the i-th fitted line, corresponding to the independent variable. y-axis coordinate, Let x be the x-axis coordinate of the independent variable on the i-th fitted boundary line after fitting, where the coordinate system is centered at the rear axle of the vehicle, with the positive x-axis pointing directly in front of the vehicle and the positive y-axis pointing directly to the left of the vehicle. The coefficients of the k-th order polynomial for the i-th fitted boundary line are fixed parameters obtained through fitting. n represents the highest order of the polynomial. It can be understood that the fitted boundary curve can be used to represent solid lines, double solid lines, and physical fences such as curbs, guardrails, water-filled barriers, and pallets.

[0059] (2) Generate the non-drivable area based on the boundary curve.

[0060] No-drivable areas can include custom-defined no-drivable areas, which can be defined in conjunction with legally prohibited areas. For example, the law stipulates that vehicles cannot cross double solid lines on either side of a lane. To prevent misjudgments due to distance errors when locating obstacles, legal safety buffer zones can be configured based on legally prohibited areas. For instance, areas where the distance to the double solid lines is less than a second preset distance (e.g., a fixed value of 0.4m) can be considered legal safety buffer zones, meaning obstacles are considered to be able to pass through these areas. Thus, the custom-defined no-drivable areas are defined as areas outside the nearest double solid line to the vehicle, and areas where the distance to the nearest double solid line is greater than or equal to the second preset distance.

[0061] The non-drivable area can also include a physical barrier area, which can be determined based on a physical fence. Understandably, obstacles generally cannot cross physical barriers such as curbs, guardrails, water-filled barriers, and fences to collide with vehicles. Furthermore, to prevent positioning errors, a physical barrier safety buffer distance (i.e., a first preset distance) can be configured based on the physical fence. The area in the vehicle's lane where the distance between it and the physical fence is less than or equal to the first preset distance is considered the physical barrier safety buffer area, an area considered inaccessible to obstacles. Therefore, the physical barrier area can be the area outside the nearest physical fence to the vehicle, and the area in the vehicle's lane where the distance between it and the physical fence is less than or equal to the first preset distance.

[0062] For example, assuming the horizontal coordinate of the water-filled barrier is -1.8m and the first preset distance is 0.5m, then areas with a horizontal coordinate less than -1.3m are considered to be physical obstruction areas.

[0063] Understandably, in some embodiments, determining the presence of a target obstacle in the vehicle's monitoring blind spot as described in S201 above may include: acquiring vehicle information and perceived obstacles around the vehicle; generating a monitoring blind spot based on the vehicle information, and selecting preliminary obstacles that meet alarm conditions from the perceived obstacles around the vehicle; and determining the presence of a target obstacle in the vehicle's monitoring blind spot based on the preliminary obstacles and the monitoring blind spot. Understandably, a detailed explanation of the process can be found below. Figure 3A The description.

[0064] Figure 3A According to some embodiments of this application, a schematic diagram of a specific process for determining the presence of a target obstacle in the monitoring blind spot of a vehicle is shown.

[0065] S301, acquire vehicle information and perceive obstacles around the vehicle.

[0066] In some embodiments, vehicle information includes vehicle status information and vehicle parameter information.

[0067] Understandably, vehicles include a self-regulating information calculation module, which can be used to determine the current vehicle status and parameter information. For example, vehicle status information may include wheel speed, steering wheel angle, and steering wheel speed collected by sensors. Vehicle parameter information may include the vehicle's length, width, axle length, distance from the rear axle to the front bumper center, distance from the rear axle to the rear bumper center, lateral stiffness, and steering ratio. Furthermore, the self-regulating information calculation module can also include, but is not limited to, calculating the vehicle's current driving state parameters, such as vehicle speed, lateral and longitudinal acceleration, turning radius, current curvature, and yaw angle. Understandably, based on the real-time vehicle information obtained, the vehicle's driving state type can be accurately identified.

[0068] In some embodiments, the vehicle can sense potential obstacles around it through a sensing module, i.e., obtain obstacle perception. For example, obstacle perception may include static or dynamic obstacles such as vehicles, pedestrians, non-motorized vehicles, guardrails, curbs, traffic cones, walls, and trees.

[0069] S302 generates the vehicle's monitoring blind spot based on vehicle information and filters out preliminary obstacles that meet the alarm conditions from the perceived obstacles around the vehicle.

[0070] In some embodiments, the vehicle's driving state type is identified based on vehicle information; based on the driving state type, a monitoring blind spot is generated according to a preset blind spot generation method corresponding to the driving state type, wherein different driving state types correspond to different geometric parameters of the generated monitoring blind spot. For example, the geometric parameters may include area or shape. For instance, different preset blind spot generation methods correspond to different geometric parameters.

[0071] Understandably, the specific process of generating vehicle monitoring blind spots based on vehicle information can be found in [reference needed]. Figure 3B The description of that will not be repeated here.

[0072] S303, based on the initial selected obstacles and the monitoring blind spot, it is determined that there is a target obstacle in the vehicle's monitoring blind spot.

[0073] In some embodiments, preliminary obstacles are acquired; candidate obstacles located within a candidate monitoring area are selected from the preliminary obstacles; wherein the range of the candidate monitoring area is larger than the monitoring blind zone, and the candidate monitoring area includes the monitoring blind zone; and a target obstacle is determined from the candidate obstacles. For example, the candidate monitoring area includes the monitoring blind zone, and an area outside the monitoring blind zone whose distance to the nearest longitudinal boundary corresponding to the monitoring blind zone is less than or equal to a first preset boundary distance. The direction of the nearest longitudinal boundary corresponding to the monitoring blind zone is the same as the vehicle's travel direction.

[0074] The following is a detailed introduction to identifying the target obstacle from the candidate obstacles in S303.

[0075] When the number of candidate obstacles is equal to 1, if the candidate obstacle is located within the vehicle's blind spot, the candidate obstacle will be used as the target obstacle; or, if the candidate obstacle is located within the vehicle's blind spot and meets the collision time condition, the candidate obstacle will be used as the target obstacle.

[0076] For example, the conditions for identifying a target obstacle from candidate obstacles can differ for different blind spot detection systems. For a BSD system, it's sufficient to determine whether a candidate obstacle is within the blind spot. For instance, when there is only one candidate obstacle, it is considered the target obstacle if it is located within the vehicle's blind spot. For a Lane Change Assist (LCA) system, in addition to determining whether a candidate obstacle is within the blind spot, it's necessary to further determine whether the collision time between the candidate obstacle and the vehicle is too short to result in a collision. For example, if the candidate obstacle is within the vehicle's blind spot and meets the collision time condition, it is considered the target obstacle.

[0077] If the number of candidate obstacles is greater than or equal to 2, and there is a through obstacle among the candidate obstacles that meets the sandwich passage condition, the through obstacle that is closest to the vehicle in longitudinal distance or has the shortest collision time and is located in the monitoring blind zone will be selected as the target obstacle. Alternatively, if the number of candidate obstacles is greater than or equal to 2, and there is a through obstacle among the candidate obstacles that meets the sandwich passage condition, the through obstacle that is closest to the vehicle in longitudinal distance or has the shortest collision time, is located in the monitoring blind zone, and whose collision with the vehicle meets the collision time condition will be selected as the target obstacle.

[0078] For example, there are candidate obstacle 1 and candidate obstacle 2. And candidate obstacle 1 and candidate obstacle 2 satisfy the sandwich passage condition, that is, passing obstacle 1 and passing obstacle 2 are obtained. Passing obstacle 1 is closer to the vehicle in longitudinal distance than passing obstacle 2, and passing obstacle 1 is in the monitoring blind spot, so it is regarded as the target obstacle.

[0079] If the number of candidate obstacles is greater than or equal to 2, and the sandwich passage condition is not met, the candidate obstacle that is closest to the vehicle in longitudinal distance or has the shortest collision time and is located in the monitoring blind zone will be selected as the target obstacle. Alternatively, if the number of candidate obstacles is greater than or equal to 2, and the sandwich passage condition is not met, the candidate obstacle that is closest to the vehicle in longitudinal distance or has the shortest collision time, is located in the monitoring blind zone, and whose collision with the vehicle meets the collision time condition will be selected as the target obstacle.

[0080] In some embodiments, the sandwich passage condition includes: the width of the candidate obstacle is less than the lateral clearance distance between the vehicle and the nearest longitudinal candidate obstacle; the position of the candidate obstacle is located within the lateral interval corresponding to the clearance between the two nearest outer edges of the vehicle body and the nearest longitudinal candidate obstacle; the candidate obstacle has a tendency to move closer to the vehicle; and the candidate obstacle remains stable relative to the tendency to move closer to the vehicle.

[0081] For example, the following method is used to determine that a candidate obstacle has a tendency to move closer to the vehicle: when the longitudinal velocity of the candidate obstacle is greater than the longitudinal velocity of the vehicle, and the lateral distance between the candidate obstacle and the vehicle is less than a lateral distance threshold, the candidate obstacle is determined to have a tendency to move closer to the vehicle.

