A hud image display calibration method, device and storage medium

Abstract

The application discloses a HUD image display calibration method and device and a storage medium, relates to the technical field of HUD image calibration, and comprises the following steps: acquiring the eye movement range of different users in different use areas when driving a vehicle according to the use area of the vehicle, and recording the initial eye movement range data; respectively performing eye movement range preprocessing on the initial eye movement range data of different use areas to obtain reference eye movement range data of different use areas; and performing eye box range acquisition processing to obtain eye box range position data of different use areas; and based on the corrected eye box data of different use areas, the HUD image display is calibrated during the vehicle manufacturing process; the application is used for solving the problem that the existing HUD image calibration technology cannot adjust the calibration eye box according to the eye movement range of users in different use areas when calibrating the vehicle-mounted HUD during the vehicle manufacturing process, so that the calibrated HUD is adapted to users in different areas.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of HUD image calibration, in particular to a HUD image display calibration method, device and storage medium. BACKGROUND

[0002] The HUD image calibration technology refers to a technology system that, by means of hardware adjustment, software algorithm or multi-sensor fusion, etc., solves the deviation of the image in the display process due to device characteristics, environmental interference or user visual angle changes, and finally ensures that the image is clear, accurate and accurately matched with the real scene in the user's field of view.

[0003] The existing HUD image calibration technology often needs to use an industrial camera to simulate the driver's field of view when calibrating the vehicle-mounted HUD in the vehicle manufacturing process, and the industrial camera is placed in the set eyebox range for calibration. However, the setting of the eyebox range is usually based on the industry general ergonomics data, which is an abstract generalization of the average user. However, the height data of users of different genders in different regions is often different, and the difference in some regions is greater than the coverage range of the average model. If the calibration is performed according to the unified eyebox, the eye positions of most users in some regions may be out of the standard eyebox range, so that most users in the region cannot clearly see the image when using the HUD, and need to manually adjust, affecting the user experience. If the eyebox range is set too large to cover all possible situations, it will inevitably lead to a complicated calibration process and high calibration cost. For example, in the patent application with the publication number CN112164377A, the eyebox used in the HUD image correction process is based on the industry general ergonomics data, and is not adjusted according to the regional differences. The corrected image may not be suitable for all users in different regions. Therefore, the existing HUD image calibration technology cannot adjust the calibration eyebox according to the eye movement range of the users in the region where the vehicle is used when calibrating the vehicle-mounted HUD in the vehicle manufacturing process, so that the calibrated HUD is adapted to users in different regions. SUMMARY

[0004] The present application aims to at least solve one of the technical problems in the prior art, by obtaining the eye movement range of different users in different use areas when driving the vehicle according to the use area of the vehicle, denoted as initial eye movement range data; performing eye movement range preprocessing on the initial eye movement range data of different use areas respectively to obtain reference eye movement range data of different use areas; performing eyebox range acquisition processing based on the reference eye movement range data to obtain eyebox range position data of different use areas; calibrating the HUD image display in the vehicle manufacturing process based on the corrected eyebox data of different use areas; to solve the problem that the existing HUD image calibration technology cannot adjust the eyebox for calibration according to the eye movement range of the users in the use area of the vehicle when calibrating the vehicle-mounted HUD in the vehicle manufacturing process, so that the calibrated HUD is adapted to users in different areas.

[0005] To achieve the above-mentioned purpose, in a first aspect, the present application provides a HUD image display calibration method, comprising the following steps:

[0006] Obtaining the eye movement range of different users in different use areas when driving the vehicle according to the use area of the vehicle, denoted as initial eye movement range data;

[0007] Performing eye movement range preprocessing on the initial eye movement range data of different use areas respectively to obtain reference eye movement range data of different use areas;

[0008] Performing eyebox range acquisition processing based on the reference eye movement range data to obtain eyebox range position data of different use areas;

[0009] Calibrating the HUD image display in the vehicle manufacturing process based on the corrected eyebox data of different use areas.

[0010] Further, obtaining the eye movement range of different users in different use areas when driving the vehicle according to the use area of the vehicle, denoted as initial eye movement range data comprises the following sub-steps:

[0011] Denote any vehicle as a first vehicle, obtain all use areas of the first vehicle, denoted as the overall use range; divide the overall use range into multiple use areas according to geography and administrative region, and denote any one use area as a first use area;

[0012] A spatial rectangular coordinate system is established in the first vehicle, denoted as a first spatial coordinate system; for all first vehicles in the first use area, the positions of the eyes of the driver in the first spatial coordinate system are acquired at a first time interval when the first vehicle is normally driven, and the acquisition times are recorded simultaneously, and the initial eye movement range data is obtained by classifying and merging according to the corresponding driver; the initial eye movement range data of all use areas is repeatedly acquired, wherein the first time interval is t1.

