A passenger car side rear blind area adaptive monitoring method and system

Abstract

The application belongs to the technical field of vehicle safety monitoring, and specifically discloses a passenger car rear side blind area adaptive monitoring method and system, the method comprising the following steps: acquiring a current vehicle model, left / right rearview mirror angle parameters and spatial position data of a current driver's eyes relative to a specified reference object; based on a blind area parameter calibration library corresponding to the current vehicle model, acquiring optimal left / right rear side blind area parameters of the driver, the blind area parameter calibration library comprising a correspondence among vehicle model data, a position of a human eye relative to a specified reference object, left / right rearview mirror angle parameters and left / right rear side blind area parameters. The application can adaptively determine more reasonable and effective blind area warning area parameters according to the position of the current driver's eyes, so that the blind area covered by subsequent monitoring and warning can cover all dangerous areas that the driver cannot see.

Description

Technical Field

[0001] This invention belongs to the field of vehicle blind spot monitoring technology, and particularly relates to an adaptive monitoring method and system for the side and rear blind spots of passenger vehicles. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Blind spot monitoring, lane change assist, and door opening warning functions in automotive intelligent driving assistance modules are all based on the scenario of accidents caused by blind spots when drivers and passengers exit the vehicle after driving or parking. External sensors provide hazard warnings to drivers and passengers, which will greatly reduce accidents caused by drivers and passengers not observing carefully or being unable to observe due to blind spots. This has huge social benefits and is also a function that users urgently need to configure in vehicle intelligent driving assistance functions.

[0004] Existing technologies include extensive research on blind spot monitoring sensor technology, blind spot monitoring and warning strategies, algorithms, target object identification within blind spots, and the echo effects of objects like long, regular iron fences within blind spots. These technologies are constantly evolving and maturing. However, as OEMs increasingly adopt this technology, it has been discovered that differences in user groups, driver body type, and seating posture lead to a discrete distribution of the H-point (or eye point). Furthermore, variations in the style and curvature of exterior rearview mirrors result in significant differences in blind spots between models. If the same blind spot parameters are input into the intelligent driving assistance system, it cannot guarantee complete coverage of all potentially dangerous areas to the side and rear—the truly necessary blind spots for warning. Summary of the Invention

[0005] To overcome the shortcomings of the prior art, the present invention provides a method for calibrating blind spot parameters for passenger vehicles, which can adaptively determine more reasonable and effective blind spot warning area parameters based on the current eye position of the driver, so that the blind spot area targeted by subsequent monitoring and warning can cover all dangerous areas that the driver cannot see.

[0006] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:

[0007] An adaptive monitoring method for the side and rear blind spots of a passenger vehicle includes the following steps:

[0008] Acquire the current vehicle model, left / right rearview mirror angle parameters, and spatial position data of the current driver's eyes relative to a specified reference object;

[0009] Based on the current vehicle corresponding blind area parameter calibration library, the best left / right rear blind area parameter of the driver is obtained, and the blind area parameter calibration library includes the correspondence between the vehicle data, the position of the human eye relative to the specified reference, the left / right rearview mirror angle parameter, and the left / right rear blind area parameter.

[0010] Further, the current driver's eye position data relative to the specified reference is obtained by:

[0011] After the vehicle is started, a plurality of driver face images are obtained based on the vehicle-mounted camera at a set interval, and the position data of the eyes relative to the camera is calculated respectively;

[0012] When the difference between adjacent position data in a plurality of continuous position data is less than a set value, the average value of the plurality of continuous position data is taken as the eye position of the driver.

[0013] Further, the blind area parameter calibration library of each vehicle is constructed by:

[0014] Obtain the identifiable field of view range when a plurality of drivers drive with different sitting positions and different left / right rearview mirror angles;

[0015] Based on the identifiable field of view range, the corresponding blind area parameter is obtained;

[0016] The position data of the driver's eyes relative to the specified reference, the left / right rearview mirror angle, and the left / right rear blind area parameter are associated to construct the blind area parameter calibration library.