[0082] The stability of a candidate obstacle's motion relative to a nearby vehicle is determined by acquiring the number of tracking frames, velocity confidence, and velocity magnitude of the candidate obstacle. A candidate obstacle is considered stable relative to a nearby vehicle if its tracking frame count is greater than a preset number of tracking frames, its velocity confidence is greater than a confidence threshold, and its velocity magnitude is greater than a velocity magnitude threshold.

[0083] Understandably, identifying obstacles based on sandwich-like conditions can help vehicles recognize complex interactive behaviors.

[0084] In some embodiments, the collision time condition includes: when the vehicle is not turning or making a U-turn, the collision time from the candidate obstacle to the vehicle is less than or equal to a collision time threshold; when the vehicle is turning or making a U-turn, the collision time from the candidate obstacle to the vehicle is less than or equal to a collision time extension threshold, wherein the collision time extension threshold is greater than the collision time threshold.

[0085] Understandably, when a vehicle is turning or making a U-turn, the vehicle speed is relatively slow, and the risk of collision between the vehicle and the obstacle is low. Adding a collision condition where the collision time from the obstacle to the vehicle is less than or equal to the collision time extension threshold can prevent redundant alarms from being triggered.

[0086] That Figure 3B According to some embodiments of this application, a schematic diagram of a specific process for generating vehicle monitoring blind spots based on vehicle information is shown. The process is illustrated using the vehicle's onboard infotainment system as an example. The specific steps are as follows:

[0087] S3021 identifies the vehicle's driving status type based on vehicle information.

[0088] For example, the driving state type includes at least one of the following: driving on continuous curves and driving on non-continuous curves. Among them, driving on non-continuous curves may include, but is not limited to: driving on a straight road, turning at an intersection, changing lanes, or making a U-turn.

[0089] (1) Driving on continuous curves.

[0090] In some embodiments, when a vehicle meets the conditions for driving on continuous curves, the driving state type of the vehicle is considered to include driving on continuous curves. The conditions for driving on continuous curves include at least one of the following: the curvature of the vehicle's path is greater than a preset path curvature threshold (e.g., the preset path curvature threshold is 0.02m). -1 The conditions for continuous curves are: the vehicle is not in the intersection area, and the vehicle's continuous curve time exceeds a continuous curve time threshold (e.g., 1 second). The continuous curve time can be defined as the time during which the detected path curvature of the vehicle exceeds a preset path curvature threshold, or the time the vehicle is not in the intersection area. Understandably, the continuous curve driving condition excludes the situation where the vehicle is in the intersection area to avoid confusion with turning at an intersection. When the vehicle's path curvature exceeds a preset path curvature threshold (e.g., 0.02m), the continuous curve driving condition is defined as: the vehicle is not in the intersection area, and the vehicle's continuous curve time exceeds a preset path curvature threshold (e.g., 0.02m). -1 This can identify roads with significant curvature (such as urban road curves) and where the vehicle's continuous curvature time exceeds a threshold (e.g., 1 second), ensuring that the vehicle is not driving on continuous curves.

[0091] Among them, the following formula (2) shows a formula for calculating the path curvature of a vehicle.

[0092] Formula (2);

[0093] Where κ is the path curvature, and its unit can be... , is the rate of change of heading angle, which can be expressed in rad / s, and v is the current vehicle speed, which can be expressed in m / s.

[0094] (2) Driving on a straight road.

[0095] In some embodiments, when a vehicle meets the straight-road condition, the vehicle's driving state type is considered to include straight-road driving. The straight-road driving condition includes at least one of the following: the vehicle's path curvature is less than a preset path curvature threshold (e.g., the preset path curvature threshold is 0.02m). -1 The following conditions are considered when a vehicle is not in an intersection area, or when its straight-line travel time exceeds a threshold (e.g., 1 second). The straight-line travel time can be defined as the time during which the detected path curvature is less than a preset path curvature threshold, or the time the vehicle is not in an intersection area. Understandably, the straight-line travel condition excludes the situation where the vehicle is in an intersection area to avoid confusion with intersection travel. When the vehicle's path curvature is less than a preset path curvature threshold (e.g., 0.02m), the straight-line travel condition is considered valid. -1This can determine if the road curvature is small (such as a slight curve or a straight line on a highway) and the vehicle's straight-line travel time is greater than the straight-line travel time threshold (e.g., 1 second). This can ensure that the vehicle is traveling on a straight road and eliminate instantaneous abnormal changes in path curvature, vehicle heading, or travel trajectory caused by factors such as road surface bumps, sensor noise, and lane line interference.

[0096] (3) Turning at the intersection.

[0097] In some embodiments, when a vehicle meets the intersection turning conditions, the vehicle's driving state type is considered to include intersection turning. The intersection turning conditions include at least one of the following: the vehicle is located in an intersection area; the angle between the vehicle's target heading and its current heading matches the turning intention heading angle; and the predicted turn completion time is greater than a turning time threshold (e.g., a turning time threshold of 1 second).

[0098] Understandably, the angle between the target heading and the current heading refers to the angular difference between the vehicle's desired direction of travel and its actual direction of travel. The turning intention heading angle is a preset angle threshold range. When this angle difference falls within the turning intention heading angle range, it indicates that the vehicle has a clear turning intention, and at this time it is not in a straight-ahead state. Furthermore, a turning prediction completion time greater than the turning time threshold ensures that the vehicle is turning at an intersection rather than on a curve.

[0099] For example, the vehicle's coordinates can be determined using high-precision maps or visual detection, and whether the vehicle is located within the intersection area can be determined based on whether its coordinates are within the intersection area. The predicted turn completion time can be calculated based on the current vehicle speed and turning geometry parameters, estimating the time required for the vehicle to complete the turn. These turning geometry parameters can include the vehicle's turning radius, turning angle, and speed.

[0100] The following formula (3) shows a formula for calculating the predicted completion time of a turn.

[0101] Formula (3);

[0102] in, Indicates the predicted completion time of the turn. This indicates the turning radius, and the unit can be meters (m). This indicates the turning angle, and the unit can be rad. This represents the current vehicle speed, in m / s. Furthermore, the current speed can be further limited, for example, to less than 6 m / s. This is because a vehicle's speed when turning is generally no greater than 6 m / s; a speed greater than 6 m / s is usually not considered a turn. Therefore, the time required for the vehicle to complete a turn can be predicted using a speed less than 6 m / s.

[0103] (4) Turn around

[0104] It is understandable that a U-turn can also be called a U-shaped turn. In some embodiments, when a vehicle meets the conditions for a U-turn, the vehicle's driving state is considered to include a U-turn. The conditions for a U-turn include at least one of the following: a change in heading angle greater than 90 degrees, a vehicle speed less than a U-turn speed threshold (e.g., 3 m / s), a steering wheel held at a large angle (e.g., 15 degrees) for 3-8 seconds, a gear shift (e.g., from D to R, or from R to D), and both the low-speed maintenance time and the large-angle steering wheel maintenance time meet preset thresholds. For example, the vehicle speed is less than 1.5 m / s and the duration of the large-angle steering wheel maintenance both meet 3.5 seconds. It is understandable that a change in heading angle greater than 90 degrees can prevent misjudgment as a normal lane change.

[0105] (5) Changing lanes

[0106] In some embodiments, when a vehicle meets lane-change conditions, its driving state is considered to include lane change. These lane-change conditions include at least one of the following: side turn signal activation, the distance between the vehicle and the nearest lane line being less than a lane line distance threshold (e.g., 1 / 6 of the vehicle's width), and the vehicle's lateral speed exceeding a lateral lane-change speed threshold (e.g., 0.5 m / s). Understandably, the turn signal clearly indicates a lane change is required, the distance between the vehicle and the nearest lane line being less than the lane line distance threshold indicates the vehicle is approaching the lane line, and the lateral speed exceeding the lateral lane-change speed threshold helps to eliminate interference from road surface bumps. Furthermore, including lane lines and lateral speed as lane-change elements in the lane-change conditions allows for the identification of lane-change situations even when the user fails to activate the turn signal but shows a tendency to change lanes, thus improving safety redundancy.

[0107] S3022, Based on the driving state type, generate the vehicle's monitoring blind spot according to the preset blind spot generation method corresponding to the driving state type.

[0108] Understandably, different driving conditions result in different geometric parameters for the generated blind spots. For example, geometric parameters may include, but are not limited to, area and shape.

[0109] In some embodiments, when driving in a non-continuous curve, the preset blind spot generation method includes: determining the rectangular boundary coordinates of the monitoring blind spot based on the distance from the rear axle to the B-pillar, the preset safe forward extension distance, the vehicle width, and the preset lateral extension distance of the blind spot; and generating monitoring blind spots located on both sides of the vehicle based on the rectangular boundary coordinates.

[0110] For example, for a BSD system or LCA system, when the vehicle is traveling on a straight road, the monitoring blind spot can be a rectangular area, and when the vehicle is traveling on a series of curves, the monitoring blind spot can be a ring-shaped sector area.

[0111] Formulas (4)-(7) below specifically show the rectangular boundary coordinates corresponding to the monitoring blind spot on the right side of the vehicle.