[0013] Further, the initial eye movement range data of different use areas is respectively preprocessed to obtain reference eye movement range data of different use areas, including the following sub-steps:

[0014] For the initial eye movement range data of the first use area, the acquisition times corresponding to all drivers are arranged in descending order, denoted as a first time sequence; the last k1% part of the first time sequence is denoted as a second time sequence, wherein k1% is a set percentage;

[0015] The second time sequence is evenly divided into k2 groups, sequentially denoted as time groups 1-k2, and the average number of times of each group is calculated, sequentially denoted as CP1-CPk2, wherein k2 is a set number;

[0016] The difference between any two adjacent average numbers of times in CP1-CPk2 is calculated, denoted as an average difference RCi, wherein RCi=CPi-CPi-1; the maximum average difference RCn is obtained, and the time group n corresponding to the average number of times CPn is denoted as a first time group; the minimum value of the first time group is obtained, denoted as a time threshold CS0;

[0017] Drivers with acquisition times less than CS0 are denoted as insufficient drivers, and drivers with acquisition times greater than or equal to CS0 are denoted as reference drivers; the data of insufficient drivers in the initial eye movement range data is removed, and the basic eye movement range data of the first use area is obtained.

[0018] Further, the initial eye movement range data of different use areas is respectively preprocessed to obtain reference eye movement range data of different use areas, including the following sub-steps:

[0019] For the basic eye movement range data of the first use area, any one reference driver in the basic eye movement range data is denoted as a first driver; for the position of the eyes of the first driver in the first spatial coordinate system acquired each time, the midpoint of the line connecting the left eye coordinates and the right eye coordinates is denoted as an eye point, and the coordinates are obtained,

[0020] respectively, and the average value of the distance from each eye point to the average point is calculated and the average value LP and the standard deviation LB are obtained;

[0021] For each eye point, if the distance from the average point is within the range [LP-k3*LB, LP+k3*LB], it is marked as a normal eye point, otherwise it is marked as an abnormal eye point, where k3 is a proportionality coefficient.

[0022] Further, the initial eye movement range data of different use areas are respectively preprocessed to obtain reference eye movement range data of different use areas, which further includes the following sub-steps:

[0023] The minimum value of the distance from the eye point to the average point is recorded as the expansion distance, and any one normal eye point is recorded as the first eye point.

[0024] For the first eye point, the average value of the distance from the nearest k4 normal eye point to the first eye point is calculated and recorded as the nearest average distance of the first eye point, where k4 is the number of settings.

[0025] The normal eye points corresponding to the nearest average distances of the nearest average sequence in the first k5% are recorded as candidate eye points, and any one candidate eye point is recorded as a second eye point, where k5% is a percentage of settings.

[0026] For the second eye point, the second eye point is taken as the center and the corresponding nearest average distance is taken as the initial radius, the radius is increased by the expansion distance each time, the number of normal eye points contained in each spherical region is counted, and the eye point density is calculated according to the corresponding spherical volume; the expansion is repeated to obtain the maximum eye point density and the corresponding radius, which are recorded as the first number density of the second eye point and the first density radius, respectively.

[0027] The first number density and the first density radius of all candidate eye points are repeatedly obtained, the candidate eye point with the maximum first number density is recorded as the eye movement reference point, the corresponding first density radius is recorded as the eye movement reference radius, and the corresponding spherical region is recorded as the eye movement reference region.

[0028] The eye movement reference points and the eye movement reference radii of all reference drivers in the basic eye movement range data are repeatedly obtained, and the reference eye movement range data of the first use area are obtained after completion, and the reference eye movement range data of all use areas are repeatedly obtained.

[0029] Further, the eyebox range acquisition processing based on the reference eye movement range data to obtain the eyebox range position data of different use areas includes the following sub-steps:

[0030] For the reference eye movement range data of the first use area, the vertical coordinates of the eye movement reference points of all reference drivers are obtained and arranged in ascending order as an eye point height sequence, and the density clustering algorithm is used to divide the eye point height sequence into two sub-sequences, which are respectively recorded as an equivalent female sequence and an equivalent male sequence in ascending order;

[0031] The reference drivers corresponding to the vertical coordinates in the equivalent female sequence and the equivalent male sequence are respectively marked as the corresponding equivalent female driver and the equivalent male driver, and the reference eye movement range data is respectively equivalent to female eye movement data and male eye movement data according to the corresponding reference driver; the equivalent female eye movement data and the equivalent male eye movement data are recorded as the first eye movement range data.