[0017] Further, the blind area parameter acquisition method includes:

[0018] Reference vehicles are respectively arranged at equal distances on the left and right rear of the vehicle to be tested, and the lateral distance between the reference vehicle and the vehicle to be tested is the width of a single lane;

[0019] In different driving environments, the range of the reference vehicle that can be seen by the driver is obtained;

[0020] The included angle between the left and right field of view edge lines and the vehicle body axis is taken as the left and right rear blind area parameters respectively, wherein the left field of view edge line is the connecting line between the outermost edge point of the left rearview mirror and the leftmost point of the range of the reference vehicle that can be seen on the left rear, and the right field of view edge line is the connecting line between the outermost edge point of the right rearview mirror and the rightmost point of the range of the reference vehicle that can be seen on the right rear.

[0021] Further, the best left / right rear blind area parameter of the driver includes:

[0022] According to the driver's eye position, find the position closest to the driver's eye position in the blind area parameter calibration library and less than the set threshold;

[0023] In the left rear blind area parameters and right rear blind area parameters associated with the position, respectively according to the angle of the left and right rearview mirrors, find the left and right rear blind area parameter calibration values.

[0024] Further, the blind area parameter calibration library stores the maximum and minimum values of the left and right rear blind area parameter calibration values for the same eye position;

[0025] After finding the left and right rear blind area parameter calibration values, the current driving mode is also obtained;

[0026] According to the current driving mode, the maximum and minimum values of the left and right rear blind area parameters are respectively weighted and summed to obtain the left and right rear blind area parameters.

[0027] Further, the blind area calibration library stores default blind area parameters;

[0028] If the position closest to the driver's eye position and less than the set threshold cannot be found, the default blind area parameters are used;

[0029] If the corresponding position is found but the angle of the current left or right rearview mirror cannot be found, the blind area parameters are estimated according to the linear relationship between the left rearview mirror angle and the left blind area parameters, or the linear relationship between the right rearview mirror angle and the right blind area parameters.

[0030] Further, after obtaining the optimal left / right rear blind area parameters, the blind area range is determined according to the blind area parameters and the set visual angle range:

[0031] Based on the set maximum visual angle of the human eye, the left / right visual angle edge line is drawn according to the current driver's eye position;

[0032] In the four regions divided by the intersection of the left visual field edge line and the left visual angle edge line, the left rear region is the left rear blind area range; in the four regions divided by the intersection of the right visual field edge line and the right visual angle edge line, the right rear region is the right rear blind area range.

[0033] One or more embodiments provide a passenger car side rear blind area adaptive monitoring system, comprising:

[0034] A current data acquisition module for acquiring current vehicle type, left / right rearview mirror angle parameters and current driver's eye spatial position data relative to a specified reference object;

[0035] The blind area parameter judgment module is configured to obtain the optimal left / right rear blind area parameter of the driver based on a blind area parameter calibration library corresponding to the current vehicle model, wherein the blind area parameter calibration library comprises vehicle model data, the position of the human eye relative to a specified reference object, the angle parameter of the left / right rearview mirror, and the corresponding relationship between the left / right rear blind area parameter.

[0036] One or more embodiments provide a computer readable storage medium having stored thereon a computer program, which, when executed by a processor, implements the adaptive monitoring method for the side rear blind area of the passenger vehicle.

[0037] One or more embodiments provide a vehicle controller connected with a camera for shooting the image of the driver's face, and configured to implement the adaptive monitoring method for the side rear blind area of the passenger vehicle.

[0038] The above one or more technical solutions have the following beneficial effects:

[0039] The present application provides a dynamic blind area parameter confirmation method, which can adaptively determine more reasonable and effective blind area warning region parameters according to the current driver's eye position, so that the blind area covered by the subsequent monitoring and warning can completely cover all dangerous areas that the driver cannot see. BRIEF DESCRIPTION OF DRAWINGS

[0040] The accompanying drawings, which form a part of the present description, are included to provide a further understanding of the application and are incorporated in and constitute a part of this application. The embodiments of the application illustrated in the drawings are provided to explain the present application and are not meant to limit the application.

