Image adjusting method and device, vehicle and storage medium

Abstract

The invention provides an image adjusting method and device, a vehicle and a storage medium. When the target vehicle is in the attitude indicated by the attitude information, the relative position between the target image displayed by the vehicle-mounted screen corresponding to the target user in the target vehicle and the target user may change, so that the target image shakes when the target user watches the target image. Since the shaking degree between the target user and the target image is related to the attitude of the target vehicle and the user attribute of the target user, the position offset for adjusting the target image is determined through the target model based on the attitude information of the target vehicle and the user attribute of the target user. In the vehicle driving process, the position of the target image on the vehicle-mounted screen is adjusted based on the position offset, dynamic adjustment of the target image is achieved, the shaking degree between the target user and the target image when the target user watches a film is reduced, and the stable film watching entertainment effect is achieved.

Description

Technical Field

[0001] The present application relates to the field of vehicles, and more specifically, to a method, a device, a vehicle and a storage medium for adjusting an image in the field of vehicles. Background Art

[0002] With the development of vehicle intelligence, the entertainment function of vehicles has also developed rapidly. Screens of various sizes, such as the central control screen, the co-pilot entertainment screen, and the ceiling screen, are deployed in different locations of the vehicle to provide users with entertainment experiences such as watching movies. However, the vehicle will have different postures during driving. When the vehicle is in different postures, the position of the screen on which the user watches the movie is different relative to the user. During the user's viewing process, the position of the screen relative to the user changes, which will cause the video image on the screen to shake. If the user is in such an environment for a long time, it will cause dizziness and nausea, which will greatly reduce the vehicle's viewing and entertainment experience.

[0003] Therefore, there is an urgent need for a method for dynamically adjusting video images to dynamically adjust the video images so as to reduce the degree of shaking between the user and the video image when the user is watching a movie, so as to achieve a stable viewing and entertainment effect. Summary of the invention

[0004] The present application provides a method, device, vehicle and storage medium for adjusting an image. The method can dynamically adjust a target image on a vehicle screen while the vehicle is driving, so as to reduce the degree of shaking between a target user and the target image when the target user is watching a movie, so as to achieve a stable viewing and entertainment effect.

[0005] In a first aspect, a method for adjusting an image is provided, the method comprising: obtaining posture information of the target vehicle and user attributes of a target user in the target vehicle during driving of the target vehicle; inputting the posture information and the user attributes into a target model to obtain a position offset for adjusting the target image, the target model being trained based on multiple sample posture information, multiple sample user attributes, and corresponding multiple sample position offsets, the target image being an image displayed on a vehicle screen corresponding to the target user; and adjusting the position of the target image on the vehicle screen based on the position offset.

[0006] In the above technical solution, when the target vehicle is in the posture indicated by the posture information, the target image displayed on the vehicle-mounted screen corresponding to the target user in the target vehicle may change its relative position with the target user, resulting in shaking between the target user and the target image, so that the target image shakes when the target user watches the target image. Since the degree of shaking between the target user and the target image is related to the posture of the target vehicle and the user attributes of the target user, the position offset of the target image to be adjusted is determined by the target model based on the posture information of the target vehicle and the user attributes of the target user in this application. During the driving process of the vehicle, the position of the target image on the vehicle-mounted screen is adjusted based on the position offset, and the target image is dynamically adjusted to reduce the degree of shaking between the target user and the target image when the target user is watching a movie, so as to achieve a stable viewing and entertainment effect.

[0007] In combination with the first aspect, in some possible implementations, the position of the target image on the vehicle-mounted screen is adjusted based on the position offset, including: determining a first movement direction and a corresponding first movement amount for adjusting the target image in the horizontal direction based on the position offset, and determining a second movement direction and a corresponding second movement amount for adjusting the target image in the vertical direction; moving the target image on the vehicle-mounted screen in the first movement direction by the first movement amount, and moving it in the second movement direction by the second movement amount.

[0008] In the above technical solution, the target image is displayed on the vehicle screen, and the position offset includes the direction and offset of adjusting the target image in the horizontal direction, and the direction and offset of adjusting the target image in the vertical direction. The present application determines the specific parameters for adjusting the target image from the position offset (the first moving direction and the first moving amount adjusted in the horizontal direction, and the second moving direction and the second moving amount adjusted in the vertical direction), and adjusts the position of the target image on the vehicle screen based on the specific parameters to achieve accurate position adjustment of the target image and reduce the degree of shaking between the target user and the target image when the target user is watching a movie.

[0009] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, before moving the target image on the vehicle-mounted screen by the first movement amount in the first movement direction and by the second movement amount in the second movement direction, the method also includes: based on the first movement amount, reducing the target image in the horizontal direction, and based on the second movement amount, reducing the target image in the vertical direction to obtain a reduced image, and the reduced image is displayed in the central display area of ​​the vehicle-mounted screen; and moving the target image on the vehicle-mounted screen by the first movement amount in the first movement direction and by the second movement amount in the second movement direction, including: moving the reduced image from the central display area to the first movement direction by the first movement amount, and to the second movement direction by the second movement amount.

[0010] In the above technical solution, before adjusting (moving) the target image, the target image is reduced in the horizontal direction and the vertical direction based on the first movement amount and the second movement amount. Afterwards, the target image is adjusted in the horizontal direction and the vertical direction of the vehicle-mounted screen based on the first movement amount and the second movement amount, respectively. This method of first reducing and then adjusting can ensure that the adjusted target image does not lose the content on the original image, and can also reduce the degree of shaking between the target user and the target image when the target user is watching a movie, thereby improving the target user's viewing and entertainment experience.

[0011] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, before moving the target image on the vehicle-mounted screen by the first movement amount in the first movement direction and by the second movement amount in the second movement direction, the method also includes: based on the first movement amount and the second movement amount, determining a redundant display area in the edge area of ​​the display area of ​​the vehicle-mounted screen, the redundant display area is used to indicate the area to which the target image can be moved, the display area includes the redundant display area and the central display area, and the redundant display area and the central display area do not overlap, and the target image is displayed in the central display area; and, moving the target image on the vehicle-mounted screen by the first movement amount in the first movement direction and by the second movement amount in the second movement direction, including: moving the target image from the central display area to the first movement direction by the first movement amount and to the second movement direction by the second movement amount, so that part of the target image is displayed in the redundant display area.