[0032] Further, the eyebox range acquisition processing based on the reference eye movement range data to obtain the eyebox range position data of different use areas includes the following sub-steps:

[0033] The number of collections corresponding to each reference driver in the first eye movement range data is obtained and summed to obtain the total number of collections, and the proportion of the number of collections corresponding to each reference driver in the total number of collections is calculated and recorded as the collection weight of the corresponding reference driver;

[0034] All collection weights are arranged in descending order, and the reference drivers corresponding to the top k6% of the collection weights are recorded as high-frequency drivers, where k6% is a set percentage;

[0035] The minimum circumscribed rectangle of the eye movement reference points of all high-frequency drivers is obtained and recorded as a high-frequency eye movement range, and k4 points are uniformly selected in the high-frequency eye movement range and recorded as candidate representative points, where k7 is a set number;

[0036] Any one candidate representative point is recorded as a first representative point, if the first representative point is located in the eye movement reference area of a certain high-frequency driver, the collection weight of the corresponding high-frequency driver is accumulated, and the total accumulation weight of the first representative point is obtained by repeating the accumulation, which is recorded as the total consensus;

[0037] The total consensus of all candidate representative points is repeatedly obtained, and the candidate representative point with the maximum total consensus is recorded as a general representative point; the minimum circumscribed sphere with the general representative point as the center and containing the sum of the collection weights of the reference drivers greater than k8% is obtained and recorded as a general representative sphere, and the minimum circumscribed rectangle of the general representative sphere is obtained and recorded as an eyebox reference range, and the eyebox range position information is obtained after completion, where k8% is a set percentage;

[0038] The eyebox range position information of the equivalent female eye movement data and the equivalent male eye movement data of the first use area is repeatedly acquired to obtain the eyebox range position data of the first use area, and the eyebox range position data of all use areas is repeatedly acquired.

[0039] Further, the calibration of the HUD image display in the vehicle manufacturing process based on the corrected eyebox data of different use areas includes the following sub-steps:

[0040] For the eyebox range position data of the first use area, the union of the two eyebox reference ranges corresponding to the equivalent female driver and the equivalent male driver is acquired according to the eyebox reference ranges, and is recorded as the calibration eyebox range of the first use area, and the calibration eyebox range of all use areas is repeatedly acquired.

[0041] After the vehicle assembly is completed, the corresponding calibration eyebox range is acquired according to the use area of the vehicle, the detection camera is placed in the calibration eyebox range, the reflection image of the HUD projected onto the glass is real-time shot, and the display position, display size, display angle, distortion, ghosting and field of view angle of the HUD image are calibrated.

[0042] In a second aspect, the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores computer readable instructions, and when the computer readable instructions are executed by the processor, the steps in the above method are executed.

[0043] In a third aspect, the present application provides a storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps in the above method are executed.

[0044] The present application has the following beneficial effects: the present application acquires the eye movement range of different users when driving the vehicle according to the use area of the vehicle, which is recorded as initial eye movement range data; the initial eye movement range data of different use areas is respectively preprocessed to obtain reference eye movement range data of different use areas; the eyebox range position data of different use areas is obtained based on the reference eye movement range data; the HUD image display is calibrated in the vehicle manufacturing process based on the corrected eyebox data of different use areas; when the vehicle-mounted HUD is calibrated in the vehicle manufacturing process, the calibration eyebox can be adjusted according to the eye movement range of the user in the vehicle use area, so that the calibrated HUD is adapted to users in different regions.

[0045] The application obtains the average value by grouping, excludes the drivers with less data amount through the mutation of the average value, only keeps the representative drivers, ensures the reliability of subsequent analysis, and avoids the deviation of the absolute threshold set by people; the eye movement reference point and its radius are automatically identified by using the local density around each point and the spherical expansion, and the eye movement reference area is generated, the advantage is that the optimal concentration of local point density is considered, and the inclusiveness of the final area to most normal eye points is ensured, the accuracy and robustness of subsequent eye box positioning are improved; the collection weight is set based on the proportion of the collection times, and the eye box reference point is selected based on the total consensus, the advantage is that the actual user's line of sight features can be ensured to be reflected to the greatest extent, the user with frequent driving has higher weight, and the eye box reference range obtained is closer to the actual use scene. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 A step flowchart of the method of the application;

[0047] Figure 2 An eye movement reference area acquisition flowchart of the application;

[0048] Figure 3 An eye box reference range acquisition flowchart of the application;

[0049] Figure 4 A structural schematic diagram of the electronic device of the application. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the application.