[0041] Figure 1 A flowchart of the adaptive monitoring method for the side rear blind area of the passenger vehicle in one or more embodiments of the present application;

[0042] Figure 2 A diagram for solving the driver's eye coordinates in one or more embodiments of the present application;

[0043] Figure 3 A diagram for dividing the blind area in one or more embodiments of the present application;

[0044] Figure 4 A diagram for testing the blind area in one or more embodiments of the present application. DETAILED DESCRIPTION

[0045] It should be noted that the following detailed description is exemplary in nature and is intended to provide further description of the application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0046] It is to be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, steps, operations, elements, components, and / or groups thereof, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof.

[0047] The embodiments in the present application and the features in the embodiments can be combined with each other in the case of no conflict.

[0048] Embodiment One

[0049] Since the field of view of the driver observing the side rear area of the outside rearview mirror is mainly limited by the vehicle model, the angle of the rearview mirror and the position of the human eye, and the position of the driver's eyes is related to the sitting posture of the driver of different body types, and the adjustment angle of the outside rearview mirror is related to the driving style of the driver. This embodiment calibrates the blind area parameters of drivers of different driving styles and body types under different angles of the outside rearview mirror for different vehicle models by the vehicle manufacturer, obtains the corresponding relationship between the position of the driver's eyes and the blind area parameters under different vehicle models and different angles of the outside rearview mirror, and constructs a blind area parameter calibration library. Based on the blind area parameter calibration library, when the user drives the vehicle, the vehicle can automatically obtain the position of the user's eyes, and combine the vehicle model data and the angle of the rearview mirror of the current vehicle to obtain the blind area parameters suitable for the user, realize the adjustment of the adaptive blind area warning range, and further improve the driving safety of the vehicle.

[0050] Specifically, the embodiment discloses a passenger car side rear blind area adaptive monitoring method based on passenger car blind area parameter calibration, as shown in Figure 1 The method comprises the following steps:

[0051] Step 1: Obtain the current vehicle model data, left / right outside rearview mirror angle parameter and the spatial position data of the current driver's eyes relative to a specified reference object.

[0052] The vehicle model data is built in the vehicle controller before the vehicle is delivered. The vehicle model data includes but is not limited to vehicle model, vehicle front track, wheelbase, vehicle body length, etc.

[0053] The outside rearview mirror angle parameter is obtained through the angle sensor arranged on the outside rearview mirror. The driver can adjust the outside rearview mirror to the appropriate angle through the outside rearview mirror adjustment mechanism to meet his own driving needs. The outside rearview mirror adjustment mechanism includes an angle sensor for real-time acquisition of the outside rearview mirror angle information and feedback to the vehicle controller.

[0054] The specified reference object is preferably an object with a fixed position in the vehicle, such as a vehicle-mounted camera itself for shooting the driver, or a driver's seat, etc.

[0055] Specifically, if the camera is taken as the reference object, the spatial position data acquisition method of the current driver's eyes relative to the specified reference object is as follows:

[0056] Step 1.1: After the vehicle starts, a plurality of driver face images are acquired based on the vehicle-mounted camera at a set interval;

[0057] Step 1.2: The eye position of each of the plurality of driver face images is identified;

[0058] Step 1.3: The position data of the centers of the eyes in the plurality of driver face images relative to the camera are acquired;

[0059] Step 1.4: The plurality of acquired position data are sorted in time sequence, and when the difference between adjacent position data in a plurality of continuous position data is less than a set value for a plurality of continuous times, it is considered that the driver's posture is stable, and the average value of the plurality of continuous position data is taken as the eye position of the driver.

[0060] Figure 2 The solution based on the seat as the reference object is shown in the schematic diagram. The vehicle-mounted camera can be a camera equipped in a driver monitoring system (DMS) in the passenger compartment. The eye position data can be any existing technology for three-dimensional coordinate positioning based on image data, which is not limited here.