[0012] In the above technical solution, before adjusting (moving) the target image, a redundant display area is determined in the edge area of ​​the display area of ​​the vehicle-mounted screen based on the first movement amount and the second movement amount, so that the target image is displayed in the central area (central display area) of the display area, so that the redundant display area is used to adjust the position of the target image. Afterwards, based on the first movement amount and the second movement amount, the target image is adjusted in the horizontal direction and the vertical direction of the vehicle-mounted screen respectively. This setting of a redundant display area on the display area so that the target image is displayed in the central display area of ​​the display area is equivalent to a method of first reducing the target image and then adjusting the target image. This method can ensure that the adjusted target image does not lose the content on the original image, and can also reduce the degree of shaking between the target user and the target image when the target user is watching a movie, thereby improving the target user's viewing and entertainment experience.

[0013] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the method for determining the target model includes: determining multiple sample posture information, multiple sample user attributes, and corresponding multiple sample position offsets for adjusting the position of the target image; based on the multiple sample posture information, the multiple sample user attributes, and the corresponding multiple sample position offsets, adjusting the weight parameters in the target model to be trained to obtain an adjusted model; when the loss value between the position offset obtained by the adjusted model and the corresponding sample offset is less than a preset value, determining the adjusted model as the target model.

[0014] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the position of the target image on the vehicle-mounted screen is adjusted based on the position offset, including: obtaining the posture information of the target user's head; correcting the position offset based on the posture information to obtain the target position offset; and adjusting the position of the target image on the vehicle-mounted screen based on the target position offset.

[0015] In the above technical solution, the position offset of the target image determined by the target model based on the posture information and user attributes is an indirect way of estimating the position offset, and does not involve the posture information of the target user's head at the posture indicated by the posture information. Therefore, the present application also corrects the position offset based on the posture information of the target user's head to obtain a more accurate position offset (target position offset); based on the target position offset, adjust the position of the target image on the vehicle screen. Compared with the process of adjusting the position of the target image on the vehicle screen based on the position offset, this solution can better reduce the degree of shaking between the target user and the target image when the target user is watching a movie.

[0016] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the posture information includes at least one of the tilt angle and the pitch angle, the user attribute includes at least one of the upper body length, gender, age and weight, and the posture information of the target vehicle and the user attributes of the target user in the target vehicle are obtained, including: obtaining the tilt angle and the pitch angle through the angle sensor in the target vehicle; determining the upper body length of the target user through the visual sensor in the target vehicle; obtaining the face image of the target user through the visual sensor, and determining the gender and the age based on the image features of the face image; obtaining the upper body image of the target user through the visual sensor, and determining the widths of multiple limb parts in the upper body image; determining the fatness level of the target user based on the widths of the multiple limb parts; and determining the weight based on the fatness level and the gender.

[0017] In the above technical solution, the specific contents of the posture information and user attributes, as well as the method of obtaining the posture information and user attributes are described. Among them, since the upper body length of the target user will affect the adjustment of the target image in the vertical direction, the gender, age and weight of the target user will affect the degree of shaking between the target user and the target image, and further affect the adjustment of the target image in the horizontal direction, the user attribute includes at least one of the upper body length, gender, age and weight.

[0018] In a second aspect, a device for adjusting an image is provided, the device comprising: an acquisition module, used to acquire posture information of a target vehicle and user attributes of a target user in the target vehicle during driving of the target vehicle; a processing module, used to input the posture information and the user attributes into a target model to obtain a position offset for adjusting the target image, the target model is trained based on multiple sample posture information, multiple sample user attributes and corresponding multiple sample position offsets, and the target image is an image displayed on a vehicle screen corresponding to the target user; an adjustment module, used to adjust the position of the target image on the vehicle screen based on the position offset.

[0019] In combination with the second aspect, in some possible implementations, the adjustment module is specifically used to: determine, based on the position offset, a first moving direction and a corresponding first moving amount for adjusting the target image in the horizontal direction, and determine a second moving direction and a corresponding second moving amount for adjusting the target image in the vertical direction; move the target image on the vehicle-mounted screen in the first moving direction by the first moving amount, and move the target image in the second moving direction by the second moving amount.

[0020] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, before the target image is moved on the vehicle-mounted screen by the first movement amount in the first movement direction and by the second movement amount in the second movement direction, the device also includes: a reduction module, used to reduce the target image in the horizontal direction based on the first movement amount, and to reduce the target image in the vertical direction based on the second movement amount to obtain a reduced image, and the reduced image is displayed in the central display area of ​​the vehicle-mounted screen; and the adjustment module is specifically used to move the reduced image from the central display area to the first movement direction by the first movement amount, and to the second movement direction by the second movement amount.

[0021] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, before the target image is moved on the vehicle-mounted screen by the first movement amount in the first movement direction and by the second movement amount in the second movement direction, the device also includes: a determination module, which is used to determine a redundant display area in the edge area of ​​the display area of ​​the vehicle-mounted screen based on the first movement amount and the second movement amount, and the redundant display area is used to indicate the area to which the target image can be moved, and the display area includes the redundant display area and the central display area, and the redundant display area and the central display area do not overlap, and the target image is displayed in the central display area; and the adjustment module is specifically used to move the target image from the central display area to the first movement direction by the first movement amount and to the second movement direction by the second movement amount, so that part of the target image is displayed in the redundant display area.

[0022] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the determination module is specifically used to: determine multiple sample posture information, multiple sample user attributes and corresponding multiple sample position offsets for adjusting the position of the target image; based on the multiple sample posture information, the multiple sample user attributes and the corresponding multiple sample position offsets, adjust the weight parameters in the target model to be trained to obtain an adjusted model; when the loss value between the position offset obtained by the adjusted model and the corresponding sample offset is less than a preset value, determine the adjusted model as the target model.

[0023] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the acquisition module is also used to obtain the posture information of the target user's head; the device also includes: a correction module, used to correct the position offset based on the posture information to obtain a target position offset; the adjustment module is specifically used to adjust the position of the target image on the vehicle-mounted screen based on the target position offset.

[0024] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the posture information includes at least one of the tilt angle and the pitch angle, the user attribute includes at least one of the upper body length, gender, age and weight, and the acquisition module is specifically used to: acquire the tilt angle and the pitch angle through the angle sensor in the target vehicle; determine the upper body length of the target user through the visual sensor in the target vehicle; acquire the face image of the target user through the visual sensor, and determine the gender and the age based on the image features of the face image; acquire the upper body image of the target user through the visual sensor, and determine the widths of multiple limb parts in the upper body image; determine the fatness level of the target user based on the widths of the multiple limb parts; determine the weight based on the fatness level and the gender.