[0112] Formula (4);

[0113] in, This indicates the coordinates of the lower left corner vertex of the monitoring blind zone. This indicates the distance from the rear axle to the vehicle's B-pillar. Indicates the safe forward reach distance. This indicates the width of the vehicle.

[0114] Formula (5);

[0115] in, This indicates the coordinates of the top left corner vertex of the monitoring blind zone. This indicates the lateral extension distance of the monitoring blind spot.

[0116] Formula (6);

[0117] in, This indicates the coordinates of the top right corner vertex of the monitoring blind zone. This refers to the longitudinal coverage length, which is the total length of the area that the vehicle can effectively detect and cover along its longitudinal direction. Understandably, blind spots have a longitudinal extension to ensure sufficient warning capability for obstacles approaching from behind. Understandably, the specific range and requirements for the length of the blind spot vary between different alarm systems. For example, in a BSD system, the longitudinal coverage length Dlong can be 3 meters, while for an LCA system, the longitudinal coverage length Dlong can be 70 meters to ensure sufficient warning capability for targets approaching rapidly from behind.

[0118] Formula (7);

[0119] in, This indicates the coordinates of the lower right corner vertex of the monitoring blind zone. , , , This means that the rectangular boundary coordinates of the blind zone can be realized, which can realize the geometric definition of the blind zone and form a closed polygonal region.

[0120] In some embodiments, when the driving state is continuous curve driving, a preset blind spot generation method includes: obtaining the sector parameters of the first monitoring blind spot according to a preset annular sector calculation method based on the vehicle's turning radius and vehicle width, wherein the sector parameters include the inner arc length, the outer arc length, and the sector angle; and generating monitoring blind spots located on both sides of the vehicle based on the sector parameters. It can be understood that the generated monitoring blind spot shape is an annular sector.

[0121] For example, the radius of the inner arc length can be calculated using the following formula (8).

[0122] Rinner=R+0.5w+0.5 formula (8);

[0123] Where Rinner represents the radius of the inner arc, R represents the vehicle's turning radius (in meters), and w represents the vehicle width (in meters, typically 1.8 meters). For example, refer to... Figure 3C In the two monitoring blind spots S1 generated by vehicle 100, the turning radius R of the vehicle is estimated according to the steering wheel angle or path, and the arc length radius R12 corresponding to the inner arc length L1 of the monitoring blind spot S1 on the left can be obtained according to formula (8) based on the turning radius R.

[0124] For example, the radius of the outer arc length can be calculated using the following formula (9).

[0125] Router=R+0.5w+2.5 formula (9);

[0126] Here, Router represents the radius of the outer arc length. For example, refer to... Figure 3C In the monitoring blind spots S1 generated on both sides of vehicle 100, the arc length radius R11 of the outer arc length L2 can be obtained according to formula (9) based on the turning radius R.

[0127] For example, taking the average value of the inner and outer arc lengths as 3m as an example, formula (10) shows the calculation method of calculating the sector angle based on the arc radius of the outer arc length and the arc radius of the inner arc length.

[0128] Formula (10);

[0129] in, This represents the sector angle, and the unit can be rad.

[0130] Understandably, based on the arc length formula, the inner arc length L1 can be... The outer arc length L2 can be .

[0131] Figure 4 According to some embodiments of this application, a flowchart of another blind spot monitoring and alarm method is shown. In this flowchart, after the vehicle generates its blind spot monitoring based on vehicle information, it progressively filters out a first target and a second target from the perceived obstacles around the vehicle. The first and second targets are related to alarm conditions. An alarm is then triggered based on either the first or second target. The method is illustrated using the vehicle's infotainment system as an example. The specific steps are as follows:

[0132] S01, Obtain vehicle information.

[0133] Understandably, the specific details of the vehicle information can be found in the S301 above, and will not be repeated here.

[0134] S02, generates an undriveable area.

[0135] Understandably, non-drivable areas can be generated based on environmental information from vehicle data. Understandably, vehicles can generate perception capabilities for static environmental semantics such as lane line types, curbs, fences, water-filled barriers, and stone blocks based on environmental information, avoiding the problem of frequent false triggering in physically impassable areas such as outside double solid lines and on the shoulder, which is caused by relying solely on corner radar perception and risk assessment based on the attributes of the vehicle and surrounding moving obstacles.

[0136] S03, Driving status type recognition.

[0137] Understandably, the specific identification method for driving status type can be referred to in S3021 above, and will not be repeated here.

[0138] S04, Monitoring blind spot generation.

[0139] Understandably, the specific method for generating monitoring blind spots can be referred to in S3022 above, and will not be elaborated here.

[0140] S05, identify and perceive obstacles and predict their trajectories.

[0141] In some embodiments, the vehicle identifies surrounding obstacles (such as other moving vehicles) and predicts their trajectories. Specifically, the vehicle can calculate the heading angle deviation of the perceived obstacle relative to its lane direction, and use this heading angle deviation to distinguish the obstacle's driving trend for subsequent trajectory prediction model selection, thereby improving the accuracy and robustness of trajectory prediction.

[0142] The following formula (11) shows a formula for calculating heading angle deviation.

[0143] Formula (11);

[0144] in, This indicates the deviation of the perceived obstacle from the lane direction in terms of heading angle, and the unit can be rad. The heading angle for detecting obstacles, measured in rad. This represents the direction angle of the lane where the perceived obstacle is located, and the unit can be rad. `wrap()` is an angle normalization function used to convert values ​​outside a specified range to a target range. For example, the target range is 0°~360° (or -180°~180°).

[0145] In some embodiments, a vehicle motion prediction model can be used to predict the trajectory of a perceived obstacle. For example, vehicle motion prediction models generally include constant velocity (CV) models or constant turn rate and velocity (CTRV) models. CV models are generally suitable for scenarios where the obstacle is traveling straight along the lane, its heading remains essentially constant, and it is moving approximately at a constant velocity in a straight line. CTRV models are generally used for scenarios where the obstacle is undergoing stable turning, is turning or changing lanes, and its heading is changing steadily. Furthermore, the vehicle can also predict the trajectory of the perceived obstacle based on the target vehicle's current motion state (speed, heading angle, angular velocity, acceleration, etc.) using nonlinear weights. An adaptive weighted fusion of the CV model and the CTRV model is performed to achieve accurate and robust prediction of the future trajectory of perceived obstacles.

[0146] The following formula (12) shows a formula for calculating a nonlinear weight.

[0147] Formula (12);

[0148] in, This represents the non-linear weight, and k represents the weight adjustment coefficient. Indicates the heading angle deviation threshold. The standard deviation of the heading angle is represented in rad. Nonlinear weights can be calculated using the Sigmoid function to smoothly switch between CV and CTRV models.

[0149] The following formula (13) shows a method that combines nonlinear weights to achieve hybrid prediction of CV and CTRV models, adapting to different driving scenarios.

[0150] Formula (13);

[0151] in, This represents the predicted location of a target object that is perceived as an obstacle; the unit can be meters (m). This represents the position prediction under a uniform velocity model, and the unit can be meters (m). This represents the position prediction under a constant rotational speed model, with units in meters (m). Understandably, this involves nonlinear weights. It can achieve hybrid prediction of CV and CTRV models, adapting to different driving scenarios.

[0152] S06, determine if a primary target exists. If a primary target exists, proceed to S07; otherwise, confirm that no alarm is triggered.

[0153] In some embodiments, based on the identified obstacle and vehicle information, a non-drivable area and a monitoring blind spot are generated to determine whether a first target exists. If a first target exists, proceed to S07; otherwise, determine not to alarm. Specifically, pre-configured alarm conditions are obtained. Based on the obstacle information and the pre-configured alarm conditions, it is determined whether there is a preliminary obstacle among the detected obstacles that meets the alarm conditions. If a preliminary obstacle exists, it is determined whether there is a candidate obstacle located in the candidate monitoring area. The candidate monitoring area is larger than the monitoring blind spot and includes the monitoring blind spot. The first target is the candidate obstacle with the closest longitudinal distance to the vehicle. When the number of candidate obstacles is 1, the candidate obstacle is the first target. When the number of candidate obstacles is greater than or equal to 2, the candidate obstacle with the closest longitudinal distance to the vehicle is taken as the first target. If a candidate obstacle exists, it is determined that a first target must exist, and proceed to S07; otherwise, if a first target does not exist, determine not to alarm.

[0154] In some implementations, determining whether there is a preliminary obstacle among the perceived obstacles that meets the alarm conditions can be done by: determining whether the perceived obstacle is a vehicle type, whether the speed meets a preset speed threshold, whether the heading angle difference between the perceived obstacle and the vehicle is less than a preset heading angle difference, whether the perception time reaches a preset perception time, and whether it is not located in a non-drivable area.

[0155] For example, determining whether the speed of the perceived obstacle meets a preset speed threshold can be done by: determining whether the longitudinal speed of the perceived obstacle is greater than a longitudinal speed threshold (e.g., 2 m / s) and whether the lateral speed is less than a lateral speed threshold (e.g., 1.5 m / s). When the longitudinal speed of the perceived obstacle is greater than the longitudinal speed threshold and the lateral speed is less than the lateral speed threshold, it is determined that the speed of the perceived obstacle meets the preset speed threshold.