[0051] Embodiment 1, please refer to Figure 1 The application provides a HUD image display calibration method, including the following steps:

[0052] Step S1: according to the use area of the vehicle, the eye movement range of different users in different use areas when driving the vehicle is obtained, which is recorded as initial eye movement range data; step S1 includes the following sub-steps:

[0053] Step S101, record any vehicle as a first vehicle, obtain all use areas of the first vehicle, record as a total use range; divide the total use range into multiple use areas according to geography and administrative regions, and record any one use area as a first use area; the area division can capture the differences in body shape and driving posture of users in different regions, making the subsequent calibration more targeted and avoiding "one size fits all" which may cause inaccurate image viewing or user discomfort when users in certain regions use it;

[0054] Step S102, establish a space rectangular coordinate system in the first vehicle, record as a first space coordinate system; for all first vehicles in the first use area, obtain the position of the driver's eyes in the first space coordinate system when the first vehicle is driving normally and at a first time interval, record the collection times, and classify and merge according to the corresponding driver, record as initial eye movement range data; because there are cases where multiple people drive the same vehicle, all collected data should be classified according to the driver, which can be assisted by face recognition or iris recognition to assign a unique number to each driver, and the method data is classified;

[0055] Step S103, repeat the collection of initial eye movement range data in all use areas, wherein the first time interval is t1; in this embodiment, the first time interval is 0.5 seconds;

[0056] In the specific implementation process, height is the core indicator of human proportion, and the average height and height distribution of people in different regions are significantly different; the core function of the eyebox is to ensure that the user's eyes can still be in the clear field of view range when moving, and its parameters need to match the eye position distribution of the target population; the height difference in different regions will indirectly change the range and position of the eyebox by affecting the spatial position of the eyes, thereby affecting the direction and amplitude of the HUD image correction.

[0057] Step S2, respectively preprocess the initial eye movement range data of different use areas to obtain reference eye movement range data of different use areas; step S2 includes the following substeps:

[0058] Step S201, for the initial eye movement range data of the first use area, arrange the collection times of all drivers in descending order, record as a first number sequence; record the last k1% part of the first number sequence as a second number sequence, wherein k1% is a set percentage; in this embodiment, k1%=40%, and k1% can be set according to the actual application scenario; because the users with more collection times have sufficient data, there is no need to filter, so in order to simplify the calculation, the users with more collection times can be removed first;

[0059] Step S202, divide the second frequency sequence into k2 groups in sequence, and record them as group 1-k2, and calculate the average value of each group, and record them as CP1-CPk2, wherein k2 is the number set; in this embodiment, k2=20, and k2 can be set according to an actual application scene;

[0060] Step S203, calculate the difference value of any two adjacent average values in CP1-CPk2, and record it as average difference value RCi, wherein RCi=CPi-CPi-1; obtain the maximum average difference value RCn, and record the corresponding frequency group n of the corresponding frequency average value CPn as the first frequency group; obtain the minimum value of the first frequency group, and record it as the frequency threshold CS0; through grouping aggregation, the driver is respectively collected, and the most significant dividing point in the collection amount distribution is automatically located by using the maximum difference value principle, and the frequency threshold is dynamically determined.

[0061] Step S204, record the driver with the collection frequency less than CS0 as the insufficient driver, and record the driver with the collection frequency greater than or equal to CS0 as the reference driver; eliminate the data of the insufficient driver in the initial eye movement range data, and complete the basic eye movement range data of the first use area; a small number of samples with insufficient collection frequency are eliminated to avoid their excessive interference on subsequent statistics, and meanwhile, sufficient data representing the driver group in the area are reserved;

[0062] Step S205, for the basic eye movement range data of the first use area, record any one reference driver in the basic eye movement range data as the first driver; for the position of the eyes collected by the first driver each time in the first spatial coordinate system, obtain the midpoint of the connection line of the left eye coordinates and the right eye coordinates, record it as the eye point, and obtain the coordinates, and combine the positions of the two eyes into a single midpoint to facilitate subsequent calculation.

[0063] Step S206, respectively obtain the horizontal coordinate average value, the vertical coordinate average value and the vertical coordinate average value of all eye points of the first driver, and record them as PX, PY and PZ in sequence; record the point with coordinates (PX, PY, PZ) as the average point, calculate the distance from each eye point to the average point, and obtain the average value LP and the standard deviation LB;

[0064] Step S207, for each eye point, if the distance from the eye point to the average point is located in [LP-k3*LB, LP+k3*LB], the eye point is a normal eye point, otherwise, the eye point is an abnormal eye point, wherein k3 is a proportion coefficient; the accidental abnormal points or measurement noise are eliminated to ensure that the subsequent calculation is based on the normal eye point data; in this embodiment, k3=3.