[0061] Since the driver's eye position is related to the sitting posture of the driver with different body shapes, within a certain time after the vehicle starts, the driver is likely to make slight adjustments to the posture according to his own comfort. In order to obtain the eye position that is more in line with the true situation of the driver, the embodiment acquires a plurality of images within a certain time after the vehicle starts, and takes the eye position that tends to be stable as the basis for subsequent blind area parameter matching, which is more accurate.

[0062] Step 2: Based on the blind area parameter calibration library corresponding to the current vehicle model, the best left / right rear blind area parameters of the driver are acquired, and the blind area parameter calibration library includes vehicle model data, outside rearview mirror angle parameters, position of the human eye relative to the specified reference object, and corresponding relationship between the blind area parameters.

[0063] Through the above method, the vehicle can adaptively adjust the blind area parameters according to the spatial position of the driver's eyes, which is helpful for more accurately monitoring the blind area range subsequently.

[0064] The blind area parameter calibration library construction method includes:

[0065] (1) Through testing, for different vehicle models, the identifiable field of view ranges of a plurality of drivers in different left / right outside rearview mirror angles and comfortable sitting postures are acquired under different driving environments.

[0066] To cover as many as possible eye positions of drivers and adjustment angles of the rearview mirror, the drivers include different heights and body shapes, and the driving styles include aggressive to conservative.

[0067] The driving environment includes the weather environment and the driving scene. Since whether the weather is sunny or the light is sufficient is an important factor affecting the driver's vision, in order to obtain the maximum possible blind area range and maximize the safety of driving, the embodiment selects a rainy evening; the driving scene includes urban and suburban areas.

[0068] Other requirements: Before the test, the tester adjusts the seat and rearview mirror according to the habit; the tester sits in the normal driving posture and head posture; the co-driver sits in a natural state.

[0069] Before calculating the visible range, the core issues that need to be clarified include: 1. Define the side rear invisible area, visible area, and thinking area; 2. Define the difference between static blind area and dynamic blind area; 3. Balance the driving style and observation of the driver; 4. Test scene setting; 5. Data processing method.

[0070] Problem one: Define the side rear invisible area, visible area, and thinking area

[0071] The side rear area, under normal driving habits and scenes, we can only obtain through the rearview mirror, so there will be a clear boundary line (the edge of the field of view) to distinguish the visible area from the invisible area. As long as the driver does not deliberately adjust the head position and posture, this field of view boundary line is clearly determined. Since other road participants, especially cars and trucks, have a larger width, some positions may be in the visible area and some positions may be in the invisible area. When the very obvious features of the target are in the visible area, we can quickly and clearly observe and monitor the target. Although the target is not entirely in the visible area, it can be considered visible. If the part of the target in the visible area needs to be carefully observed and judged to identify whether it is another road participant due to the lack of obvious features or due to the color blending with the surrounding environment, weak external light source, rain and fog on the car rearview mirror, etc., this area is defined as the thinking area. This area will change within a certain range depending on the driver's driving style, observation level, vehicle speed, thinking area vehicle features, external light source environment, and weather-induced rain and fog on the rearview mirror.

[0072] Problem two: Define the difference between static blind area and dynamic blind area

[0073] When the vehicle stops at a location, we have enough time to observe the side rear area, and the impact is that the thinking area will be relatively greatly compressed, static blind area ≈ invisible area; when the vehicle is driving on a relatively busy road section, as the vehicle speed increases, the time and thinking energy we use to observe the side rear area will become very short, and our main energy will be used to judge the traffic state in front and side front, and the impact is that the thinking area will be relatively greatly expanded, dynamic blind area ≈ invisible area + thinking area.

