Adjustment method, device and equipment of vehicle head-up display system and storage medium

Abstract

The application relates to the technical field of intelligent driving, and discloses a kind of adjustment method, device and equipment of vehicle-mounted head-up display system and storage medium, wherein the method comprises: obtaining the driving pose information of a driver;Based on the driving pose information, the imaging size and imaging distance of the vehicle-mounted head-up display system are determined;According to the imaging size and imaging distance, the projection state of the vehicle-mounted head-up display system for driving information is adjusted.Through the implementation of the technical scheme of the application, dynamic adjustment of the HUD imaging size and imaging distance is realized, thereby realizing adaptive dynamic adjustment of the imaging effect, and the best HUD display effect is guaranteed to the greatest extent.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent driving, and in particular to a vehicle-mounted head-up display system adjusting method, device, equipment and storage medium. BACKGROUND

[0002] The vehicle-mounted head-up display system (HUD) can project driving information in the form of virtual image onto the front windshield of the vehicle, so that the driver can obtain real-time information without looking down at the instrument panel. However, due to the differences in height, vision, viewing angle and other factors of the driver, the display effect of the HUD has certain limitations. The current adjustment of the HUD is mainly based on the adaptive adjustment of the height, which is difficult to dynamically adjust the imaging effect of the HUD according to the actual situation of different drivers in the vehicle, so as to achieve the best HUD display effect. SUMMARY

[0003] Therefore, the present application provides a vehicle-mounted head-up display system adjusting method, device, equipment and storage medium to solve the problem of difficulty in dynamically adjusting the imaging effect of the HUD.

[0004] In a first aspect, the present application provides a vehicle-mounted head-up display system adjusting method, which comprises: obtaining the driving pose information of the driver; determining the imaging size and imaging distance of the vehicle-mounted head-up display system based on the driving pose information; and adjusting the projection state of the vehicle-mounted head-up display system for the driving information according to the imaging size and imaging distance.

[0005] The vehicle-mounted head-up display system adjusting method provided by the present application detects the driving pose information of the driver, calculates the imaging size and imaging distance of the virtual image generated by the HUD on the windshield in real time based on the detected driving pose information, and then dynamically adjusts the projection state of the driving information projected by the vehicle-mounted head-up display system on the windshield according to the imaging size and imaging distance, so that the projection state of the virtual image generated for the driving information meets the actual situation of the current driver, realizes the adaptive dynamic adjustment of the imaging effect of the HUD, and maximizes the best HUD display effect.

[0006] In an optional embodiment, based on the driving pose information, the imaging size and imaging distance of the vehicle-mounted head-up display system are determined, which comprises: analyzing the driving pose information to determine the spatial position coordinates of the key parts corresponding to the driver; obtaining the imaging position coordinates of the vehicle-mounted head-up display system; and determining the imaging size and imaging distance based on the spatial position coordinates of the key parts and the imaging position coordinates.

[0007] The adjusting method of the vehicle-mounted head-up display system provided by the embodiment of the present application determines the imaging size and the imaging distance suitable for the current driver in combination with the spatial position coordinates of each key part of the driver and the imaging position coordinates of the HUD, so that the imaging parameters of the HUD can be dynamically adjusted according to the actual situation of different drivers in the vehicle, so as to achieve the best imaging effect.

[0008] In an optional implementation, the driver's key part spatial position coordinates for virtual image observation are determined based on the driving posture information, including: determining the driver's body spatial position coordinates based on the driving posture information; analyzing the body spatial position coordinates to determine the driver's head spatial position coordinates, forehead spatial position coordinates and eye spatial position coordinates; and determining the head spatial position coordinates, the forehead spatial position coordinates and the eye spatial position coordinates as the key part spatial position coordinates.

[0009] The adjusting method of the vehicle-mounted head-up display system provided by the embodiment of the present application extracts the spatial position coordinates of the key parts such as the head, the forehead and the eyes from the driver's body spatial position coordinates, so as to facilitate accurate prediction of the imaging size and the imaging distance in combination with the spatial position coordinates of the key parts, so as to provide the driver with driving information with the best display effect, which is conducive to improving the driving safety.