[0065] Step S208, please refer to Figure 2The minimum value of the distance from the eye point to the mean point is denoted as the expansion distance; and any one normal eye point is denoted as a first eye point; and the expansion distance is used as a radius growth step for subsequent spherical regions;

[0066] In step S209, the average distance from the nearest k4 normal eye points to the first eye point is calculated, and is denoted as the nearest average distance of the first eye point; the nearest average distances of all normal eye points are repeatedly obtained; and the nearest average distances are arranged in descending order, and are denoted as a nearest average sequence, where k4 is a set number; in this embodiment, k4 = 5, and k4 can be set according to an actual application scenario, but should not be too large in order to balance the calculation amount; the smaller the nearest average distance, the more concentrated the first eye point is.

[0067] In step S210, the normal eye points corresponding to the nearest average distances of the first k5% of the nearest average sequence are denoted as candidate eye points, and any one candidate eye point is denoted as a second eye point, where k5% is a set percentage; in this embodiment, k5% = 30%, and the ratio can be flexibly adjusted.

[0068] In step S211, for the second eye point, a spherical region with the second eye point as the center and the corresponding nearest average distance as the initial radius is obtained; the radius is increased by the expansion distance each time; the number of normal eye points contained in each spherical region is counted; and the eye point number density is calculated according to the corresponding spherical volume; the expansion is repeated to obtain the maximum eye point number density and the corresponding radius, which are denoted as the first number density of the second eye point and the first density radius, respectively; the eye point number density = the number of contained normal eye points / the corresponding spherical volume; the core position and the coverage range that best represent the eye position distribution of the driver are automatically identified, thereby ensuring the accuracy of the eye movement reference region.

[0069] In step S212, the first number density and the first density radius of all candidate eye points are repeatedly obtained; the candidate eye point with the maximum first number density is denoted as an eye movement reference point; the corresponding first density radius is denoted as an eye movement reference radius; and the corresponding spherical region is denoted as an eye movement reference region; if there are multiple maximum first number densities, the candidate eye point with the maximum first density radius is selected as the eye movement reference point;

[0070] In step S213, the eye movement reference points and the eye movement reference radii of all reference drivers in the basic eye movement range data are repeatedly obtained; the reference eye movement range data of the first use region is obtained after completion; and the reference eye movement range data of all use regions is repeatedly obtained.

[0071] In the specific implementation process, because the number of collections by most users will form a relatively concentrated normal range, while users with too few collections will form a clear gap from this range, the average value is calculated by simple grouping to find the jump point of the gap as a threshold, avoiding the deviation of manually setting absolute thresholds. By utilizing the local density and spherical expansion around each point, eye-tracking reference points and their radii are identified, and an eye-tracking reference region is generated. This takes into account the optimal concentration of local point density and ensures that the final region is inclusive of most normal eye points, avoiding the subjectivity of setting the radius based on experience, and making the eye-tracking reference region more closely match the density characteristics of the data itself. This improves the accuracy and robustness of subsequent eye box positioning.

[0072] Step S3 involves obtaining eye box range data based on reference eye movement range data to obtain eye box range location data for different usage areas. Step S3 includes the following sub-steps:

[0073] Step S301: For the reference eye movement range data of the first usage area, obtain the vertical coordinates of all reference drivers' eye movement reference points and arrange them in ascending order, denoted as the eye point height sequence. Use a density clustering algorithm to divide the eye point height sequence into two subsequences, denoted in ascending order as the equivalent female sequence and the equivalent male sequence, respectively. The vertical coordinates of the eye movement reference points are the spatial position parameters of the driver's eyes in the vertical direction, which are directly related to height. At the group level, since there is a significant difference in average height between men and women, men usually have a higher average value. Their eye point height distribution will show a bimodal trend, that is, forming high-density areas around two different center values. The male group is concentrated in the higher interval, and the female group is concentrated in the lower interval.

[0074] Step S302: The reference drivers corresponding to the vertical coordinates in the equivalent female sequence and the equivalent male sequence are marked as the corresponding equivalent female driver and equivalent male driver, respectively. The reference eye movement range data is then converted into equivalent female eye movement data and equivalent male eye movement data according to the corresponding reference driver. The equivalent female eye movement data and equivalent male eye movement data are recorded as the first eye movement range data. Using the physiological difference of gender, the overall data is automatically stratified to provide a basis for subsequent fitting of the eye box range of different gender groups, ensuring that subsequent calibration is equally accurate for drivers of different genders.

[0075] For step S303, please refer to... Figure 3 As shown, the number of times each reference driver is sampled in the first eye movement range data is obtained and summed to obtain the total number of samplings. The proportion of the sampling times of each reference driver to the total number of samplings is calculated and recorded as the sampling weight of the corresponding reference driver. Drivers with more sampling times, that is, users who drive vehicles more frequently, have higher weights, which can make subsequent positioning more consistent with actual usage scenarios.