[0074] Problem three: balance the driving style and observation of the driver

[0075] Through the elaboration of problem one and problem two, we find that the key point lies in the definition of the thinking area. In addition to the influence of rain and mist on the field of view due to weather factors, the biggest variable is the driving style and observation of the driver. In the early stage of vehicle design, based on the standard man, the driver's sitting posture, eye position and direct and indirect fields of view will be checked, and the standard rearview mirror field of view area will be included.

[0076] When determining the blind area range, the concept of thinking area is introduced, that is, the influence of weather, vehicle speed and driver's subjective consciousness is added, which is more flexible than fixed blind area setting. The blind area parameters are obtained by taking the left and right side rear reference vehicles as reference, which is more in line with the scene of the vehicle driving on the road, and the obtained blind area parameters are more reasonable.

[0077] Based on the above definition, it can be known that the identifiable field of view range includes visible area, whether it includes thinking area and the size of the included thinking area range are related to weather, road conditions and driver's subjective factors. Therefore, in this embodiment, the weather is set to be rainy evening, so as to obtain the minimum visible area of each driver, thereby obtaining a safer blind area region.

[0078] Of course, those skilled in the art can understand that if more detailed blind area parameters are wanted for different weather or different driving environment, more kinds of meteorological environment and driving scene can be selected for testing.

[0079] As Figures 3-4 shown, the identifiable field of view range calculation method is:

[0080] A, reference objects are arranged at equal distances on the left and right sides of the vehicle, and the reference objects are vehicles in this embodiment, which are used to simulate side rear vehicles; taking the left rear as an example, considering that the limit position relationship of the side blind area of two vehicles is that the vehicle presses the left side road line, the left side blind area vehicle interval lane presses the right side line, and the lateral distance of two vehicles is the width of a single lane, which is 3.5m.

[0081] B, record the range of reference objects that the driver can see, and in this embodiment, the size of the vehicles behind the left and right sides that can be seen. Due to the position relationship of dynamic testing and the influence of safety, the opinion obtained from the dynamic blind area is transferred to static testing. As shown in the figure, according to the data obtained in question three, the judgment of the thinking area is balanced (the intermediate state is late), such as the left rear side seeing the right front lamp of the left vehicle as a clear visible feature (about 0.3m), and the right rear side seeing 1 / 3 of the right vehicle as a clear visible feature (about 0.6m).

[0082] C, collect the thinking area judgment criteria after dynamic driving of no less than 30km including urban and suburban working conditions, such as when each of the left and right rear areas sees how much in front of the vehicle to measure when the road participants are obviously determined.

[0083] (2) Obtain corresponding blind area parameters based on the identifiable field of view range.

[0084] In this embodiment, the blind area parameters include the included angle between the left / right side field of view edge line and the vehicle body axis. Among them, the left side field of view edge line is the line connecting the outermost edge point of the left rearview mirror and the leftmost point of the reference object range that can be seen behind the left side, and the right side field of view edge line is the line connecting the outermost edge point of the right rearview mirror and the rightmost point of the reference object range that can be seen behind the right side.

[0085] (3) Based on the rearview mirror angle, the position data of the driver's eyes relative to the specified reference object, and the left / right blind area parameters, a blind area parameter calibration library is constructed.

[0086] In order to obtain a complete blind area parameter calibration library, a large number of tests need to be carried out for each vehicle type, and sufficient test data need to be collected. After obtaining a large amount of test data, the test data is processed in this embodiment, and for each vehicle type, a blind area parameter calibration library is constructed respectively.

[0087] As a specific implementation, constructing a blind area parameter calibration library specifically includes: regarding positions with an eye position interval less than a set threshold as the same position, for the same eye position, a plurality of blind area parameters under each angle of the left and right rearview mirrors are obtained respectively, and the minimum value under each angle of the left and right sides is selected as the calibration value. In this embodiment, the minimum included angle between the left and right side field of view edge lines and the vehicle body axis is selected as the calibration value.