[0010] In an optional implementation, the imaging size and the imaging distance are determined based on the key part spatial position coordinates and the imaging position coordinates, including: converting the key part spatial position coordinates and the imaging position coordinates to the same coordinate system to determine target head coordinates, target forehead coordinates, target eye coordinates and target imaging position coordinates in the same coordinate system; determining the driver's body inclination angle based on the target eye coordinates; determining the driver's head deflection angle based on the target imaging position coordinates and the target forehead coordinates; determining the target distance from the driver's head to the virtual image based on the target imaging position coordinates and the target head coordinates, the virtual image being generated by the projection of the vehicle-mounted display system; inputting the body inclination angle, the head deflection angle and the target distance into a preset imaging adjustment model to output the imaging size and the imaging distance through the preset imaging adjustment model; wherein the preset imaging adjustment model is obtained by pre-training based on a deep learning algorithm.

[0011] The adjustment method for an in-vehicle head-up display system provided in this invention performs coordinate transformation to convert the spatial position coordinates and the imaging position coordinates to the same coordinate system. Within this same coordinate system, by combining the relationships between head coordinates, eye coordinates, forehead coordinates, and imaging position coordinates, the method determines the driver's body tilt angle, head deflection angle, and target distance from the head to the virtual image during driving. Subsequently, an imaging adjustment model pre-trained based on a deep learning algorithm outputs the corresponding imaging size and imaging distance, thereby achieving adaptive adjustment of the imaging size and imaging distance, making the driving assistance function more intelligent.

[0012] In one optional implementation, training a preset imaging adjustment model based on a deep learning algorithm includes: detecting whether the imaging function of the vehicle head-up display system is activated for the first time; when the imaging function of the vehicle head-up display system is activated for the first time, obtaining the driver's pose reference value; based on the pose reference value, determining the imaging size calibration value and imaging distance calibration value of the vehicle head-up display system; in response to the adjustment operation of the imaging size calibration value and imaging distance calibration value, determining the adjusted target imaging size and target imaging distance; and iteratively training the preset imaging adjustment model using a deep learning algorithm based on the pose reference value, the target imaging size, and the target imaging distance.

[0013] The adjustment method for the vehicle head-up display system provided in this embodiment of the invention determines the imaging size calibration value and imaging distance calibration value through the pose reference value, and then iteratively trains the preset imaging adjustment model by combining the driver's pose reference value and the adjusted target imaging size and target imaging distance, so as to achieve accurate prediction of imaging size and imaging distance.

[0014] In one optional implementation, obtaining the driver's driving posture information includes: detecting at least one driving position of the driver; collecting posture information corresponding to at least one driving position; and integrating the posture information to generate driving posture information.

[0015] The adjustment method for the vehicle head-up display system provided in this embodiment of the invention detects multiple driving positions for the driver and integrates the pose information corresponding to different driving positions to obtain the driver's driving pose information. This facilitates the subsequent adjustment of the imaging size and imaging distance of the virtual image generated by the HUD in combination with different pose information, so as to make the adjustment of the imaging size and imaging distance more precise.

[0016] In one optional implementation, the projection state of the vehicle head-up display system for driving information is adjusted according to the imaging size and imaging distance, including: acquiring the current projection state of the driving information on the windshield of the actual vehicle; sending the imaging size and imaging distance to the adjustment system corresponding to the vehicle head-up display system, and dynamically adjusting the current projection state through the adjustment system.

[0017] The adjustment method for the vehicle head-up display system provided in this embodiment of the invention adjusts the projection state of the virtual image generated by the HUD by adjusting the imaging size and imaging distance, so that the virtual image projected onto the windshield better meets the driver's observation of driving information, thereby further improving vehicle driving safety.

[0018] Secondly, the present invention provides an adjustment device for an in-vehicle head-up display system, the device comprising: an acquisition module for acquiring driver's driving posture information; an imaging information determination module for determining the imaging size and imaging distance of the in-vehicle head-up display system based on the driver's posture information; and an adjustment module for adjusting the projection state of the in-vehicle head-up display system for driving information according to the imaging size and imaging distance.

[0019] Thirdly, the present invention provides an in-vehicle device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the adjustment method of the in-vehicle head-up display system of the first aspect or any corresponding embodiment thereof.

[0020] Fourthly, the present invention provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions, the computer instructions being used to cause a computer to execute the adjustment method of the vehicle head-up display system of the first aspect or any corresponding embodiment thereof.