[0076] Step S304, arrange all the collection weights in descending order, and record the reference drivers corresponding to the top k6% collection weights as high-frequency drivers, where k6% is a set percentage; in this embodiment, k6% = 60%, which can be flexibly adjusted;

[0077] Step S305, obtain the minimum circumscribed rectangle of the eye movement reference points of all high-frequency drivers, and record it as a high-frequency eye movement range; evenly select k7 points in the high-frequency eye movement range, and record them as candidate representative points, where k7 is a set number; in this embodiment, k7 = 2000, which can be set according to the actual application scenario; the larger k7 is, the more accurate the general representative points are, but the larger the calculation amount is.

[0078] Step S306, record any one candidate representative point as a first representative point; if the first representative point is located in the eye movement reference area of a high-frequency driver, accumulate the collection weight of the corresponding high-frequency driver; repeat the accumulation to obtain the total accumulated weight of the first representative point, and record it as a total consensus; the total consensus represents how many user eye movement reference areas cover a candidate representative point; the higher the value is, the more the point can represent the dense area of the majority of people;

[0079] Step S307, repeat the total consensus of all candidate representative points, and record the candidate representative point with the maximum total consensus as a general representative point; obtain the minimum circumscribed spherical surface with the general representative point as the center and the sum of the collection weights of the reference drivers contained being greater than k8%; record it as a general representative spherical surface; obtain the minimum circumscribed rectangle of the general representative spherical surface, and record it as an eyebox reference range; complete the eyebox range position information of the first use area; where k8% is a set percentage; in this embodiment, k8% = 90%, that is, the collection weight of the majority of drivers, which can be adjusted appropriately;

[0080] Step S308, repeat the eyebox range position information of the equivalent female eye movement data and the equivalent male eye movement data of the first use area to obtain the eyebox range position data of the first use area; repeat the eyebox range position data of all use areas;

[0081] In the specific implementation process, the divided "equivalent female sequence" and "equivalent male sequence" are not strictly classified according to the gender label, but are functional equivalent groups formed according to the actual distribution characteristics of the eye point height; for example, the vertical coordinates of the eye movement reference points of some tall female drivers may fall into the equivalent male sequence, and the vertical coordinates of the eye movement reference points of some short male drivers may fall into the equivalent female sequence.

[0082] Step S4, based on the corrected eyebox data of different use areas, calibrate the HUD image display in the vehicle manufacturing process; step S4 includes the following sub-steps:

[0083] Step S401, for the eyebox range position data of the first use area, the union of the two eyebox reference ranges corresponding to the equivalent female driver and the equivalent male driver is obtained, denoted as the calibration eyebox range of the first use area, and the calibration eyebox range of all use areas is repeatedly obtained; the calibration eyebox range covers all typical eye ranges of male and female drivers in the current use area, ensuring that the eyes of the driver can fall within the calibration area regardless of the height or posture of the driver;

[0084] Step S402, after the vehicle is assembled, the calibration eyebox range corresponding to the use area of the vehicle is obtained, the detection camera is placed in the calibration eyebox range, the reflection image of the HUD projected on the glass is real-time shot, and the display position, display size, display angle, distortion, ghosting and field of view angle of the HUD image are calibrated;

[0085] In the specific implementation process, the calibration eyebox range parameters of the region can be automatically called from the database or the assembly guide sheet according to the region where the vehicle will be sold; it is ensured that when the users in each region start to use the vehicle, the HUD image presents the best display effect.

[0086] Embodiment 2, please refer to Figure 4 as shown, Figure 4 An example of a structural schematic diagram of an electronic device, which can include: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface, the memory complete the communication among each other through the communication bus. The memory stores computer readable instructions, and the processor can call the instructions in the memory, when the computer readable instructions are executed by the processor, the steps in a kind of HUD image display calibration method are run, to realize the following functions: according to the use area of vehicle, the eye movement range of different users when driving vehicle is obtained, denoted as initial eye movement range data; the initial eye movement range data of different use areas is respectively preprocessed, to obtain reference eye movement range data of different use areas; based on reference eye movement range data, eyebox range acquisition processing is carried out, to obtain eyebox range position data of different use areas; based on the correction eyebox data of different use areas, the HUD image display is calibrated in the vehicle manufacturing process.

[0087] In addition, the logic instructions in the memory described above can be implemented in the form of a software function unit and used as an independent product or used, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0088] In embodiment 3, the present application also provides a computer readable storage medium, and the present application provides a storage medium having a computer program stored thereon, and the computer program is executed by a processor to run the steps in a HUD image display calibration method to realize the following functions: obtaining the eye movement range of different users when driving a vehicle in different use areas as initial eye movement range data according to the use area of the vehicle; performing eye movement range preprocessing on the initial eye movement range data of different use areas respectively to obtain reference eye movement range data of different use areas; performing eye box range acquisition processing based on the reference eye movement range data to obtain eye box range position data of different use areas; and calibrating the HUD image display in the vehicle manufacturing process based on the corrected eye box data of different use areas.