[0088] As another specific implementation, constructing a blind area parameter calibration library specifically includes: regarding positions with an eye position interval less than a set threshold as the same position, for the same eye position, a plurality of blind area parameters under each angle of the left and right rearview mirrors are obtained respectively, and the maximum and minimum values under each angle of the left and right rearview mirrors are selected as the calibration values for storage.

[0089] After obtaining the driver's eye position and the left and right side mirror angles in step 1, the corresponding blind area parameters can be obtained from the blind area parameter calibration library by searching.

[0090] As a specific embodiment, when the minimum angle between the left and right side field of view edge lines and the vehicle body axis is used as the calibration value in the blind area parameter calibration library, obtaining the corresponding blind area parameters from the blind area parameter calibration library specifically includes:

[0091] A. First, according to the driver's eye position, find the position in the blind area parameter calibration library that is closest to the driver's eye position and has a distance less than a set threshold;

[0092] B. Then, in the left and right rear blind area parameters associated with the position, respectively according to the angles of the left and right rearview mirrors, find the left and right rear blind area parameter calibration values.

[0093] As another specific embodiment, when the maximum and minimum values at each angle of the left and right side mirrors are used as the calibration values for storage in the blind area parameter calibration library, obtaining the corresponding blind area parameters from the blind area parameter calibration library specifically includes:

[0094] A. First, according to the driver's eye position, find the position in the blind area parameter calibration library that is closest to the driver's eye position and has a distance less than a set threshold;

[0095] B. Find the maximum and minimum calibration values of the left and right rear blind area parameters associated with the position, obtain the current driving mode, and perform weighted summation on the maximum and minimum calibration values according to the driving mode to obtain the blind area parameter.

[0096] The corresponding multiple blind area parameters under the same eye position correspond to aggressive to conservative driving styles from small to large, and common driving modes include eco (economic) mode, comfort (comfort) mode, sport (sport) mode, etc., which also correspond to different driving styles. Therefore, this embodiment combines the driving mode and solves the blind area parameter suitable for the current driver by weighted summation of the maximum and minimum calibration values. The weight coefficients of the maximum and minimum calibration values are 1, if the current driving mode is sport mode, the weight of the minimum calibration value is set to a value of 0.9-1, and if the current driving mode is eco mode, the weight of the maximum calibration value is set to a value of 0.9-1.

[0097] The method further includes step 3: determining the blind area range according to the blind area parameter and the set viewing angle range. The blind area range is the area that the controller monitors and warns against during the use of the vehicle.

[0098] Specifically, the blind area range calculation method is: first, connect the outermost of the left rearview mirror with the distance of the reference object that can be seen behind the left side, and connect the outermost of the right rearview mirror with the distance of the reference object that can be seen behind the right side, to obtain the left and right side of the field of view edge line; then, according to the driver's eye position, draw the left and right side of the visual angle boundary line based on the maximum visual angle, in this embodiment, the visual angle boundary line is drawn according to the maximum horizontal visual angle of 156°; according to the left side of the visual field edge line and the left side of the visual angle edge line, and the right side of the visual field edge line and the right side of the visual angle edge line, the left and right rear blind area ranges are determined respectively.

[0099] The left side of the visual field edge line and the left side of the visual angle edge line intersect to divide four regions, and the left rear region in the four regions is the left rear blind area range; similarly, the right side of the visual field edge line and the right side of the visual angle edge line intersect to divide four regions, and the right rear region in the four regions is the right rear blind area range.

[0100] In addition, since the test data in the blind area calibration library may not completely cover all possible eye positions and rearview mirror angles, this embodiment also gives a blind area parameter calculation scheme, which specifically includes:

[0101] A. The blind area calibration library stores default blind area parameters. If no position closest to the driver's eye position and less than a set threshold is found, the default blind area parameters are used;

[0102] B. If a position closest to the driver's eye position and less than a set threshold is found, but the angle of the current left or right rearview mirror cannot be found, the calibration value is estimated according to the relationship between the left rearview mirror angle and the left side blind area parameter, or the relationship between the right rearview mirror angle and the right side blind area parameter. In this embodiment, the relationship fitting is performed according to the left rearview mirror angle and the left side blind area parameter, and the right rearview mirror angle and the right side blind area parameter in the test data.