[0025] In a third aspect, a vehicle is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the vehicle executes the method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0026] In a fourth aspect, a computer-readable storage medium is provided, which stores instructions. When the instructions are executed on a computer or a processor, the computer or the processor executes the method in the first aspect or any possible implementation of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a schematic diagram of a scene in which a vehicle is traveling on a turning section provided in an embodiment of the present application;

[0028] Figure 2 is a schematic flow chart of a method for adjusting an image provided in an embodiment of the present application;

[0029] Figure 3 is a schematic diagram of an interface for adjusting an image provided in an embodiment of the present application;

[0030] Figure 4 is a schematic diagram of another interface for adjusting an image provided in an embodiment of the present application;

[0031] Figure 5 is a schematic diagram of another interface for adjusting an image provided in an embodiment of the present application;

[0032] Figure 6 is a structural schematic diagram of a device for adjusting an image provided in an embodiment of the present application;

[0033] Figure 7 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] The technical solutions in the present application will be described clearly and in detail below in conjunction with the accompanying drawings. In the description of the embodiments of the present application, "multiple" means two or more than two. The terms "first" and "second" are used for descriptive purposes only and should not be understood as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0035] Figure 1 This is a schematic diagram of a scenario in which a vehicle is traveling on a curved road section provided in an embodiment of the present application.

[0036] During the driving process, the vehicle will be in different postures. When the vehicle is in different postures, the position of the vehicle screen on which the user is watching the movie is different relative to the user. During the user's viewing process, the position of the vehicle screen relative to the user changes, which will cause the video image on the vehicle screen to shake.

[0037] For example, Figure 1 In (a), the target vehicle is traveling on a curved road. The target user in the target vehicle is watching a movie on the in-vehicle screen, which currently displays the target image. During the left turn of the target vehicle, due to the influence of inertia, the target user still maintains the original motion state (going straight). Therefore, the target user will tilt to the right relative to the target image, as shown in FIG. Figure 1 As shown in (b). The position of the target user moves from the position indicated by the thick solid line to the position indicated by the thin solid line. Furthermore, the vehicle screen is installed in the target vehicle, and the target image on the vehicle screen moves with the target vehicle. Therefore, when the target vehicle turns left, the position of the target image on the vehicle screen changes relative to the target user, which will give the user the feeling that the target image on the vehicle screen is shaking.

[0038] It should be understood that in some embodiments, the vehicle-mounted screen includes any one of the entertainment display screens such as the central control display screen, the co-pilot display screen, and the headrest display screen behind the seat in the target vehicle.

[0039] Figure 2 It is a schematic flowchart of a method for adjusting an image provided in an embodiment of the present application.

[0040] It should be understood that the method for adjusting an image provided in the embodiment of the present application can be applied to Figure 1The target vehicle shown. Specifically, the method for adjusting the image can be applied to a target controller in the target vehicle, which is any one of a vehicle controller and a body domain controller in the target vehicle. The body domain controller is used to control various vehicle components in the target vehicle. In some embodiments, the vehicle components include lights, wipers, windows, rearview mirrors, seats, vehicle air conditioners, doors, Bluetooth devices, steering wheels, brake pedals, and various types of vehicle screens.

[0041] For example, Figure 2 As shown, the method 200 includes:

[0042] Step 201: During the driving of a target vehicle, a vehicle controller obtains posture information of the target vehicle and user attributes of a target user in the target vehicle.

[0043] It should be understood that the "posture information of the target vehicle" in step 201 can reflect the motion posture of the target vehicle during driving. The posture information includes at least one of the tilt angle and the pitch angle. The tilt angle refers to the angle between the target vehicle and the horizontal plane, and the pitch angle refers to the angle between the target vehicle and the vertical plane. The "user attributes" in step 201 are used to reflect the basic characteristics of the target user, and the user attributes include at least one of the upper body length, gender, age and weight.

[0044] In a possible implementation, step 201 includes: the vehicle controller obtains the tilt angle and the pitch angle through the angle sensor in the target vehicle; the vehicle controller determines the upper body length of the target user through the visual sensor in the target vehicle; the vehicle controller obtains the facial image of the target user through the visual sensor, and determines the gender and the age based on the image features of the facial image; the vehicle controller obtains the upper body image of the target user through the visual sensor, and determines the widths of multiple limb parts in the upper body image; the vehicle controller determines the fatness level of the target user based on the widths of the multiple limb parts; the vehicle controller determines the weight based on the fatness level and the gender.

[0045] In some embodiments, the angle sensor includes any one of an acceleration sensor and a gyroscope sensor.

[0046] In some embodiments, the visual sensor is a camera of various types, and the vehicle controller determines the upper body length of the target user through the visual sensor in the target vehicle, including: the vehicle controller obtains the upper body image of the target user through the visual sensor, and determines the relative position between the head of the target user and multiple reference points from the upper body image; the vehicle controller determines the positions of the multiple reference points in the target vehicle, and determines the position of the head in the target vehicle based on the relative positions and the positions of the reference points; the vehicle controller determines the upper body length based on the position of the head in the target vehicle and the position of the seat cushion.

[0047] In some embodiments, the plurality of reference points include position points on a seat headrest, position points on a seat back, and position points on a ceiling in the vehicle, etc. in the target vehicle.

[0048] In some embodiments, the vehicle controller determines the gender and the age based on the image features of the facial image, including: the vehicle controller inputs the facial image into a target detection model, and the target detection model extracts skin condition features and facial feature features from the image features of the facial image, the skin condition features include at least one of skin texture features, skin color features, skin brightness features and wrinkle texture features, and the facial feature features include at least one of facial features, and the facial features include features of the eyes, eyebrows, nose, mouth and ears; the vehicle controller identifies the skin condition features and the facial features respectively through the classifier in the target detection model to determine the gender and the age.

[0049] It should be understood that users of different ages have different skin conditions. The skin condition is used to indicate the state of skin texture, skin color, skin brightness, wrinkle texture, etc. Generally, older users have darker skin color, less shiny skin, rougher skin texture, and more wrinkles. Therefore, the age of the target user can be determined by the skin condition characteristics.