[0021] The beneficial effects of this invention are:

[0022] (1) This invention combines the detected driver posture information to calculate the imaging size and imaging distance of the virtual image generated by the HUD on the windshield in real time, thereby realizing the adaptive dynamic adjustment of the HUD imaging effect and ensuring the best HUD display effect to the greatest extent.

[0023] (2) The present invention can dynamically adjust the imaging parameters of the HUD according to the actual situation of different drivers in the vehicle, so that the virtual image projected onto the windshield is more in line with the driver's observation of driving information, making the driving assistance function more intelligent and further improving the driving safety of the vehicle. Attached Figure Description

[0024] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0025] Figure 1 This is a flowchart of an adjustment method for an in-vehicle head-up display system according to an embodiment of the present invention;

[0026] Figure 2 This is a flowchart of an adjustment method for another vehicle head-up display system according to an embodiment of the present invention;

[0027] Figure 3 This is a flowchart of an adjustment method for another vehicle head-up display system according to an embodiment of the present invention;

[0028] Figure 4 This is a structural block diagram of the adjustment device of the vehicle head-up display system according to an embodiment of the present invention;

[0029] Figure 5 This is a schematic diagram of the hardware structure of the vehicle-mounted device according to an embodiment of the present invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0031] A head-up display (HUD) system projects driving information as a virtual image onto the vehicle's windshield, allowing the driver to access real-time information without looking down at the dashboard.

[0032] Due to differences in drivers' height, vision, and viewing angle, the display effect of HUDs has certain limitations. Therefore, it is necessary to adjust the virtual image of the HUD in conjunction with the driver's driving posture. Currently, mechanical design technology is typically used, combined with the integrated application of sensor technology, computer vision technology, and artificial intelligence technology to achieve adaptive height adjustment of the HUD, making the adjustment of the HUD more precise and stable.

[0033] Current technologies only adaptively adjust the virtual image height of the HUD. They use various in-vehicle sensors to identify the user's posture and adjust the corresponding height coordinates of the HUD to achieve a better display effect. However, these solutions ultimately only adjust the HUD display height, and their effect on optimizing the actual HUD display is not significant. They only solve the problem of whether the user can see the image properly, but do not address the issue of poor display quality. Due to the unique optical display characteristics of HUDs, different user postures, head turning angles, and ambient lighting conditions all affect the HUD display effect. Simply adjusting the HUD height cannot meet the driver's needs for quick and accurate access to the displayed information.

[0034] Based on this, the technical solution of the present invention obtains information such as the driver's body position and posture, calculates the imaging size and imaging distance of the HUD virtual image in real time based on the obtained information such as the body position and posture, and dynamically adjusts the projection state of the virtual image in combination with the calculated imaging size and imaging distance to achieve the best HUD display effect.

[0035] According to an embodiment of the present invention, an embodiment of an adjustment method for an in-vehicle head-up display system is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0036] This embodiment provides a method for adjusting an in-vehicle head-up display system, which can be used for in-vehicle devices such as in-vehicle head-up display systems installed in vehicles. Figure 1 This is a flowchart of an adjustment method for an in-vehicle head-up display system according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0037] Step S101: Obtain the driver's driving posture information.

[0038] Driving posture information is used to characterize the driver's body position and driving posture in the driver's seat. The in-vehicle display system includes a projection lens and an image acquisition device, with the image acquisition device positioned to one side of the projection lens. The image acquisition device may include one or more of the following: optical sensors, inertial sensors, driver monitoring systems (DMS), and interior monitoring systems (IMS) cameras. No specific limitations are specified here, and those skilled in the art can determine the appropriate device based on actual needs.

[0039] The driver's driving posture information can be acquired through an image acquisition device. Specifically, a spatial coordinate system for the driver is established using DMS and IMS cameras installed in the vehicle, and the driver's driving posture information in that spatial coordinate system is acquired.

[0040] Step S102: Based on the driver's posture information, determine the imaging size and imaging distance of the vehicle head-up display system.

[0041] Imaging size and imaging distance are used to characterize the imaging parameters of the HUD. The HUD can combine imaging size and imaging distance to project real-time driving information during the driving process onto the vehicle's windshield, making it easier for the driver to determine the driving information during the driving process through the virtual image presented by the HUD. Among them, driving information is used to characterize the current vehicle speed, navigation and other driving information during the driving process, so that the driver can see the driving information without looking down or turning their head as much as possible.