[0156] For example, determining whether the obstacle perception duration has reached the preset perception duration can be done as follows: the vehicle perception module outputs perception data at a fixed period, with each frame having a fixed duration, such as 16.67ms. Therefore, the obstacle perception duration can be obtained based on the number of frames in which the vehicle perceives the obstacle's presence. The number of frames in which the obstacle is perceived is compared with the preset number of frames corresponding to the preset perception duration. If the number of perceived frames is greater than or equal to the preset number of frames, it is determined that the obstacle perception duration has reached the preset perception duration.

[0157] Understandably, identifying the obstacle as a vehicle excludes pedestrians. An obstacle with a longitudinal velocity greater than its longitudinal velocity is used to exclude obstacles that won't cross the vehicle, while an obstacle with a lateral velocity less than a threshold avoids interference from vehicles changing lanes quickly. An obstacle detection duration that reaches a preset duration is used to eliminate noise interference. An obstacle not located in a non-drivable area is used to exclude obstacles that pose no collision risk.

[0158] The following describes the process of obtaining candidate obstacles based on the initial obstacle selection.

[0159] For example, in an LCA system, determining whether a candidate obstacle exists within the candidate monitoring area among the initially selected obstacles can be done in the following way. Assume the y-axis coordinate of the initially selected obstacle is yi, and the preset y-axis coordinate range is [-2...]. , - / 2], and [ / 2,2 Then it is necessary to determine. Whether it is true or not, among which, Indicates the width of the vehicle. This indicates the lane width where the vehicle is located. The preset y-axis coordinate range includes the lateral range of the blind spot and is greater than the lateral range of the blind spot.

[0160] Furthermore, the x-axis coordinate of the initially selected obstacle is xi, with a preset x-axis coordinate range of [-70, 2.2]. This preset x-axis coordinate range is larger than the vertical range of the monitoring blind zone. It is determined whether xi falls within the preset x-axis coordinate range. If both the x-axis and y-axis coordinates of the initially selected obstacle meet the preset coordinate range, then the initially selected obstacle meeting the preset coordinate range is considered a candidate obstacle. In this case, the candidate monitoring area is the region formed by the preset y-axis coordinate range and the preset x-axis coordinate range.

[0161] For the BSD system, the x-axis coordinate of the initially selected obstacle is xi, the y-axis coordinate of the initially selected obstacle is yi, the preset x-axis coordinate range of the vehicle's side-rear section is [-15, 2.2], and the preset y-axis coordinate range is [-2]. , - / 2], and [ / 2,2 The algorithm determines whether xi falls within a preset x-axis coordinate range and whether yi falls within a preset y-axis coordinate range. Furthermore, if both the x-axis and y-axis coordinates of the initially selected obstacle meet the preset coordinate range, then the initially selected obstacle meeting the preset coordinate range is designated as the first candidate obstacle. The algorithm further determines whether the distance between the first candidate obstacle (not belonging to the monitoring blind zone) and the monitoring blind zone meets the specified conditions.

[0162] Determine the first preset boundary distance When the first initially selected obstacle is outside the monitoring blind zone, determine whether the distance between the first initially selected obstacle and the nearest longitudinal boundary corresponding to the monitoring blind zone is less than or equal to the distance of the first preset boundary. .

[0163] If so, the first initially selected obstacle and the first initially selected obstacle belonging to the monitoring blind zone are taken as candidate obstacles. At this time, the candidate monitoring area is the second area after removing a portion of the first area formed by the preset y-axis coordinate range and the preset x-axis coordinate range. The portion of the second area is the area where the distance between the nearest longitudinal boundary corresponding to the monitoring blind zone and the first preset boundary distance is greater than the distance between the two boundaries. It is understandable that since the first target is the candidate obstacle closest to the vehicle's longitudinal distance, there must be a first target among the candidate obstacles.

[0164] S07, determine whether a second target exists based on the sandwich traversal condition. If a second target exists, proceed to S09 to perform a risk assessment based on the second target; otherwise, proceed to S08 to perform a risk assessment based on the first target.

[0165] Understandably, the sandwich passage conditions can include: the width of the candidate obstacle is less than the lateral clearance between the vehicle and the nearest longitudinal candidate obstacle; the candidate obstacle is located within the lateral interval corresponding to the clearance between the two nearest outer edges of the vehicle body and the nearest longitudinal candidate obstacle; the candidate obstacle has a tendency to move closer to the vehicle; and the candidate obstacle's movement relative to the approaching vehicle remains stable. If there is a passing obstacle among the candidate obstacles that satisfies the sandwich passage conditions, then the existence of a second target is determined, and the passing obstacle with the shortest longitudinal distance or the shortest collision time is selected as the second target.

[0166] Understandably, after identifying candidate obstacles, a preliminary target can be obtained based on the candidate obstacles, and then a passage obstacle can be identified based on the preliminary target, and a second target can be identified based on the passage obstacle.

[0167] The process of obtaining preliminary targets based on candidate obstacles will be introduced below.

[0168] In some implementations, the following method can be used to determine whether the width of a candidate obstacle is less than the lateral clearance distance between the vehicle and the nearest longitudinal candidate obstacle. Specifically, the nearest longitudinal candidate obstacle is identified, which is the first target mentioned above. The lateral clearance distance between the vehicle and the nearest longitudinal candidate obstacle is calculated. Based on the lateral clearance distance and the vehicle width corresponding to the vehicle type, the vehicle target type that can pass through the nearest longitudinal candidate obstacle is determined. The width of the candidate obstacle corresponding to this target type will be less than the lateral clearance distance between the vehicle and the nearest longitudinal candidate obstacle, and it will be used as the initial target.

[0169] For example, based on CNCAP and actual traffic behavior statistics, Formula (14) shows a crossing capability level between a vehicle and the nearest longitudinal candidate obstacle. The specific level of this crossing capability level corresponds to the type of vehicle target that is allowed to cross the lateral gap.

[0170] Formula (14);

[0171] in, This indicates the width of the lateral clearance between the vehicle and the nearest longitudinal candidate obstacle.

[0172] When the width is <1.0m (None), it means the width is only barely enough for pedestrians to pass through, but the system does not consider it a valid crossing risk. When the width is between 1.0 and 2.0m (TwoWheelerOnly), it represents the typical passageway for two-wheeled vehicles (including delivery electric bikes). When the width is between 2.0 and 2.8m (LightVehicles), it means small cars can cut in and pass through. When the width is ≥2.8m (AllVehicles), it means all vehicles, including trucks, can pass through. For example, the actual calculation method for the lateral clearance width between a vehicle and the nearest longitudinal candidate obstacle is to calculate the net lateral space between the vehicle and the nearest longitudinal candidate obstacle using the lateral coordinates and width of the vehicle and the nearest longitudinal candidate obstacle. Specifically, the width between the lateral coordinates of the vehicle and the nearest longitudinal candidate obstacle is subtracted from the sum of half the widths of the vehicle and the nearest longitudinal candidate obstacle respectively. The remaining space is the passageway that other traffic participants (such as two-wheeled vehicles and pedestrians) may pass through. This value directly determines whether obstacles of a certain size are allowed to enter the "sandwich zone".

[0173] For example, refer to Figure 5 As shown, Figure 5 The first target 1 is the closest longitudinal candidate obstacle. The widths of the initial target 51, initial target 52, and initial target 53 are less than the lateral clearance distance d1 between the vehicle and the first target 1. Similarly, refer to... Figure 6 As shown, Figure 6The first target 2 is the closest longitudinal candidate obstacle. The widths of the preliminary targets 61, 62, and 63 are less than the lateral clearance distance d2 between the vehicle and the first target 2 (not shown in the figure).

[0174] Next, we will introduce the process of obtaining the obstacles that satisfy the sandwich passage conditions based on the initial target, and obtaining the second target based on the obstacles.

[0175] Understandably, once the initial target is determined, it can be further determined whether the target's position lies within the lateral range corresponding to the gap between the two nearest outer edges of the vehicle body and the nearest longitudinal candidate obstacle. It is also necessary to determine whether the initial target exhibits a tendency to move closer to the vehicle and whether this tendency remains stable relative to the approaching vehicle. If all the aforementioned conditions are met, then an obstacle satisfying the sandwich crossing condition exists, and the obstacle with the shortest longitudinal distance or the shortest collision time is selected as the second target.

[0176] For example, continue to refer to Figure 5 Both preliminary targets 51 and 52 meet the conditions for passing through a sandwich, while the position of preliminary target 53 is incorrect. Preliminary targets 51 and 52 are therefore designated as obstacles. Furthermore, preliminary target 51 has the shortest longitudinal distance to the vehicle, so it is designated as the second target.

[0177] For example, continue to refer to Figure 6 If the direction of movement (i.e. the trend of movement) of the initial target 61 is incorrect, and the positions of the initial targets 62 and 63 are incorrect, and it is determined that there is no obstacle among the initial obstacles that meets the conditions for passing through the sandwich, then there is no second target.

[0178] In some implementations, determining whether the position of the initial target is located within the lateral interval corresponding to the gap between the two nearest outer edges of the vehicle body and the nearest longitudinal candidate obstacle can be done in the following ways.