[0050] It should also be understood that users of different genders have different facial features. The facial features include eyes, eyebrows, nose, mouth, and ears. Generally speaking, men have wider nose bridges, more three-dimensional nose wings, and larger noses; women's eyes are mostly round, while men's eyes are mostly oval, etc. Therefore, the gender of the target user can be determined by the facial features.

[0051] In some embodiments, the limb parts include at least two of the waist, chest and arms, and the vehicle controller determines the fatness level of the target user based on the widths of multiple limb parts, including: the vehicle controller determines the sum of the widths of the multiple limb parts to obtain the total width; the vehicle controller determines the fatness level based on the width range corresponding to the total width; and the vehicle controller determines the weight based on the fatness level and the gender, including: the vehicle controller determines the weight as the product of the target weight corresponding to the fatness level and the weighted value of the weight corresponding to the gender.

[0052] In the above technical solution, the vehicle controller determines the fatness level based on the sum of the widths of multiple limbs, which is equivalent to inferring the approximate weight of the target user from the appearance; the vehicle controller determines the weight as the product of the target weight corresponding to the fatness level and the weight weight value corresponding to the gender, which is equivalent to correcting the approximate weight of the target user based on the weight weight value corresponding to the gender to obtain the target weight, that is, the weight of the target user. The above solution can determine the weight more accurately.

[0053] In step 202, the vehicle controller inputs the posture information and the user attributes into a target model to obtain a position offset for adjusting a target image. The target model is trained based on multiple sample posture information, multiple sample user attributes, and corresponding multiple sample position offsets. The target image is the image displayed on the vehicle screen corresponding to the target user.

[0054] It should be understood that the "target model" in the above step 202 is used to determine the position offset for adjusting the target image based on the posture information of the target vehicle and the user attributes of the target user. This is because the posture information of the target vehicle will affect the relative position between the target image displayed on the vehicle screen and the target user; the user attributes will also affect the relative position between the target image and the target user. Specifically, when the user attribute is weight, when the target vehicle turns left, the degree to which the heavy user tilts to the right is different from the degree to which the light user tilts to the right. When the user attribute is gender, when the target vehicle turns left, the degree to which the male user tilts to the right is different from the degree to which the female user tilts to the right. When the user attribute is age, when the target vehicle turns left, users of different ages tilt to the right to different degrees. When the user attribute is upper body length, when the target vehicle accelerates, users of different upper body lengths tilt backward to different degrees. Therefore, it is necessary to determine the position offset for adjusting the target image based on the posture information and user attributes to keep the relative position between the target image and the target user unchanged as much as possible and reduce the degree of shaking between the target image and the target user.

[0055] It should also be understood that the "target image" in step 202 is a two-dimensional image, and the "position offset" includes two parameters. The first parameter of the two parameters is used to indicate the adjustment of the target image in the horizontal direction. The second parameter of the two parameters is used to indicate the adjustment of the target image in the vertical direction.

[0056] In one possible implementation, the method for determining the target model includes: a vehicle controller determines multiple sample posture information, multiple sample user attributes, and corresponding multiple sample position offsets for adjusting the position of the target image; the vehicle controller adjusts the weight parameters in the target model to be trained based on the multiple sample posture information, the multiple sample user attributes, and the corresponding multiple sample position offsets to obtain an adjusted model; when a loss value between the position offset obtained by the adjusted model and the corresponding sample offset is less than a preset value, the adjusted model is determined as the target model.

[0057] It should be understood that the above scheme is equivalent to a process in which, before obtaining the target model, the vehicle controller obtains multiple sample posture information, multiple sample user attributes and corresponding multiple sample position offsets through a testing process, and then adjusts the weight parameters in the target model to be trained through the multiple sample posture information, the multiple sample user attributes and the corresponding multiple sample position offsets to obtain the target model.

[0058] In some embodiments, the target model determined by the vehicle controller can be represented by the following formula (1):

[0059] (X,Y) = f1(am,bn) (1)

[0060] Among them, (X, Y) is the position offset, a is the first weight coefficient, m is the first variable, b is the second weight coefficient, and n is the second variable.

[0061] It should be understood that the process of adjusting the weight parameters in the above solution can be understood as: the process of adjusting the coefficients of m and n.

[0062] It should also be understood that X is the first parameter in the above solution, and Y is the second parameter in the above solution. It should also be understood that the first parameter and the second parameter may have negative values.

[0063] It should also be understood that, when the posture information includes the tilt angle and pitch angle of the target vehicle, and the user attributes include upper body length, gender, age and weight, the target model can be represented as formula (2);

[0064] (X,Y) =f1(a1m1+a2m2,b1n1+b2n2+b3n3+b4n4) (2)

[0065] Wherein, (X,Y) is the position offset, a1 is the third weight coefficient, m1 is the third variable, a2 is the fourth weight coefficient, m2 is the fourth variable, b1 is the fifth weight coefficient, n1 is the fifth variable, b2 is the sixth weight coefficient, n2 is the sixth variable, b3 is the seventh weight coefficient, n3 is the seventh variable, b4 is the eighth weight coefficient, and n4 is the eighth variable. The third weight coefficient is the coefficient corresponding to the tilt angle of the target vehicle, and the third variable is used to indicate any tilt angle; the fourth weight coefficient is the coefficient corresponding to the pitch angle of the target vehicle, and the fourth variable is used to indicate any pitch angle; the fifth weight coefficient is the coefficient corresponding to the length of the upper body, and the fifth variable is used to indicate any upper body length; the sixth weight coefficient is the coefficient corresponding to the gender, and the sixth variable is used to indicate any gender; the seventh weight coefficient is the coefficient corresponding to the age, and the seventh variable is used to indicate any age; the eighth weight coefficient is the coefficient corresponding to the weight, and the eighth variable is used to indicate any weight. It should be understood that a1, m1, a2, m2, b1, n1, b2, n2, b3, n3, b4 and n4 mentioned above can be determined by determining a, m, b and n.

[0066] It should be understood that the process of adjusting the weight parameters in the above solution can be understood as: the process of adjusting the coefficients of m1, m2, n1, n2, n3 and n4.