[0042] The driver's pose information acquired by the image acquisition device is preprocessed and analyzed to determine data such as the driver's head position, head rotation angle, and body tilt angle. Based on the functional relationship between this data and the imaging size and imaging distance, the imaging size and imaging distance corresponding to the current driver pose information are determined. The functional relationship between the driver's head position, head rotation angle, body tilt angle, and the imaging size and imaging distance is pre-fitted. Specifically, the fitting of the functional relationship can be achieved in various ways, such as algorithms based on artificial neural networks, machine learning, and deep learning. The fitting method is not limited here, as long as the functional relationship between the driver pose information and the imaging size and imaging distance can be determined.

[0043] Step S103: Adjust the projection state of the vehicle head-up display system for driving information according to the imaging size and imaging distance.

[0044] The determined imaging size and imaging distance are transmitted to the HUD's adjustment system. The adjustment system can then adjust the virtual image of the driving information in real time according to the imaging size and imaging distance, thereby adjusting the projection state of the driving information so that the virtual image of the driving information projected onto the windshield has the best display effect.

[0045] The adjustment of the imaging size and imaging distance can be achieved in various ways, such as adjustment systems based on mechanical structures, optical systems, motors, hydraulics, etc. The adjustment system is not limited here, as long as it can adjust the projection state of the virtual image in real time in conjunction with the imaging size and imaging distance.

[0046] The adjustment method for the vehicle head-up display system provided in this embodiment detects the driver's driving posture information and calculates the imaging size and imaging distance of the virtual image generated by the HUD on the windshield in real time based on the detected driving posture information. Then, it dynamically adjusts the state of the vehicle head-up display system projecting driving information on the windshield according to the imaging size and imaging distance, so that the projection state of the virtual image generated for the driving information meets the current actual situation of the driver, realizing adaptive dynamic adjustment of the HUD imaging effect and ensuring the best HUD display effect to the greatest extent.

[0047] This embodiment provides a method for adjusting an in-vehicle head-up display system, which can be used for in-vehicle devices such as in-vehicle head-up display systems installed in vehicles. Figure 2 This is a flowchart of an adjustment method for an in-vehicle head-up display system according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0048] Step S201: Obtain the driver's driving posture information. For detailed explanation, please refer to the relevant descriptions in the above embodiments; they will not be repeated here.

[0049] Step S202: Based on the driver's posture information, determine the imaging size and imaging distance of the vehicle head-up display system.

[0050] Specifically, step S202 above may include:

[0051] Step S2021: Analyze the driver's posture information and determine the spatial coordinates of the key parts corresponding to the driver.

[0052] The HUD virtual image is displayed in the windshield for the driver to see, while the key parts are the body parts that need to be referenced to determine the HUD virtual image. Since driving posture information can characterize the driver's body position and driving posture, by analyzing the driving position information, the spatial coordinates of the body can be extracted. By combining the relative positional relationship between the driver's key parts and the body, the spatial coordinates corresponding to each key part can be determined.

[0053] In some optional implementations, step S2022 above includes:

[0054] Step a1: Determine the driver's spatial position coordinates based on the driver's posture information.

[0055] Step a2: Analyze the body's spatial coordinates to determine the driver's head, forehead, and eye spatial coordinates.

[0056] Step a3: Determine the spatial coordinates of key parts by using the spatial coordinates of the head, forehead, and eyes.

[0057] Based on the driver's posture information, the driver's position in the driver's seat can be determined. By combining the pre-constructed spatial coordinate system of the driver's seat with the driver's current driving position, the driver's body spatial coordinates can be determined. Since the driver's head, forehead, and eyes are crucial for observing the HUD virtual image, the head, forehead, and eyes are the key parts corresponding to the driver.

[0058] The image acquisition device corresponding to the HUD can determine the relative positions of the driver's head, forehead, eyes, and body. After determining the body's spatial coordinates, by combining the relative positions of the driver's head, forehead, and eyes with the body, the spatial coordinates of the driver's head, forehead, and eyes can be determined. These spatial coordinates of the head, forehead, and eyes are then the spatial coordinates corresponding to the key body parts.

[0059] In the above embodiments, by detecting the spatial coordinates of the driver's body, the spatial coordinates of key parts such as the head, forehead, and eyes are extracted. This facilitates the accurate prediction of imaging size and imaging distance by combining the spatial coordinates of key parts, thereby providing the driver with driving information with the best display effect and improving driving safety.