[0179] It is understandable that the expression for the lateral interval is different when the initial target is located on the left or right side of the vehicle. For ease of explanation, taking the initial target located on the left side of the vehicle as an example, formula (15) shows a calculation method for determining whether the position of the initial target is located within the lateral interval corresponding to the gap between the two nearest outer edges of the vehicle body and the nearest longitudinal candidate obstacle.

[0180] Formula (15);

[0181] in, This indicates the coordinates of the side of the vehicle's outer edge closest to the initial target. This indicates the width of the initial target selection. This represents the coordinates of the vehicle's outer edge closest to the initial target within the longitudinally nearest candidate obstacle. This indicates the width of the vehicle in the initial selection.

[0182] It is understandable that when the coordinates of the initially selected target satisfy formula (15), it means that the entire body of the initially selected target is placed within the longitudinal driving area formed by the lateral interval corresponding to the gap between the two nearest outer edges of the vehicle body and the nearest longitudinal candidate obstacle.

[0183] Understandably, if the longitudinal velocity of the initial target (i.e., the candidate obstacle) is greater than the longitudinal velocity of the vehicle, and the lateral distance between the initial target and the vehicle is less than the lateral distance threshold, it is determined that the initial target has a tendency to move closer to the vehicle. Formula (16) shows a formula for judging the movement trend of the initial target.

[0184] Formula (16);

[0185] in, This indicates the longitudinal velocity of the initially selected target. Indicates the longitudinal speed of the vehicle. Indicates the coordinates of the rear axis center of the initial target. This indicates the coordinates of the rear axle center of the vehicle. This indicates the driving area distance threshold (i.e., the lateral distance threshold), for example, 2.5m.

[0186] In some implementations, the following methods can be used to determine whether the motion trend of the initially selected target relative to the approaching vehicle remains stable.

[0187] For example, if the number of tracking frames for the initial target is greater than the preset number of tracking frames, the velocity confidence of the initial target is greater than the confidence threshold, and the velocity magnitude of the initial target is greater than the velocity magnitude threshold, then the initial target can be considered to maintain a stable motion trend relative to the approaching vehicle.

[0188] In some implementations, a second target can be identified from obstacles in the following ways.

[0189] For example, a second target can be determined from passing obstacles based on the longitudinal distance from the vehicle. The passing obstacle closest to the vehicle in longitudinal distance is taken as the second target. Formula (17) shows a calculation formula for determining a second target from passing obstacles based on longitudinal distance.

[0190] Formula (17);

[0191] Here, Select-Target represents the second target. This represents the longitudinal coordinate (i.e., the x-axis coordinate) of the i-th obstacle to be traversed. This represents the vehicle's longitudinal coordinate (i.e., the x-axis coordinate).

[0192] For example, a second target can be determined from the obstacles passing through the vehicle based on the collision time with the vehicle. The obstacle passing through the vehicle with the shortest collision time with the vehicle is taken as the second target. Formula (18) shows a formula for calculating the collision time between the obstacle passing through the vehicle.

[0193] Formula (18);

[0194] in, This represents the collision time between the i-th obstacle and the vehicle. This represents the x-axis (vertical) coordinate of the i-th obstacle to be traversed. This represents the vehicle's x-axis (longitudinal) coordinate. This indicates the vehicle's x-axis (longitudinal) speed. This represents the x-axis (longitudinal) velocity of the i-th obstacle.

[0195] S08: Determine if the first target poses a risk. If the first target poses a risk, proceed to S10; otherwise, do not issue an alarm.

[0196] It is understandable that different alarm systems have different requirements for the generation of risks.

[0197] For example, the activation condition for an alarm can be that the first target is in the monitoring blind zone, and the deactivation condition can be that the first target is not in the monitoring blind zone. For a BSD system, it is only necessary to determine whether the first target is in the monitoring blind zone. If the first target is determined to be in the monitoring blind zone, then the first target is determined to pose a risk, that is, the first target is a target obstacle, and the system proceeds to S10 to trigger an alarm. Otherwise, if no risk is posed, no alarm is triggered.

[0198] For example, the activation condition for an alarm can be set as the first target being in the blind zone and meeting the collision time condition, while the deactivation condition can be set as the first target not being in the blind zone or not meeting the collision time condition. For the LCA system, it is necessary not only to determine whether the first target is in the blind zone, but also whether the collision time between the first target and the vehicle meets the collision time condition. If the first target is both in the blind zone and meets the collision time condition, then the first target is determined to pose a risk, i.e., the first target is a target obstacle, and the process proceeds to S10; otherwise, no alarm is triggered.

[0199] In some embodiments, it can be determined whether the first target is within the monitoring blind zone based on the coordinates of the first target and the coordinates of the monitoring blind zone. For example, the following formula (19) illustrates a judgment logic for determining whether the first target is in the monitoring blind zone on the left side of the vehicle.

[0200] Formula (19);

[0201] Where (x_j, y_j) represent the coordinates of the first target. EBZ left This indicates the monitoring blind spot on the left side. True means the first target is in the monitoring blind spot on the left side of the vehicle, while false means the first target is not in the monitoring blind spot on the left side of the vehicle.

[0202] The following formula (20) shows a judgment logic for the first target being in the monitoring blind spot on the right side of the vehicle.

[0203] Formula (20);

[0204] EBZ right This indicates the monitoring blind spot on the right side. True means the first target is in the monitoring blind spot on the right side of the vehicle, while false means the first target is not in the monitoring blind spot on the right side of the vehicle.

[0205] In other embodiments, the collision time between the first target and the vehicle is calculated based on the longitudinal distance and longitudinal speed of the first target relative to the vehicle, and the vehicle's driving state is considered to determine whether the first target meets the collision time condition. Specifically, when the vehicle is not turning or making a U-turn, if the collision time between the first target and the vehicle is less than or equal to a collision time threshold, then the first target is determined to meet the collision time condition. When the vehicle is turning or making a U-turn, if the collision time between the first target and the vehicle is less than or equal to a collision time extension threshold, where the collision time extension threshold is greater than the collision time threshold, then the first target is determined to meet the collision time condition.

[0206] Understandably, when a vehicle is turning or making a U-turn, extending the collision time threshold, i.e. increasing the alarm trigger threshold, can suppress unnecessary alarms.

[0207] For example, the following formula (21) shows a formula for calculating the longitudinal distance between a first target and a vehicle.

[0208] Formula (21);

[0209] in, This represents the longitudinal coordinate of the center of the first target in the vehicle coordinate system. The longitudinal coordinate of the vehicle's center (usually 0). This indicates the distance from the rear axle of the vehicle to its B-pillar. This indicates the longitudinal distance of the first target relative to the vehicle's B-pillar.

[0210] Formula (22) below shows a formula for calculating collision time based on longitudinal distance.

[0211] Formula (22);

[0212] in, This represents the longitudinal velocity of the first target relative to the vehicle (along the x-axis). This indicates the time of collision between the first target and the vehicle.

[0213] Understandably, collision time is calculated only when the first target is approaching the vehicle (vrel, x>0); otherwise, it is considered to be moving away or stationary, with extremely low risk. Choosing the B-pillar between the first target and the vehicle as the longitudinal distance, rather than choosing the rear of the vehicle, can more accurately reflect the collision risk at the moment of lane change.

[0214] It is understandable that using collision time as the activation condition of the alarm system can be configured according to the logic of the following formula (23).

[0215] Formula (23);

[0216] in, The base threshold representing the collision time (e.g., a typical value of 2.0). This indicates the preset extension time. This represents the hysteresis bandwidth (typically 0.3). Understandably, the hysteresis mechanism is introduced to prevent frequent jitter alarms near the time threshold (the base threshold plus a preset extension time). That is, the threshold for extending the collision time.

[0217] Understandably, using collision time as the exit condition of the alarm system can be configured according to the logic of the following formula (24).

[0218] Formula (24);

[0219] Understandably, this is only triggered when the collision time is significantly lower than the collision time extension threshold. Understandably, it is only deactivated when the collision time is significantly higher, thus improving user experience stability.

[0220] S09, determine whether the second target poses a risk. If the second target poses a risk, proceed to S10; otherwise, do not issue an alarm.

[0221] Understandably, the process of determining whether the second objective poses a risk is the same as the process of determining whether the first objective poses a risk, and will not be elaborated here.

[0222] S10, alarm level escalation judgment.

[0223] Understandably, alarm systems are configured with a basic alarm mode. When a risk is identified at the first or second target (i.e., after the target obstacle is identified), the basic alarm mode is generally used by default. To enhance the alert's effectiveness, some alarm systems can determine whether to escalate the alarm level based on the vehicle's driving status. If an escalation is deemed necessary, the upgraded alarm level is used; otherwise, the alarm mode corresponding to the basic alarm level is used.