[0067] In some embodiments, the vehicle controller determines a plurality of sample posture information, a plurality of sample user attributes, and a plurality of corresponding sample position offsets for adjusting the position of the target image, including: the vehicle controller obtains a plurality of sample posture information, sample user attributes of a plurality of users under the postures indicated by each sample posture information, and a corresponding offset of each user's eye from a test experiment, wherein the offset of the eye includes a horizontal offset and a vertical offset; when the horizontal offset is greater than or equal to a first threshold, the vehicle controller determines the first threshold as the sample position offset for adjusting the position of the target image in the horizontal direction; when the horizontal offset is less than the first threshold, the vehicle controller determines the first threshold as the sample position offset for adjusting the position of the target image in the horizontal direction; When the first threshold is greater than or equal to the second threshold, the vehicle controller determines the horizontal offset as the sample position offset for adjusting the position of the target image in the horizontal direction; when the vertical offset is greater than or equal to the second threshold, the second threshold is determined as the sample position offset for adjusting the position of the target image in the vertical direction; when the vertical offset is less than the second threshold, the vehicle controller determines the vertical offset as the sample position offset for adjusting the position of the target image in the vertical direction; wherein the first threshold and the second threshold are used to indicate the upper limit of the distance for adjusting the position of the target image without affecting the multiple users viewing the target image.

[0068] In some embodiments, the first threshold is the product of the length of the target image and the first coefficient, and the value range of the first coefficient is (0, 0.5). The second threshold is the product of the width of the target image and the second coefficient, and the value range of the second coefficient is (0, 0.5). Optionally, both the first coefficient and the second coefficient are 0.2.

[0069] Step 203: The vehicle controller adjusts the position of the target image on the vehicle screen based on the position offset.

[0070] It should be understood that before adjusting the target image based on the position offset, the vehicle controller may perform pre-processing such as shrinking the target image to obtain a processed image, and then adjust the processed image. The specific implementation process is as follows.

[0071] The first

[0072] In one possible implementation, step 203 includes: the vehicle controller determines, based on the position offset, a first moving direction and a corresponding first moving amount for adjusting the target image in the horizontal direction, and determines a second moving direction and a corresponding second moving amount for adjusting the target image in the vertical direction; the vehicle controller moves the target image on the vehicle-mounted screen in the first moving direction by the first moving amount, and moves it in the second moving direction by the second moving amount.

[0073] In the above technical solution, the target image is displayed on the vehicle screen, and the position offset includes the direction and offset of adjusting the target image in the horizontal direction, and the direction and offset of adjusting the target image in the vertical direction. The present application determines the specific parameters for adjusting the target image from the position offset (the first moving direction and the first moving amount adjusted in the horizontal direction, and the second moving direction and the second moving amount adjusted in the vertical direction), and adjusts the position of the target image on the vehicle screen based on the specific parameters to achieve accurate position adjustment of the target image and reduce the degree of shaking between the target user and the target image when the target user is watching a movie.

[0074] It should be understood that the vehicle controller does not pre-process the target image before adjusting the target image in the first manner, which is equivalent to directly adjusting the position of the target image on the vehicle screen based on the position offset.

[0075] Figure 3 It is a schematic diagram of an interface for adjusting an image provided in an embodiment of the present application.

[0076] Exemplarily, taking the position offset (-a, b) as an example, the process of the vehicle controller adjusting the position of the target image on the vehicle screen is described.

[0077] Based on the position offset (-a, b), the vehicle controller determines that the first moving direction of the target image in the horizontal direction is adjusted to the left direction, and the first movement amount of the target image in the horizontal direction is adjusted to a; and determines that the second moving direction of the target image in the vertical direction is adjusted to the upward direction, and the second movement amount of the target image in the vertical direction is adjusted to b.

[0078] Specifically, Figure 3 As shown, the vehicle controller moves the target image on the vehicle screen to the left by a first movement amount a, and moves it upward by a second movement amount b.

[0079] It should be understood that Figure 3 As shown in FIG. 1 , before the target image is adjusted, the target image covers the entire display area. When adjusting, the target image is directly moved to the left by a and upward by b based on the center of the target image. Therefore, after the target image is adjusted, the adjusted image loses part of the original image content. This is because the adjusted image (such as Figure 3 The area indicated by the dotted line in the figure is beyond the display range of the display area. The adjusted image is displayed in Figure 3 The area indicated by the solid line.

[0080] The second

[0081] In one possible implementation, before the vehicle controller moves the target image on the vehicle screen in the first moving direction by the first moving amount and in the second moving direction by the second moving amount, the method 200 also includes: the vehicle controller shrinks the target image in the horizontal direction based on the first moving amount, and shrinks the target image in the vertical direction based on the second moving amount to obtain a reduced image, and the reduced image is displayed in the central display area of ​​the vehicle screen; and the vehicle controller moves the target image on the vehicle screen in the first moving direction by the first moving amount and in the second moving direction by the second moving amount, including: the vehicle controller moves the reduced image from the central display area to the first moving direction by the first moving amount, and to the second moving direction by the second moving amount.

[0082] In the above technical solution, before adjusting (moving) the target image, the target image is reduced in the horizontal direction and the vertical direction based on the first movement amount and the second movement amount. Afterwards, the target image is adjusted in the horizontal direction and the vertical direction of the vehicle-mounted screen based on the first movement amount and the second movement amount, respectively. This method of first reducing and then adjusting can ensure that the adjusted target image does not lose the content on the original image, and can also reduce the degree of shaking between the target user and the target image when the target user is watching a movie, thereby improving the target user's viewing and entertainment experience.

[0083] In some embodiments, the vehicle controller shrinks the target image in the horizontal direction based on the first movement amount, and shrinks the target image in the vertical direction based on the second movement amount to obtain a reduced image, including: the vehicle controller shrinks the target image in the horizontal direction by the first target movement amount, and shrinks the target image in the vertical direction by the second target movement amount, the first target movement amount is the product of the first movement amount and a third coefficient, the third coefficient is greater than or equal to 2, and the second target movement amount is the product of the second movement amount and a fourth coefficient, the fourth coefficient is greater than or equal to 2.

[0084] In the above technical solution, before adjusting the target image, the vehicle controller reduces the target image by a first target movement amount in the horizontal direction and a second target movement amount in the vertical direction. The first target movement amount is the product of the first movement amount and a third coefficient, the third coefficient is greater than or equal to 2, and the second target movement amount is the product of the second movement amount and a fourth coefficient, the fourth coefficient is greater than or equal to 2. This ensures that after adjusting the target image in the horizontal direction and the vertical direction based on the first movement amount and the second movement amount, the adjusted image will not lose the content in the original image.