[0089] Through the description of the above embodiments, the embodiments of the present application can be provided as a method, a system or a computer program product. Based on such understanding, the above technical solutions essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the method described in each embodiment or some parts of the embodiment.

[0090] In the embodiments of the present application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are only illustrative, for example, the division of modules or units is only a logical function division, and other division manners can be used in actual implementation, for example, a plurality of modules or units can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some communication interface, the indirect coupling or communication connection between the system, the module and the unit can be electrical, mechanical or other forms.

[0091] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A HUD image display calibration method, characterized by, The method comprises the following steps: According to the use area of the vehicle, the eye movement range of different users in different use areas when driving the vehicle is obtained, recorded as initial eye movement range data; The initial eye movement range data of different use areas is respectively preprocessed to obtain reference eye movement range data of different use areas; Based on the reference eye movement range data, eyebox range acquisition processing is performed to obtain eyebox range position data of different use areas; Based on the corrected eyebox data of different use areas, the HUD image display is calibrated during vehicle manufacturing; According to the use area of the vehicle, the eye movement range of different users in different use areas when driving the vehicle is obtained, recorded as initial eye movement range data, which comprises the following sub-steps: Any vehicle is recorded as a first vehicle, and all use areas of the first vehicle are obtained, recorded as a total use range; the total use range is divided into multiple use areas according to geography and administrative region, and any one use area is recorded as a first use area; A spatial rectangular coordinate system is established in the first vehicle, recorded as a first spatial coordinate system; For all first vehicles in the first use area, the position of the driver's eyes in the first spatial coordinate system is obtained when the first vehicle is normally driven, and the collection times are recorded simultaneously, and the corresponding drivers are classified and combined, recorded as initial eye movement range data, and the initial eye movement range data of all use areas is repeatedly collected, wherein the first time interval is t1.

2. The HUD image display calibration method of claim 1, wherein, The initial eye movement range data of different use areas is respectively preprocessed to obtain reference eye movement range data of different use areas, which comprises the following sub-steps: For the initial eye movement range data of the first use area, the collection times of all drivers are arranged in descending order, recorded as a first time sequence; the last k1% part of the first time sequence is recorded as a second time sequence, wherein k1% is a set percentage; The second number sequence is evenly divided into k2 groups, sequentially recorded as the second group 1-k2, and the average value of each group is calculated, sequentially recorded as CP1-CP k2 wherein k2 is the number of settings; CP1 - CP k2 The difference between any two adjacent frequency averages is denoted as average difference RC i , wherein RC i = CP i - CP i-1 ; the maximum average difference RC n is obtained, and the corresponding frequency average CP n is denoted as the first frequency array, and the minimum value of the first frequency array is denoted as the frequency threshold CS0; Drivers with collection times less than CS0 are recorded as insufficient drivers, and drivers with collection times greater than or equal to CS0 are recorded as reference drivers; the data of insufficient drivers in the initial eye movement range data is excluded, and the basic eye movement range data of the first use area is obtained after completion.

3. The HUD image display calibration method of claim 2, wherein, The initial eye movement range data of different use areas is respectively preprocessed to obtain reference eye movement range data of different use areas, which further comprises the following sub-steps: For the basic eye movement range data of the first use area, any one reference driver in the basic eye movement range data is recorded as a first driver; for the position of the eyes collected each time by the first driver in the first spatial coordinate system, the midpoint of the line connecting the left eye coordinates and the right eye coordinates is obtained, recorded as an eye point, and the coordinates are obtained, The horizontal coordinate average, vertical coordinate average and vertical coordinate average of all eye points of the first driver are respectively obtained, recorded as PX, PY and PZ in order; the point with coordinates (PX, PY, PZ) is recorded as the average point, the distance from each eye point to the average point is calculated, and the average value LP and the standard deviation LB are obtained. For each eye point, if the distance from the eye point to the mean point is in the range of [LP-k3*LB, LP+k3*LB], the eye point is marked as a normal eye point, otherwise, the eye point is marked as an abnormal eye point, where k3 is a proportion coefficient.