[0103] Embodiment two

[0104] A passenger car rear blind area adaptive monitoring system, comprising:

[0105] A current data acquisition module for acquiring current vehicle type, left / right rearview mirror angle parameters and current driver's eye position data relative to a specified reference object;

[0106] A blind area parameter judgment module for obtaining the best left / right side rear blind area parameters of the driver based on the blind area parameter calibration library corresponding to the current vehicle type, wherein the blind area parameter calibration library includes the correspondence between the vehicle type data, the position of the human eye relative to the specified reference object, the left / right rearview mirror angle parameters and the left / right side rear blind area parameters.

[0107] Embodiment three

[0108] The purpose of this embodiment is to provide a computer-readable storage medium.

[0109] A computer-readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the method described in embodiment one.

[0110] Embodiment four

[0111] The purpose of this embodiment is to provide a vehicle controller.

[0112] A vehicle controller, connected with a camera for shooting the image of the driver's face, is configured to implement the adaptive monitoring method for the blind area behind the passenger car described in embodiment one.

[0113] The steps involved in the above embodiments two to five correspond to the method of embodiment one, and the specific embodiments can refer to the relevant description part of embodiment one. The term "computer-readable storage medium" should be understood to include a single medium or multiple media of one or more instruction sets; it should also be understood to include any medium capable of storing, encoding, or carrying a set of instructions for execution by a processor and causing the processor to perform any of the methods in the present application.

[0114] Although the specific embodiments of the present application are described above in combination with the accompanying drawings, it is not a limitation on the scope of protection of the present application. Those skilled in the art should understand that various modifications or changes made on the basis of the technical solutions of the present application without creative labor are still within the scope of protection of the present application.

Claims

1. An adaptive monitoring method for the side and rear blind spots of a passenger vehicle, characterized in that, Includes the following steps: Acquire the current vehicle model, left / right rearview mirror angle parameters, and spatial position data of the current driver's eyes relative to a specified reference object; Based on the blind spot parameter calibration library corresponding to the current vehicle model, the optimal left / right rear blind spot parameters of the driver are obtained. The blind spot parameter calibration library includes vehicle model data, the position of the human eye relative to a specified reference object, the left / right rearview mirror angle parameters, and the correspondence between the left / right rear blind spot parameters. Obtaining the optimal left / right rear blind spot parameters for the driver includes: Based on the driver's eye position, find the location in the blind spot parameter calibration library that is closest to the driver's eye position and is less than a set threshold; In the left rear blind spot parameters and right rear blind spot parameters associated with this position, find the calibration values ​​of the left rear blind spot parameters and right rear blind spot parameters respectively according to the angles of the left rearview mirror and the right rearview mirror; The blind spot parameter calibration library stores the maximum and minimum values ​​of the blind spot parameter calibration values ​​for the left rear and right rear for the same eye position; After finding the parameter calibration values ​​for the left rear and right rear blind spots, the current driving mode is also obtained; Based on the current driving mode, the maximum and minimum values ​​of the left rear and right rear blind spot parameters are weighted and summed to obtain the left rear and right rear blind spot parameters.

2. The adaptive monitoring method for side and rear blind spots of passenger vehicles as described in claim 1, characterized in that, The method for obtaining the spatial position data of the driver's eyes relative to the specified reference object is as follows: After the vehicle starts, multiple facial images of the driver are acquired at set intervals using the onboard camera, and the position data of the eyes relative to the camera are calculated for each image. When the difference between adjacent location data in a series of consecutive location data is less than a set value, the average value of the series of location data is taken as the driver's eye position.