[0085] Figure 4 This is another schematic diagram of an interface for adjusting an image provided in an embodiment of the present application.

[0086] Exemplarily, taking the position offset as (-a, b), the third coefficient and the fourth coefficient are both 2, that is, the first target movement amount is 2a, and the second target movement amount is 2b as an example, the process of the vehicle controller adjusting the position of the target image on the vehicle screen is described.

[0087] The vehicle controller reduces the target image in the horizontal direction by a first target movement amount of 2a, and in the vertical direction by a second target movement amount of 2b, to obtain a reduced image 1. For details, see Figure 4 The area indicated by the medium thick solid line.

[0088] Specifically, Figure 4 As shown, the vehicle controller moves the reduced image 1 to the left by a first movement amount a and moves it upward by a second movement amount b on the display area of ​​the vehicle-mounted screen to obtain an adjusted image (reduced image 2), that is, Figure 4 The area indicated by the dashed line.

[0089] It should be understood that Figure 4As shown, before adjusting the target image, the vehicle controller shrinks the target image so that the shrunken image 1 is displayed in the central display area of ​​the display area, that is, it does not cover the entire display area. During adjustment, the shrunken image 1 is directly moved to the left by a and moved upward by b based on the center of the shrunken image 1. Therefore, after adjusting the shrunken image 1, the adjusted image (shrunken image 2) can retain all the contents of the original image.

[0090] The third

[0091] In one possible implementation, before the vehicle controller moves the target image on the vehicle screen in the first moving direction by the first moving amount and in the second moving direction by the second moving amount, the method 200 also includes: the vehicle controller determines a redundant display area in the edge area of ​​the display area of ​​the vehicle screen based on the first moving amount and the second moving amount, the redundant display area is used to indicate the area to which the target image can be moved, the display area includes the redundant display area and the central display area, and the redundant display area and the central display area do not overlap, and the target image is displayed in the central display area; and the vehicle controller moves the target image on the vehicle screen in the first moving direction by the first moving amount and in the second moving direction by the second moving amount, including: the vehicle controller moves the target image from the central display area to the first moving direction by the first moving amount and to the second moving direction by the second moving amount, so that a portion of the target image is displayed in the redundant display area.

[0092] In the above technical solution, before adjusting (moving) the target image, a redundant display area is determined in the edge area of ​​the display area of ​​the vehicle-mounted screen based on the first movement amount and the second movement amount, so that the target image is displayed in the central area (central display area) of the display area, so that the redundant display area is used to adjust the position of the target image. Afterwards, based on the first movement amount and the second movement amount, the target image is adjusted in the horizontal direction and the vertical direction of the vehicle-mounted screen respectively. This setting of a redundant display area on the display area so that the target image is displayed in the central display area of ​​the display area is equivalent to a method of first reducing the target image and then adjusting the target image. This method can ensure that the adjusted target image does not lose the content on the original image, and can also reduce the degree of shaking between the target user and the target image when the target user is watching a movie, thereby improving the target user's viewing and entertainment experience.

[0093] In some embodiments, the vehicle controller determines a redundant display area in the edge area of ​​the display area of ​​the vehicle-mounted screen based on the first movement amount and the second movement amount, including: the vehicle controller marks a first area and a second area with a length of the target image and a width of the second movement amount in the upper and lower areas of the display area, respectively, and marks a third area and a fourth area with a length of the target image and a width of the first movement amount in the left and right areas of the display area, respectively; the vehicle controller determines the area composed of the first area, the second area, the third area and the fourth area as the redundant display area.

[0094] Figure 5 This is another schematic diagram of an interface for adjusting an image provided in an embodiment of the present application.

[0095] Exemplarily, taking the position offset (-a, b) as an example, the process of the vehicle controller adjusting the position of the target image on the vehicle screen is described.

[0096] The vehicle controller sets a redundant display area on the display area based on the first movement amount, the second movement amount, the length of the target image and the width of the target image, so that the target image is displayed on the display area as shown in FIG. Figure 5 The central display area shown is equivalent to indirectly reducing the target image to obtain the target image 1.

[0097] Specifically, Figure 5 As shown, the vehicle controller moves the target image 1 to the left by a first movement amount a and moves it upward by a second movement amount b on the central display area of ​​the vehicle-mounted screen to obtain an adjusted image (target image 2), that is, Figure 5 The area indicated by the dotted line in the middle. Part of the image in the target image 2 is displayed in the redundant display area.

[0098] It should be understood that Figure 5 As shown, before adjusting the target image, the vehicle controller sets a redundant display area on the display area, so that the target image is displayed in the central display area of ​​the display area, which indirectly reduces the target image (obtaining target image 1), that is, the target image does not cover the entire display area. When adjusting, the target image 1 is directly moved to the left by a and moved upward by b based on the center of the target image 1. Therefore, after adjusting the target image 1, the adjusted image (target image 2) can retain all the contents of the original image.

[0099] The fourth

[0100] In one possible implementation, step 203 includes: the vehicle controller obtains the posture information of the target user's head; the vehicle controller corrects the position offset based on the posture information to obtain the target position offset; the vehicle controller adjusts the position of the target image on the vehicle screen based on the target position offset.

[0101] It should be understood that the "position information of the head" in the above solution includes the position information of the head and the posture information of the head. The position information of the head is used to indicate the position of the head relative to the vehicle-mounted screen, and the posture information of the head includes the pitch angle and the tilt angle of the head. Among them, the pitch angle of the head refers to the angle between the head and the horizontal plane, and the tilt angle of the head refers to the angle of the head deflecting to the left or right.

[0102] In the above technical solution, the position offset of the target image determined by the target model based on the posture information and user attributes is an indirect way of estimating the position offset, and does not involve the posture information of the target user's head at the posture indicated by the posture information. Therefore, the present application also corrects the position offset based on the posture information of the target user's head to obtain a more accurate position offset (target position offset); based on the target position offset, adjust the position of the target image on the vehicle screen. Compared with the process of adjusting the position of the target image on the vehicle screen based on the position offset, this solution can better reduce the degree of shaking between the target user and the target image when the target user is watching a movie.