[0224] In some embodiments, upgrade conditions can be preset (such as the vehicle intending to change lanes). When the preset upgrade conditions are met, the alarm level for blind spot monitoring is increased; when the preset upgrade conditions are not met, the alarm method corresponding to the basic alarm level is used. For example, when the vehicle intends to change lanes, the alarm level for blind spot monitoring is increased, i.e., it is determined that the alarm level needs to be upgraded. When the vehicle does not intend to change lanes, the alarm method corresponding to the basic alarm level is used. For instance, the alarm method corresponding to the basic alarm level is a flashing yellow light on the rearview mirror; after the alarm level is upgraded, the alarm method is a flashing yellow light combined with a "beep beep beep" sound from the vehicle to remind the user.

[0225] For example, taking the monitoring blind spot as a condition for determining whether the first or second target is a risk, i.e. whether it is a target obstacle, we will explain the logic for configuring the corresponding alarm level.

[0226] Formula (25) shows the logic formula for a configured alarm level.

[0227] Formula (25);

[0228] in, This indicates that it is not within the monitoring blind zone. This indicates that in the monitoring blind spot, This indicates that the vehicle did not intend to change lanes. This indicates that the vehicle intends to change lanes. Level 0 indicates no risk and no alarm is needed. Level 1 indicates that the basic alarm method should be used. Level 2 indicates that the basic alarm method should be upgraded and the upgraded alarm method should be used.

[0229] Understandably, if the first or second target is not within the monitoring blind zone, it is determined that there is no target obstacle, and therefore no alarm is needed; the corresponding alarm level is 0. Specifically, a level of 0 can also indicate no risk.

[0230] If either the first or second target is within the monitoring blind zone, an obstacle is confirmed to exist, and the vehicle does not intend to change lanes. In this case, the alarm level is 1, which corresponds to the basic alarm level. If either the first or second target is within the monitoring blind zone, an obstacle is confirmed to exist, and the vehicle intends to change lanes. In this case, the alarm level is 2, and an alarm is triggered using the upgraded alarm method from the basic alarm level.

[0231] S11, trigger an alarm based on the BSD / LCA alarm level.

[0232] In some embodiments, when it is necessary to increase the alarm level for blind spot monitoring of the vehicle, the alarm is triggered according to the alarm method corresponding to the increased alarm level; when it is not necessary to increase the alarm level for blind spot monitoring of the vehicle, the alarm is triggered according to the alarm method corresponding to the basic alarm level.

[0233] Understandably, a separate alarm strategy with coupled intent can be implemented. Level 0 indicates no risk, and no alarm is triggered. Level 1 indicates a target obstacle but no intention to change lanes; the Human-Machine Interface (HMI) highlights this, with minimal user disruption. Level 2 indicates a target obstacle and an intention to change lanes, triggering a strong alert, such as flashing turn signals and an audible warning.

[0234] Understandably, the blind spot monitoring and alarm method proposed in this application combines the surrounding view information of each vehicle with the blind spot alarm. By fusing high-precision lane information and obstacle semantics, it dynamically estimates the behavioral intentions of the vehicle and surrounding perceived obstacles (such as moving vehicles) and the road conditions, thereby optimizing the system performance of the blind spot alarm system. Understandably, by increasing the generation method of monitoring blind spots in continuous curve scenarios, different geometric monitoring blind spots are generated for different driving scenarios, improving the monitoring capability of blind spot monitoring. Furthermore, for sandwich scenarios where obstacles (such as vehicles) pass between the vehicle and adjacent obstacle areas (such as neighboring vehicles), by adding the sandwich passing condition as one of the alarm conditions, the positive trigger rate of this high-risk interaction scenario is significantly improved, which can improve the functional operation design domain (ODD) of the blind spot alarm system. Moreover, when judging whether a vehicle intends to change lanes, if the vehicle does not use its turn signal but exhibits lateral crossing behavior, it is considered to have the intention to change lanes, supplementing the judgment method of vehicle lane change intention and improving the accuracy of identifying vehicle lane change intentions. Furthermore, dynamically increasing the alarm level based on the vehicle's intention to change lanes can further reduce the risk of collision. In addition, by introducing the constraint that obstacles are not located in drivable areas into the alarm conditions, invalid perceived obstacles located outside double solid lines, outside curbs, or behind obstacles can be filtered out. When the vehicle is turning or making a U-turn at an intersection, extending the risk confirmation time window or increasing the alarm trigger threshold can suppress unnecessary alarms, thereby systematically reducing the false trigger rate. It is understood that, in accordance with the embodiments of this application, while ensuring effective warnings for critical hazardous scenarios, it can significantly reduce interfering alarms, significantly improving user trust in the blind spot alarm system's alarm function and user experience. It is understood that the alarm system incorporating the blind spot monitoring alarm method of the embodiments of this application has the characteristics of high robustness, low false alarms, and compliance with mass production requirements.

[0235] It is understood that in other embodiments, depending on actual needs, the steps shown in the above embodiments can be combined, deleted, or replaced with other steps that are beneficial to achieving the purpose of this application, and this application does not impose any restrictions here.

[0236] This application also provides a schematic diagram of the structure of an electronic device 10'. The electronic device 10' may include at least one processor that executes instructions stored in a non-transitory computer-readable medium such as memory. The processor may be any conventional processor, such as a commercially available CPU. Optionally, the processor may be a special-purpose device such as an ASIC or other hardware-based processor. The memory may contain instructions (e.g., program logic) that can be executed by the processor to perform various functions of the vehicle 100, including the functions of the embodiments described above.

[0237] This application also provides a schematic diagram of the structure of an electronic device 10'. The electronic device 10' may include at least one processor that executes instructions stored in a non-transitory computer-readable medium such as memory. The processor may be any conventional processor, such as a commercially available central processing unit (CPU). Optionally, the processor may be a special-purpose device such as an ASIC or other hardware-based processor. The memory may contain instructions (e.g., program logic) that can be executed by the processor to perform various functions of the vehicle 100, including the functions of the embodiments described above.

[0238] Next, combine Figure 7 The structure of electronic device 10' will be described.

[0239] like Figure 7 As shown, the electronic device 10' includes one or more processors 101, system memory 102, non-volatile memory (NVM) 103, communication interface 104, input / output device 105, and system control logic unit 106 for coupling the processor 101, system memory 102, non-volatile memory 103, communication interface 104, and input / output (I / O) device 105. Wherein:

[0240] Processor 101 may include one or more processing units, such as a central processing unit, graphics processing unit (GPU), digital signal processor (DSP), microprocessor (MCU), artificial intelligence (AI) processor, field programmable gate array (FPGA), neural network processing unit (NPU), etc., or a processing module or processing circuit that may include one or more single-core or multi-core processors. In some embodiments, the CPU may be used to optimize the neural network model to be run, and the NPU may be used to run the neural network model to be run. Processor 101 is used to execute any of the blind zone monitoring methods described above.

[0241] System memory 102 is volatile memory, such as random-access memory (RAM), double data rate synchronous dynamic random access memory (DDR SDRAM), etc. System memory is used for temporary storage of data and / or instructions. For example, in some embodiments, system memory 102 can be used to store data provided by the aforementioned different services, such as sensor data, image data, or video data, and can also be used to store instructions for the blind spot monitoring methods provided in the aforementioned embodiments.

[0242] The non-volatile memory 103 may include one or more tangible, non-transitory computer-readable media for storing data and / or instructions. In some embodiments, the non-volatile memory 103 may include any suitable non-volatile memory and / or any suitable non-volatile storage device, such as a hard disk drive (HDD), compact disc (CD), digital versatile disc (DVD), solid-state drive (SSD), etc. In some embodiments, the non-volatile memory 103 may also be a removable storage medium, such as a secure digital (SD) memory card. In other embodiments, the non-volatile memory 103 may be used to store instructions for the blind zone monitoring methods provided in the foregoing embodiments.

[0243] Specifically, system memory 102 and non-volatile memory 103 may each include a temporary copy and a permanent copy of instruction 107. Instruction 107 may include, when executed by at least one of processors 101, causing electronic device 10' to implement the blind zone monitoring method provided in the embodiments of this application.

[0244] The communication interface 104 may include a transceiver for providing a wired or wireless communication interface for the electronic device 10', thereby enabling communication with any other suitable device via one or more networks. In some embodiments, the communication interface 104 may be integrated into other components of the electronic device 10', for example, the communication interface 104 may be integrated into the processor 101. In some embodiments, the electronic device 10' may communicate with other devices through the communication interface 104, for example, the electronic device 10' may obtain relevant data from other devices through the communication interface 104.

[0245] Input / output (I / O) device 105 can be an input device such as a keyboard or mouse, and an output device such as a monitor. Users can interact with electronic device 10' through input / output (I / O) device 105.

[0246] The system control logic unit 106 may include any suitable interface controller to provide any suitable interface to other modules of the electronic device 10'. For example, in some embodiments, the system control logic unit 106 may include one or more memory controllers to provide an interface to the system memory 102 and the non-volatile memory 103.

[0247] In some embodiments, at least one of the processors 101 may be packaged together with the logic of one or more controllers for the system control logic unit 106 to form a system in package (SiP). In other embodiments, at least one of the processors 101 may also be integrated on the same chip with the logic of one or more controllers for the system control logic unit 106 to form a system-on-chip (SoC).