[0060] Step S2022: Obtain the imaging position coordinates of the vehicle head-up display system.

[0061] HUD has its own spatial coordinate system, and the imaging position coordinates are determined based on the HUD's own spatial coordinate system. Specifically, the HUD constructs a corresponding spatial coordinate system based on its installation position inside the vehicle, and obtains the imaging position coordinates of the virtual image of driving information in that spatial coordinate system.

[0062] Step S2023: Based on the spatial coordinates of the key parts and the imaging coordinates, determine the imaging size and imaging distance.

[0063] By combining the spatial coordinates of the key components and the imaging coordinates, the spatial coordinates and imaging coordinates are transformed to the same coordinate system to achieve coordinate normalization. Using the normalized spatial coordinates and imaging coordinates, the relative positional relationship between the key components and the imaging position is determined. Based on this relative positional relationship, the imaging size and imaging distance of the virtual image generated by the HUD for driving information are calculated.

[0064] In some optional implementations, step S2023 above includes:

[0065] Step b1: Transform the spatial coordinates and imaging coordinates of the key parts into the same coordinate system, and determine the target head coordinates, target forehead coordinates, target eye coordinates, and target imaging coordinates in the same coordinate system.

[0066] Step b2: Determine the driver's body tilt angle based on the target eye coordinates.

[0067] Step b3: Determine the driver's head deflection angle based on the target imaging position coordinates and the target forehead coordinates.

[0068] Step b4: Based on the target imaging position coordinates and the target head coordinates, determine the target distance from the driver's head to the virtual image, which is generated by the projection of the vehicle display system.

[0069] Step b5: Input the body tilt angle, head tilt angle, and target distance into the preset imaging adjustment model, and output the imaging size and imaging distance through the preset imaging adjustment model.

[0070] The preset imaging adjustment model is pre-trained based on a deep learning algorithm.

[0071] The spatial coordinates of key parts are transformed with the imaging coordinates to be in the same coordinate system. The target head coordinates, forehead coordinates, eye coordinates and imaging coordinates are determined after the coordinate system transformation, and the target head coordinates, forehead coordinates, eye coordinates and imaging coordinates are stored.

[0072] By combining the target forehead coordinates and the target imaging position coordinates, the horizontal angle between the target forehead coordinates and the target imaging position coordinates is determined, thus forming the head deflection angle.

[0073] By combining the target eye coordinates, the vertical height coordinates of each of the driver's eyes are determined, and the body tilt angle is formed based on the horizontal angle between the vertical height coordinates of each eye.

[0074] By combining the target imaging position coordinates and the target head coordinates, the target distance from the driver's head to the imaging plane corresponding to the HUD virtual image can be calculated.

[0075] A preset imaging adjustment model is deployed in the HUD. This preset imaging adjustment model is pre-trained based on a deep learning algorithm and predicts the imaging size and imaging distance. The calculated body tilt angle, head deflection angle, and target distance are input into the preset imaging adjustment model, which then outputs the imaging size and imaging distance that conform to the current pose information.

[0076] In the above embodiments, coordinate transformation is performed to convert the spatial position coordinates and the imaging position coordinates to the same coordinate system. Within this same coordinate system, the relationship between the head coordinates, eye coordinates, forehead coordinates, and imaging position coordinates is used to determine the driver's body tilt angle, head deflection angle, and target distance from the head to the virtual image during driving. Subsequently, an imaging adjustment model pre-trained based on a deep learning algorithm is used to output the corresponding imaging size and imaging distance, thereby achieving adaptive adjustment of the imaging size and imaging distance, making the driving assistance function more intelligent.

[0077] Specifically, the steps for training a pre-defined imaging adjustment model based on a deep learning algorithm may include:

[0078] Step c1: Detect whether the imaging function of the vehicle head-up display system is activated for the first time.

[0079] Step c2: When the imaging function of the vehicle head-up display system is activated for the first time, obtain the driver's positional reference value.

[0080] Step c3: Based on the pose reference value, determine the imaging size calibration value and imaging distance calibration value of the vehicle head-up display system.

[0081] Step c4: In response to the adjustment operation of the imaging size calibration value and the imaging distance calibration value, determine the adjusted target imaging size and target imaging distance.