3. The adaptive monitoring method for side and rear blind spots of passenger vehicles as described in claim 1, characterized in that, The method for constructing the blind spot parameter calibration library for each vehicle model is as follows: Acquire the identifiable field of vision of multiple drivers driving in different seating positions and with different left / right rearview mirror angles; Based on the identifiable field of view, the corresponding blind zone parameters are obtained; By correlating the driver's eye position relative to a specified reference object, the left / right rearview mirror angles, and the left / right rear blind spot parameters, a blind spot parameter calibration library is constructed.

4. The adaptive monitoring method for side and rear blind spots of passenger vehicles as described in claim 1, characterized in that, The method for obtaining the blind zone parameters includes: Reference vehicles are set up at equal distances to the left and right rear of the vehicle to be tested, and the lateral distance between the reference vehicles and the vehicle to be tested is the width of a single lane. Under different driving conditions, obtain the range of reference vehicles that the driver can see; The angles between the left and right edge lines of the field of vision and the vehicle's axis are used as the parameters for the left and right rear blind spots, respectively. The left edge line of the field of vision is the line connecting the outermost edge of the left rearview mirror to the leftmost point of the reference vehicle range visible from the left rear. The right edge line of the field of vision is the line connecting the outermost edge of the right rearview mirror to the rightmost point of the reference vehicle range visible from the right rear.

5. The adaptive monitoring method for side and rear blind spots of passenger vehicles as described in claim 1, characterized in that, The blind zone calibration library stores default blind zone parameters; If no position is found that is closest to the driver's eye position and the distance is less than the set threshold, the default blind spot parameter is used. If the corresponding location is found, but the current angle of the left or right rearview mirror cannot be found, the blind spot parameters are estimated based on the linear relationship between the left rearview mirror angle and the left blind spot parameter, or the linear relationship between the right rearview mirror angle and the right blind spot parameter.

6. The adaptive monitoring method for the side and rear blind spots of a passenger vehicle as described in claim 4, characterized in that, After obtaining the optimal left / right rear blind spot parameters, the blind spot range is also determined based on the blind spot parameters and the set viewing angle range: Based on the maximum field of view of the human eye, draw the left and right view edge lines according to the current position of the driver's eyes; The area divided into four regions by the intersection of the left visual field edge line and the left viewing angle edge line is the left rear blind spot; the area divided into four regions by the intersection of the right visual field edge line and the right viewing angle edge line is the right rear blind spot.

7. An adaptive monitoring system for the side and rear blind spots of a passenger vehicle, characterized in that, include: The current data acquisition module is used to acquire the current vehicle model, left / right rearview mirror angle parameters, and the spatial position data of the current driver's eyes relative to a specified reference object; The blind spot parameter determination module is used to obtain the optimal left / right rear blind spot parameters of the driver based on the blind spot parameter calibration library corresponding to the current vehicle model. The blind spot parameter calibration library includes vehicle model data, the position of the human eye relative to a specified reference object, the left / right rearview mirror angle parameters, and the correspondence between the left / right rear blind spot parameters. Obtaining the optimal left / right rear blind spot parameters for the driver includes: Based on the driver's eye position, find the location in the blind spot parameter calibration library that is closest to the driver's eye position and is less than a set threshold; In the left rear blind spot parameters and right rear blind spot parameters associated with this position, find the calibration values ​​of the left rear blind spot parameters and right rear blind spot parameters respectively according to the angles of the left rearview mirror and the right rearview mirror; The blind spot parameter calibration library stores the maximum and minimum values ​​of the blind spot parameter calibration values ​​for the left rear and right rear for the same eye position; After finding the parameter calibration values ​​for the left rear and right rear blind spots, the current driving mode is also obtained; Based on the current driving mode, the maximum and minimum values ​​of the left rear and right rear blind spot parameters are weighted and summed to obtain the left rear and right rear blind spot parameters.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the adaptive monitoring method for the side and rear blind spots of a passenger vehicle as described in any one of claims 1-6.

9. A vehicle controller connected to a camera for capturing images of a driver's face, characterized in that, It is configured to implement the adaptive monitoring method for the side and rear blind spots of a passenger vehicle as described in any one of claims 1-6.

Images