[0248] Understandable. Figure 7 The structure of the electronic device 10' shown is merely an example. In other embodiments, the electronic device 10' may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0249] It is understood that the blind spot monitoring method mentioned in the embodiments of this application can be applied to electronic devices in vehicle 100. Figure 8 This is a schematic diagram of a possible functional framework of a vehicle 100 provided in an embodiment of this application.

[0250] like Figure 8 As shown, the functional framework of vehicle 100 may include various subsystems, such as the sensor system 10, control system 20, one or more peripheral devices 30 (one is shown as an example), power supply 40, and computer system 50. Optionally, vehicle 100 may also include other functional systems, such as an engine system that provides power to vehicle 100, etc., which are not limited herein. The sensor system 10 may include several detection devices that can sense the measured information and convert the sensed information into electrical signals or other required forms of information output according to a certain rule.

[0251] As shown in the figure, these detection devices may include a Global Positioning System (GPS) 11, a vehicle speed sensor 12, an Inertial Measurement Unit (IMU) 13, etc., and this application is not limited thereto. The GPS 11 is a system that uses GPS positioning satellites to perform real-time positioning and navigation globally. In this application, the GPS 11 can be used to achieve real-time positioning of the vehicle 100, providing the vehicle 100's geographical location information. The vehicle speed sensor 12 is used to detect the vehicle speed of the vehicle 100. The inertial measurement unit 13 may include a combination of an accelerometer and a gyroscope, and is a device for measuring the angular rate and acceleration of the vehicle 100. For example, during the movement of the vehicle 100, the inertial measurement unit can measure the changes in the vehicle's position and angle based on the vehicle's inertial acceleration, such as measuring the vehicle's acceleration and angular rate.

[0252] The control system 20 may include a steering unit 21, a braking unit 22, etc. The steering unit 21 may represent a system for adjusting the direction of travel of the vehicle 100, and may include, but is not limited to, a steering wheel or other structural devices for adjusting or controlling the direction of travel of the vehicle 100. The braking unit 22 may represent a system for slowing down the vehicle 100, and may also be referred to as the vehicle 100 braking system. It may include, but is not limited to, a brake controller, a reducer, or other structural devices for slowing down the vehicle 100. In practical applications, the braking unit 22 may utilize friction to slow down the tires of the vehicle 100, thereby slowing down the vehicle 100's speed.

[0253] Peripheral device 30 may include several components, such as the communication system 31, touch screen 32, user interface 33, etc., as shown in the figure. The communication system 31 is used to enable network communication between vehicle 100 and other devices besides vehicle 100. In practical applications, the communication system 31 can employ wireless communication technology or wired communication technology to achieve network communication between vehicle 100 and other devices. This wired communication technology can refer to communication between vehicle 100 and other devices via network cable or fiber optic cable, etc. This wireless communication technology includes, but is not limited to, Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Time Division Code Division Multiple Access (TD-SCDMA), Long Term Evolution (LTE), Wireless Local Area Networks (WLAN) (such as Wireless Fidelity (Wi-Fi) networks), Bluetooth (BT), Global Navigation Satellite System (GNSS), Frequency Modulation (FM), Near Field Communication (NFC), and Infrared (IR) technology, etc. The touchscreen 32 can be used to detect operation commands displayed on the touchscreen 32. For example, the user can perform touch operations on the content data displayed on the touchscreen 32 according to actual needs to achieve the corresponding function, such as playing music, video, or other multimedia files. User interface 33 may specifically be a touch panel for detecting operation commands on the touch panel. User interface 33 may also be a physical button or a mouse. User interface 33 may also be a display screen for outputting data and displaying images or data. Optionally, user interface 33 may also be at least one device belonging to the category of peripheral devices, such as a touch screen, microphone, and speaker.

[0254] Several functions of vehicle 100 are controlled and implemented by computer system 50. Computer system 50 may include multiple processors such as general-purpose processor 51', CDC 52, MDC 53, T... BOX54, as well as memory 55 (also known as storage device) and gateway 56.

[0255] In practical applications, the memory 55 can be located either inside or outside the computer system 50, such as as a cache in the vehicle 100; this application does not limit its location. The general-purpose processor 51' can be, for example, a graphics processing unit (GPU). General-purpose processor 51', CDC52, MDC53, T... BOX54 can be used to run relevant programs or instructions corresponding to programs stored in memory 55 to implement the corresponding functions of vehicle 100.

[0256] In some implementations, the general-purpose processor 51' can determine that a target obstacle exists in the vehicle's blind spot, where the target obstacle meets alarm conditions, including that the target obstacle is not located in a non-drivable area; and then a blind spot monitoring alarm is triggered. In this case, obstacles that are in the vehicle's blind spot but are in a non-drivable area can be directly filtered out, avoiding false alarms from a large number of obstacles that do not pose a collision risk, thereby improving the accuracy of the alarm.

[0257] In other implementations, the general-purpose processor 51' can also acquire first vehicle information at a first moment; generate a first monitoring blind zone based on the first vehicle information, and perform blind zone monitoring alarm based on the first monitoring blind zone; acquire second vehicle information at a second moment; generate a second monitoring blind zone based on the second vehicle information, and perform blind zone monitoring alarm based on the second monitoring blind zone, wherein the geometric parameters of the second monitoring blind zone are different from those of the first monitoring blind zone. Understandably, the difference in geometric parameters between the first monitoring blind zone generated at the first moment and the second monitoring blind zone generated at the second moment can improve the vehicle's ability to monitor blind zones, thereby improving the accuracy of the alarm.

[0258] The memory 55 may include volatile memory, such as RAM; it may also include non-volatile memory, such as ROM, flash memory, HDD, or SSD; or it may include a combination of the above types of memory. The memory 55 can be used to store a set of program code or instructions corresponding to program code, so that the general-purpose processor 51' can call the program code or instructions stored in the memory 55 to implement the corresponding functions of the vehicle 100. This function includes, but is not limited to, […]. Figure 8The functional framework diagram of vehicle 100 shown includes some or all of the functions. In this application, memory 55 can store a set of program code for controlling vehicle 100, including general-purpose processor 51', CDC 52, MDC 53, and T... The BOX54 can call this program code to control vehicle 100 to switch vehicle networks.

[0259] Optionally, in addition to storing program code or instructions, memory 55 may also store road maps, driving lines, or other structural devices used to adjust or control the direction of travel of vehicle 100.

[0260] It should be noted that the above Figure 8 This is merely a schematic diagram of one possible functional framework for vehicle 100. In practical applications, vehicle 100 may include more or fewer systems or components, and this application is not limiting. Various embodiments of the mechanisms disclosed in this application can be implemented in hardware, software, firmware, or combinations of these implementation methods. Embodiments of this application can be implemented as computer programs or program code executable on a programmable system, which includes at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device.

[0261] It should be understood that Figure 8 The functional framework structure of the vehicle 100 shown is only an example. In other embodiments, the vehicle 100 may include more or fewer modules, which is not limited herein.

[0262] This application also provides a computer program product that, when executed on a device, enables the device to implement the methods provided in the foregoing embodiments. For example, it can implement methods such as... Figure 2 or Figure 4 The blind spot monitoring method shown.

[0263] This application also provides a computer-readable storage medium storing one or more programs, which, when executed by a device, cause the device to implement the methods provided in the foregoing embodiments. For example, implementing... Figure 2 or Figure 4 The blind spot monitoring method shown.

[0264] Various embodiments of the mechanisms disclosed in this application can be implemented in hardware, software, firmware, or combinations of these implementation methods. Embodiments of this application can be implemented as computer programs or program code executable on a programmable system, the programmable system including at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device.

[0265] Program code can be applied to input instructions to execute the functions described in this application and generate output information. The output information can be applied to one or more output devices in a known manner. For the purposes of this application, the processing system includes any system having a processor such as, for example, a digital signal processor, a microcontroller, an application-specific integrated circuit, or a microprocessor.

[0266] The program code can be implemented using a high-level procedural language or an object-oriented programming language to communicate with the processing system. Assembly language or machine language can also be used when needed. In fact, the mechanisms described in this application are not limited to any particular programming language. In either case, the language can be a compiled language or an interpreted language.

[0267] In some cases, the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried on or stored thereon by one or more transient or non-transitory machine-readable (e.g., computer-readable) storage media, which may be read and executed by one or more processors. For example, the instructions may be distributed via a network or through other computer-readable media. Therefore, machine-readable media can include any mechanism for storing or transmitting information in a machine-readable (e.g., computer-readable) form, including but not limited to floppy disks, optical disks, CD-ROMs, compact disc-read-only memory (CD-ROMs), magneto-optical disks, read-only memory (ROM), random-access memory (RAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic cards or optical cards, flash memory, or tangible machine-readable storage for transmitting information (e.g., carrier waves, infrared signals, digital signals, etc.) using the Internet in the form of electrical, optical, acoustic, or other forms of propagation signals. Therefore, machine-readable media includes any type of machine-readable medium suitable for storing or transmitting electronic instructions or information in a machine-readable (e.g., computer-readable) form.