4. The HUD image display calibration method according to claim 3, wherein The initial eye movement range data of different use areas are respectively preprocessed to obtain reference eye movement range data of different use areas, which further includes the following sub-steps: The minimum value of the distance from the eye point to the mean point is recorded as an expansion distance; and any one normal eye point is recorded as a first eye point; For the first eye point, the average value of the distance from the nearest k4 normal eye points to the first eye point is calculated and recorded as the nearest average distance of the first eye point, where k4 is the number of settings; The nearest average distances of all normal eye points are repeatedly obtained; The nearest average distances are arranged in ascending order and recorded as a nearest average sequence, where k5% is a percentage of settings; Any one candidate eye point is recorded as a second eye point, where k5% is a percentage of settings; For the second eye point, the second eye point is taken as the center and the corresponding nearest average distance is taken as the initial radius, the radius is increased by the expansion distance each time, the number of normal eye points contained in the spherical region corresponding to each radius is counted, and the eye point density is calculated according to the corresponding spherical volume; the expansion is repeated to obtain the maximum eye point density and the corresponding radius, which are recorded as the first number density of the second eye point and the first density radius, respectively; The first number density of all candidate eye points and the first density radius are repeatedly obtained, the candidate eye point with the maximum first number density is recorded as an eye movement reference point, the corresponding first density radius is recorded as an eye movement reference radius, and the corresponding spherical region is recorded as an eye movement reference region; 5. The HUD image display calibration method according to claim 4, wherein The eye movement reference points and the eye movement reference radii of all reference drivers in the basic eye movement range data are repeatedly obtained, and the reference eye movement range data of the first use area are obtained after completion. The reference eye movement range data of all use areas are repeatedly obtained. Based on the reference eye movement range data, the eye box range acquisition processing is performed to obtain eye box range position data of different use areas, which includes the following sub-steps: For the reference eye movement range data of the first use area, the vertical coordinates of the eye movement reference points of all reference drivers are obtained and arranged in ascending order to form an eye point height sequence. The density clustering algorithm is used to divide the eye point height sequence into two sub-sequences, which are arranged in ascending order and recorded as an equivalent female sequence and an equivalent male sequence, respectively.

6. The HUD image display calibration method of claim 5, wherein, The reference drivers corresponding to the vertical coordinates in the equivalent female sequence and the equivalent male sequence are marked as equivalent female drivers and equivalent male drivers, respectively. The reference eye movement range data is divided into equivalent female eye movement data and equivalent male eye movement data according to the corresponding reference drivers. The equivalent female eye movement data and the equivalent male eye movement data are recorded as the first eye movement range data. Based on the reference eye movement range data, the eye box range acquisition processing is performed to obtain eye box range position data of different use areas, which further includes the following sub-steps: Obtaining the number of collection times corresponding to each reference driver in the first eye movement range data, summing up to obtain the total number of collection times, calculating the proportion of the number of collection times corresponding to each reference driver in the total number of collection times, denoted as the collection weight of the corresponding reference driver; Arranging all the collection weights in descending order, and recording the reference drivers corresponding to the top k6% collection weights as high-frequency drivers, where k6% is a set percentage; Obtaining the minimum circumscribed rectangle of the eye movement reference points of all high-frequency drivers, denoted as the high-frequency eye movement range, and uniformly selecting k7 points in the high-frequency eye movement range, denoted as candidate representative points, where k7 is a set number; Recording any one candidate representative point as a first representative point, if the first representative point is located in the eye movement reference region of a certain high-frequency driver, then the collection weight of the corresponding high-frequency driver is accumulated, and the total accumulated weight of the first representative point is obtained by repeating the accumulation, denoted as the total consensus. Repeating the total consensus of all candidate representative points, and recording the candidate representative point with the maximum total consensus as the general representative point; obtaining the minimum circumscribed spherical surface with the general representative point as the center and containing the sum of the collection weights of the reference drivers greater than k8%, denoted as the general representative spherical surface, and obtaining the minimum circumscribed rectangle of the general representative spherical surface, denoted as the eyebox reference range, and obtaining the eyebox range position information, where k8% is a set percentage; Repeating the eyebox range position information of the equivalent female eye movement data and the equivalent male eye movement data of the first use area to obtain the eyebox range position data of the first use area, and repeating the eyebox range position data of all use areas.

7. The method of calibrating a HUD image display of claim 6, wherein, Based on the corrected eyebox data of different use areas, the calibration of the HUD image display in the vehicle manufacturing process includes the following sub-steps: For the eyebox range position data of the first use area, obtaining the union of the two eyebox reference ranges according to the eyebox reference ranges corresponding to the equivalent female driver and the equivalent male driver, denoted as the calibration eyebox range of the first use area, and repeating the calibration eyebox range of all use areas; After the vehicle assembly is completed, according to the use area of the vehicle, the corresponding calibration eyebox range is obtained, the detection camera is placed in the calibration eyebox range, the reflection image of the HUD projected on the glass is photographed in real time, and the display position, display size, display angle, distortion, ghosting and field of view angle of the HUD image are calibrated.

8. An electronic device, comprising: The computer program is executed by the processor to run the steps in the method of any one of claims 1-7.

9. A storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to run the steps in the method of any one of claims 1-7.

Images