[0103] In some embodiments, the vehicle controller obtains the position information of the target user's head, including: the vehicle controller obtains the head image of the target user through the visual sensor in the target vehicle, and inputs the head image into a pre-trained hierarchical prediction network to predict the pitch angle and tilt angle of the head posture orientation. The hierarchical prediction network includes a backbone network, a feature pyramid network, a dimensionality reduction module and a hierarchical prediction module. The backbone network is used to extract spatial features of head images of different sizes. The feature pyramid network is used to fuse the spatial features of head images of different sizes to obtain fused features. The dimensionality reduction module is used to perform dimensionality reduction in two different dimensions on the fused features to obtain spatial features of two dimensions of the image. Different dimensions correspond to different numbers of head image channels. The hierarchical prediction module includes two fully connected layers. The two fully connected layers predict the spatial features of the two dimensions respectively. Each fully connected layer predicts an angle of the head posture orientation, and the size is in pixels.

[0104] In the above technical solution, two fully connected layers are used to predict the spatial features of the two dimensions respectively, so that the hierarchical prediction network can predict the head posture towards the image area that is concerned by the two angles respectively, thereby reducing the mutual interference between the predictions of the two angles.

[0105] The process of "the vehicle controller correcting the position offset based on the posture information" is further discussed in two ways as follows.

[0106] In some embodiments, the vehicle controller corrects the position offset based on the posture information to obtain a target position offset, including: the vehicle controller determines whether the head offset direction indicated by the position information in the posture information is the same as the first movement direction determined by the position offset; when the head offset direction is different from the first movement direction, the vehicle controller corrects the first movement direction to the head offset direction; when the head offset direction is the same as the first movement direction, the vehicle controller determines a fifth coefficient corresponding to the tilt angle and a sixth coefficient corresponding to the pitch angle based on the deviation between the posture information in the posture information and the posture information of the target vehicle, the fifth coefficient is used to correct the first movement determined by the position offset, and the sixth coefficient is used to correct the second movement determined by the position offset; the vehicle controller determines a first product value between the first movement and the fifth coefficient, and corrects the first movement to the first product value; the vehicle controller determines a second product value between the second movement and the sixth coefficient, and corrects the second movement to the second product value.

[0107] In the above technical solution, the vehicle controller corrects the moving direction (including the first moving direction and the second moving direction) determined by the position offset through the position information in the position information of the target user's head, and corrects the moving amount (including the first moving amount and the second moving amount) determined by the position offset through the deviation between the posture information in the head posture information and the posture information of the target vehicle. This correction process enables the vehicle controller to determine a more accurate position offset (target position offset). After the vehicle controller adjusts the target image based on the target position offset, the degree of shaking between the target user and the target image can be further reduced when the target user is watching a movie.

[0108] Figure 6 It is a structural schematic diagram of a device for adjusting an image provided in an embodiment of the present application.

[0109] For example, Figure 6 As shown, the device 600 includes:

[0110] The acquisition module 601 is used to acquire the posture information of the target vehicle and the user attributes of the target user in the target vehicle during the driving process of the target vehicle;

[0111] Processing module 602, used for inputting the posture information and the user attribute into a target model to obtain a position offset for adjusting a target image, wherein the target model is trained based on multiple sample posture information, multiple sample user attributes and corresponding multiple sample position offsets, and the target image is an image displayed on the vehicle screen corresponding to the target user;

[0112] The adjustment module 603 is used to adjust the position of the target image on the vehicle-mounted screen based on the position offset.

[0113] Optionally, the adjustment module 603 is specifically used to: determine, based on the position offset, a first moving direction and a corresponding first moving amount for adjusting the target image in the horizontal direction, and determine a second moving direction and a corresponding second moving amount for adjusting the target image in the vertical direction; move the target image on the vehicle-mounted screen in the first moving direction by the first moving amount, and move the target image in the second moving direction by the second moving amount.

[0114] Optionally, before moving the target image on the vehicle-mounted screen by the first movement amount in the first movement direction and by the second movement amount in the second movement direction, the device 600 also includes: a reduction module, used to reduce the target image in the horizontal direction based on the first movement amount, and to reduce the target image in the vertical direction based on the second movement amount to obtain a reduced image, and the reduced image is displayed in the central display area of ​​the vehicle-mounted screen; and the adjustment module 603 is specifically used to move the reduced image from the central display area to the first movement direction by the first movement amount, and to the second movement direction by the second movement amount.

[0115] Optionally, before moving the target image on the vehicle-mounted screen by the first movement amount in the first movement direction and by the second movement amount in the second movement direction, the device 600 also includes: a determination module, used to determine a redundant display area in an edge area of ​​the display area of ​​the vehicle-mounted screen based on the first movement amount and the second movement amount, the redundant display area is used to indicate an area to which the target image can be moved, the display area includes the redundant display area and the central display area, and the redundant display area and the central display area do not overlap, and the target image is displayed in the central display area; and the adjustment module 603 is specifically used to move the target image from the central display area to the first movement direction by the first movement amount and to the second movement direction by the second movement amount, so that a portion of the target image is displayed in the redundant display area.

[0116] Optionally, the determination module is further specifically used to: determine multiple sample posture information, multiple sample user attributes and corresponding multiple sample position offsets for adjusting the position of the target image; based on the multiple sample posture information, the multiple sample user attributes and the corresponding multiple sample position offsets, adjust the weight parameters in the target model to be trained to obtain an adjusted model; when the loss value between the position offset obtained by the adjusted model and the corresponding sample offset is less than a preset value, determine the adjusted model as the target model.

[0117] Optionally, the acquisition module 601 is also used to obtain the posture information of the target user's head; the device 600 also includes: a correction module, used to correct the position offset based on the posture information to obtain a target position offset; the adjustment module 603 is specifically used to adjust the position of the target image on the vehicle-mounted screen based on the target position offset.

[0118] Optionally, the posture information includes at least one of an inclination angle and a pitch angle, and the user attribute includes at least one of upper body length, gender, age and weight. The acquisition module 601 is specifically used to: acquire the inclination angle and the pitch angle through an angle sensor in the target vehicle; determine the upper body length of the target user through a visual sensor in the target vehicle; acquire a facial image of the target user through the visual sensor, and determine the gender and the age based on image features of the facial image; acquire an upper body image of the target user through the visual sensor, and determine the widths of multiple limb parts in the upper body image; determine the fatness level of the target user based on the widths of the multiple limb parts; and determine the weight based on the fatness level and the gender.