[0268] In the accompanying drawings, some structural or methodological features may be shown in a specific arrangement and / or order. However, it should be understood that such a specific arrangement and / or order may not be necessary. Rather, in some embodiments, these features may be arranged in a manner and / or order different from that shown in the illustrative drawings. Furthermore, the inclusion of structural or methodological features in a particular figure does not imply that such features are required in all embodiments, and in some embodiments, these features may be omitted or may be combined with other features.

[0269] It should be noted that all units / modules mentioned in the device embodiments of this application are logical units / modules. Physically, a logical unit / module can be a physical unit / module, a part of a physical unit / module, or a combination of multiple physical units / modules. The physical implementation of these logical units / modules themselves is not the most important factor; the combination of functions implemented by these logical units / modules is the key to solving the technical problems proposed in this application. Furthermore, to highlight the innovative aspects of this application, the above-described device embodiments of this application have not introduced units / modules that are not closely related to solving the technical problems proposed in this application. This does not mean that the above-described device embodiments do not contain other units / modules.

[0270] It should be noted that in the examples and description of this patent, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0271] Although this application has been illustrated and described with reference to certain preferred embodiments thereof, those skilled in the art will understand that various changes in form and detail may be made thereto without departing from the scope of this application.

Claims

1. A blind zone monitoring and alarm method, characterized in that, The method includes: The presence of a target obstacle in the vehicle's monitoring blind spot is determined, wherein the target obstacle meets the alarm conditions, and the alarm conditions include: the target obstacle is not located in a non-drivable area; Perform blind spot monitoring and alarm.

2. The blind zone monitoring and alarm method according to claim 1, characterized in that, The non-drivable areas include: physically blocked areas and custom-defined no-driving areas. The physical barrier area includes: the area outside the physical fence closest to the vehicle, and the area in the lane where the vehicle is located that is less than or equal to a first preset distance from the physical fence. The physical fence includes at least one of the following: curb, guardrail, water-filled barrier, and fence; The custom no-driving zone includes: the area outside the nearest double solid line of the vehicle, and the area at a distance greater than or equal to the nearest double solid line.

3. The blind zone monitoring and alarm method according to claim 1, characterized in that, The determination that a target obstacle exists in the vehicle's monitoring blind spot includes: Acquire vehicle information and perceive obstacles around the vehicle; Based on the vehicle information, a monitoring blind spot of the vehicle is generated, and preliminary obstacles that meet the alarm conditions are selected from the perceived obstacles around the vehicle. Based on the initially selected obstacles and the monitoring blind spot, it is determined that there is a target obstacle in the monitoring blind spot of the vehicle.

4. The blind zone monitoring and alarm method according to claim 3, characterized in that, The step of generating the vehicle's monitoring blind spot based on the vehicle information includes: The driving status type of the vehicle is identified based on the vehicle information; Based on the driving state type, a monitoring blind spot of the vehicle is generated according to a preset blind spot generation method corresponding to the driving state type. The geometric parameters of the generated monitoring blind spot are different for different driving state types.

5. The blind zone monitoring and alarm method according to claim 4, characterized in that, The driving status type includes at least one of the following: Driving on continuous curves, driving on non-continuous curves.

6. The blind zone monitoring and alarm method according to claim 5, characterized in that, When the driving state type is non-continuous curve driving, the preset blind spot generation method includes: Based on the distance from the rear axle to the B-pillar of the vehicle, the preset safe forward extension distance, the width of the vehicle, and the preset blind spot lateral extension distance, the rectangular boundary coordinates of the monitoring blind spot are determined. Based on the coordinates of the rectangular boundary, monitoring blind spots are generated on both sides of the vehicle.

7. The blind zone monitoring and alarm method according to claim 5, characterized in that, When the driving state type is continuous curve driving, the preset blind spot generation method includes: Based on the turning radius and width of the vehicle, the sector parameters of the first monitoring blind zone are obtained according to a preset annular sector calculation method, wherein the sector parameters include the inner arc length, the outer arc length, and the sector angle. Based on the sector parameters, monitoring blind spots are generated on both sides of the vehicle.

8. The blind zone monitoring and alarm method according to claim 3, characterized in that, The alarm conditions also include at least one of the following: The type of the target obstacle is a vehicle. The speed of the target obstacle meets a preset speed threshold. The heading angle difference between the target obstacle and the vehicle is less than a preset heading angle difference; The perception duration corresponding to the target obstacle reaches the preset perception duration.

9. The blind zone monitoring and alarm method according to any one of claims 3-8, characterized in that, The step of determining that the target obstacle exists in the vehicle's monitoring blind spot based on the initially selected obstacle and the monitoring blind spot includes: Obtain the initially selected obstacles; Candidate obstacles located in the candidate monitoring area are selected from the initial selection of obstacles; wherein the range of the candidate monitoring area is larger than the monitoring blind zone, and the candidate monitoring area includes the monitoring blind zone; The target obstacle is determined from the candidate obstacles.

10. The blind zone monitoring and alarm method according to claim 9, characterized in that, Determining the target obstacle from the candidate obstacles includes: When the number of candidate obstacles is equal to 1, if the candidate obstacle is located within the vehicle's monitoring blind spot, the candidate obstacle is designated as the target obstacle; or, if the candidate obstacle is located within the vehicle's monitoring blind spot and the candidate obstacle meets the collision time condition, the candidate obstacle is designated as the target obstacle.

11. The blind zone monitoring and alarm method according to claim 9, characterized in that, Determining the target obstacle from the candidate obstacles includes: When the number of candidate obstacles is greater than or equal to 2, and there is a through obstacle among the candidate obstacles that meets the sandwich passage condition, the through obstacle that is closest to the vehicle in longitudinal distance or has the shortest collision time and is located in the monitoring blind zone is selected as the target obstacle; or, The obstacle that is closest to the vehicle in longitudinal distance or has the shortest collision time, is located in the monitoring blind zone, and whose collision with the vehicle meets the collision time condition is selected as the target obstacle.

12. The blind zone monitoring and alarm method according to claim 9, characterized in that, Determining the target obstacle from the candidate obstacles includes: When the number of candidate obstacles is greater than or equal to 2, and the sandwich passage condition is not met, the candidate obstacle that is closest to the vehicle in longitudinal distance or has the shortest collision time and is located in the monitoring blind zone is selected as the target obstacle; or, The candidate obstacle that is closest to the vehicle in longitudinal distance or has the shortest collision time, is located in the monitoring blind zone, and whose collision with the vehicle meets the collision time condition is selected as the target obstacle.

13. The blind zone monitoring and alarm method according to claim 11, characterized in that, The sandwich passage conditions include: The width of the candidate obstacle is less than the lateral clearance distance between the vehicle and the nearest longitudinal candidate obstacle; The position of the candidate obstacle is located within the lateral interval corresponding to the gap between the two nearest outer edges of the vehicle body between the vehicle and the longitudinally nearest candidate obstacle. The candidate obstacle exhibits a tendency to move closer to the vehicle; The candidate obstacle remains stable relative to the motion trend of the vehicle.

14. The blind zone monitoring and alarm method according to claim 13, characterized in that, The candidate obstacle was determined to have a tendency to move closer to the vehicle using the following method: If the longitudinal velocity of the candidate obstacle is greater than the longitudinal velocity of the vehicle, and the lateral distance between the candidate obstacle and the vehicle is less than a lateral distance threshold, it is determined that the candidate obstacle has a tendency to move closer to the vehicle. and, The stability of the motion trend of the candidate obstacle relative to its proximity to the vehicle is determined by the following method: If the number of tracking frames for the candidate obstacle is greater than a preset number of tracking frames, the speed confidence of the candidate obstacle is greater than a confidence threshold, and the speed magnitude of the candidate obstacle is greater than a speed magnitude threshold, then it is determined that the motion trend of the candidate obstacle relative to the approaching vehicle remains stable.

15. The blind zone monitoring and alarm method according to claim 11 or 12, characterized in that, The collision time conditions include: When the vehicle does not turn or make a U-turn, the collision time from the candidate obstacle to the vehicle is less than or equal to a collision time threshold. When the vehicle turns or makes a U-turn, the collision time from the candidate obstacle to the vehicle is less than or equal to a collision time extension threshold, wherein the collision time extension threshold is greater than the collision time threshold.

16. The blind zone monitoring and alarm method according to claim 1, characterized in that, The blind spot monitoring and alarm system includes: When the vehicle intends to change lanes, the alarm level for blind spot monitoring of the vehicle is increased; The alarm will be triggered according to the alarm method corresponding to the upgraded alarm level.

17. An electronic device, characterized in that, include: Memory, used to store instructions; At least one processor is configured to execute the instructions to cause the electronic device to implement the blind spot monitoring alarm method according to any one of claims 1-16.

18. A vehicle, characterized in that, The vehicle stores instructions that are executed on the vehicle to enable the vehicle to implement the blind spot monitoring and alarm method as described in any one of claims 1-16.

19. A computer-readable storage medium, characterized in that, The readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the blind spot monitoring and alarm method according to any one of claims 1-16.

20. A computer program product, characterized in that, When the computer program product is run on the device, it causes the device to execute the blind spot monitoring and alarm method according to any one of claims 1-16.

Images