[0119] Figure 7 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application.

[0120] For example, Figure 7 As shown, the vehicle 700 includes: a memory 701, a processor 702, and a computer program 703 stored in the memory 701 and running on the processor 702, wherein when the processor 702 executes the computer program 703, the vehicle can execute any one of the methods for adjusting the image described above.

[0121] In this embodiment, the functional modules of the vehicle can be divided according to the above method example. For example, each functional module can be corresponded, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0122] In the case of dividing each functional module according to each function, the vehicle may include: an acquisition module, a processing module, an adjustment module, a determination module, a reduction module, and a correction module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.

[0123] The vehicle provided in this embodiment is used to execute the above-mentioned method of adjusting the image, and thus can achieve the same effect as the above-mentioned implementation method.

[0124] In the case of an integrated unit, the vehicle may include a processing module and a storage module. The processing module may be used to control and manage the actions of the vehicle. The storage module may be used for the vehicle to execute mutual program codes and data.

[0125] The processing module may be a processor or a controller, which may implement or execute various exemplary logic blocks, modules and circuits disclosed in the present application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module may be a memory.

[0126] This embodiment provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a computer or a processor, the computer or the processor executes any one of the above-described methods for adjusting an image.

[0127] This embodiment also provides a computer program product including instructions. When the computer program product is run on a computer or a processor, the computer or the processor executes the above-mentioned related steps to implement any one of the above-mentioned methods for adjusting an image.

[0128] Among them, the vehicle, computer-readable storage medium, computer program product or chip containing instructions provided in this embodiment are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0129] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0130] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0131] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for adjusting an image, characterized in that: The method comprises: During the driving of the target vehicle, obtaining posture information of the target vehicle and user attributes of a target user in the target vehicle; Inputting the posture information and the user attributes into a target model to obtain a position offset for adjusting a target image, wherein the target model is trained based on multiple sample posture information, multiple sample user attributes, and corresponding multiple sample position offsets, and the target image is an image displayed on a vehicle screen corresponding to the target user; Based on the position offset, the position of the target image on the in-vehicle screen is adjusted.

2. The method according to claim 1, characterized in that The adjusting the position of the target image on the vehicle-mounted screen based on the position offset comprises: Based on the position offset, determine a first movement direction and a corresponding first movement amount for adjusting the target image in the horizontal direction, and determine a second movement direction and a corresponding second movement amount for adjusting the target image in the vertical direction; The target image is moved on the in-vehicle screen in the first moving direction by the first moving amount, and in the second moving direction by the second moving amount.

3. The method according to claim 2, characterized in that Before moving the target image on the vehicle-mounted screen in the first moving direction by the first moving amount and in the second moving direction by the second moving amount, the method further includes: Based on the first movement amount, the target image is reduced in the horizontal direction, and based on the second movement amount, the target image is reduced in the vertical direction to obtain a reduced image, and the reduced image is displayed in the central display area of ​​the vehicle-mounted screen; And, moving the target image on the vehicle-mounted screen in the first moving direction by the first moving amount, and in the second moving direction by the second moving amount, comprises: The reduced image is moved from the central display area to the first moving direction by the first moving amount, and is moved to the second moving direction by the second moving amount.

4. The method according to claim 2, characterized in that: Before moving the target image on the vehicle-mounted screen in the first moving direction by the first moving amount and in the second moving direction by the second moving amount, the method further includes: Based on the first movement amount and the second movement amount, a redundant display area is determined in an edge area of ​​a display area of ​​the in-vehicle screen, the redundant display area is used to indicate an area to which the target image can be moved, the display area includes the redundant display area and a central display area, and the redundant display area and the central display area do not overlap, and the target image is displayed in the central display area; And, moving the target image on the vehicle-mounted screen in the first moving direction by the first moving amount, and in the second moving direction by the second moving amount, comprises: The target image is moved from the central display area to the first moving direction by the first moving amount, and is moved to the second moving direction by the second moving amount, so that a portion of the target image is displayed in the redundant display area.

5. The method according to claim 1, characterized in that The method for determining the target model includes: Determine multiple sample pose information 、 A plurality of sample user attributes and a corresponding plurality of sample position offsets for adjusting the position of the target image; Based on the plurality of sample posture information, the plurality of sample user attributes and the corresponding plurality of sample position offsets, adjusting weight parameters in the target model to be trained to obtain an adjusted model; In a case where a loss value between a position offset obtained by the adjusted model and a corresponding sample offset is less than a preset value, the adjusted model is determined as the target model.

6. The method according to claim 1, characterized in that The adjusting the position of the target image on the vehicle-mounted screen based on the position offset comprises: Acquire the position and posture information of the target user's head; Correcting the position offset based on the posture information to obtain a target position offset; Based on the target position offset, the position of the target image on the in-vehicle screen is adjusted.

7. The method according to claim 1, characterized in that The posture information includes at least one of a tilt angle and a pitch angle, the user attribute includes at least one of an upper body length, a gender, an age, and a weight, and the acquiring of the posture information of the target vehicle and the user attribute of the target user in the target vehicle includes: Acquire the tilt angle and the pitch angle by an angle sensor in the target vehicle; Determine the upper body length of the target user by using a visual sensor in the target vehicle; Acquire a facial image of the target user through the visual sensor, and determine the gender and age based on image features of the facial image; The upper body image of the target user is acquired through the visual sensor, and the widths of multiple limb parts in the upper body image are determined; based on the widths of the multiple limb parts, the fatness level of the target user is determined; based on the fatness level and the gender, the weight is determined.

8. A device for adjusting an image, characterized in that: The device comprises: An acquisition module, used to acquire the posture information of the target vehicle and the user attributes of the target user in the target vehicle during the driving process of the target vehicle; a determination module, configured to input the posture information and the user attributes into a target model to obtain a position offset for adjusting a target image, wherein the target model is trained based on a plurality of sample posture information, a plurality of sample user attributes, and a plurality of corresponding sample position offsets, and the target image is an image displayed on a vehicle screen corresponding to the target user; An adjustment module is used to adjust the position of the target image on the vehicle-mounted screen based on the position offset.

9. A vehicle, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the vehicle executes the method for adjusting an image as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a computer or a processor, the computer or the processor executes the method for adjusting an image according to any one of claims 1 to 7.

Images