[0082] Step c5: Based on the pose reference value, target imaging size and target imaging distance, a deep learning algorithm is used to iteratively train the preset imaging adjustment model.

[0083] The first activation refers to the driver's first use of the HUD's imaging function. When the driver's first use of the HUD's imaging function is detected, the current posture reference value of the driver can be obtained through the image acquisition device. Combining the posture reference value, the driver's head coordinate reference value, forehead coordinate reference value, head rotation angle reference value, and body tilt angle reference value can be calculated.

[0084] The imaging size calibration value and imaging distance calibration value are the calibrated imaging size and imaging distance of the HUD. These calibration values ​​are obtained based on the head coordinate reference value, forehead coordinate reference value, head rotation angle reference value, and body tilt angle reference value.

[0085] The imaging size calibration value and imaging distance calibration value are used as imaging reference values. A virtual image of driving information is projected onto the windshield based on these reference values. However, the display effect of the virtual image may not meet the current driving state. At this time, the driver can manually adjust the HUD to achieve the best display effect. Accordingly, the HUD can respond to the driver's adjustment operation and determine the target imaging size and target imaging distance corresponding to the optimal display effect based on the adjustment operation.

[0086] Subsequently, algorithms based on artificial neural networks, machine learning, and deep learning are used to iteratively train the model based on pose reference values, target imaging size, and target imaging distance to obtain a preset imaging adjustment model.

[0087] The calculation of virtual image size and imaging distance is a nonlinear problem. Here, a neural network in deep learning algorithm can be used to train the imaging adjustment model, thereby enabling the prediction of virtual image size and imaging distance based on information such as the driver's body position and posture.

[0088] Specifically, a multilayer perceptron (MLP) neural network model can be constructed here. The input layer has 3 nodes, corresponding to the target distance from the driver's head to the HUD virtual image, the head rotation angle, and the body tilt angle, respectively. The hidden layers can be determined through repeated training and adjustment. The output layer has 2 nodes, corresponding to the imaging size and imaging distance of the virtual image, respectively.

[0089] During training, gradient descent-based optimization algorithms (such as Adam and SGD) are used to minimize the model's prediction error, thereby optimizing the parameters of the imaging adjustment model. Simultaneously, regularization and other techniques are employed to avoid overfitting in the imaging adjustment model.

[0090] Based on the above imaging adjustment model, prediction formulas for imaging size and imaging distance can be obtained respectively. Specifically, the imaging size of the virtual image can be expressed as: $S=f(h,Δ1,Δ2)$, and the imaging distance of the virtual image can be expressed as: $d=g(h,Δ1,Δ2)$.

[0091] Where $h$ represents the target distance from the driver's head to the HUD virtual image; $Δ1$ represents the head rotation angle; $Δ2$ represents the body tilt angle; $f$ is a function used to calculate the image size; $g$ is a function used to calculate the image distance; and $f$ and $g$ represent the prediction functions of the output layer of the multilayer perceptron neural network model for the image size and image distance, respectively.

[0092] In the above embodiments, the imaging size calibration value and imaging distance calibration value of the HUD are determined by the pose reference value. Then, the preset imaging adjustment model is repeatedly trained by combining the driver's pose reference value and the adjusted target imaging size and target imaging distance to achieve accurate prediction of imaging size and imaging distance.

[0093] Step S203: Adjust the projection state of the vehicle head-up display system for driving information according to the imaging size and imaging distance. For detailed explanation, please refer to the relevant descriptions in the above embodiments; they will not be repeated here.

[0094] The adjustment method for the vehicle head-up display system provided in this embodiment combines the spatial coordinates of the driver's various key parts with the imaging position coordinates of the HUD to determine the imaging size and imaging distance suitable for the current driver. This allows for dynamic adjustment of the HUD's imaging parameters based on the actual situation of different drivers in the vehicle, in order to achieve the best imaging effect.

[0095] This embodiment provides a method for adjusting an in-vehicle head-up display system, which can be used for in-vehicle devices such as in-vehicle head-up display systems installed in vehicles. Figure 3 This is a flowchart of an adjustment method for an in-vehicle head-up display system according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps:

[0096] Step S301: Obtain the driver's driving posture information.

[0097] Specifically, step S301 includes:

[0098] Step S3011: Detect at least one driving position of the driver.

[0099] The driving position refers to the driver's location inside the vehicle, which can be detected and obtained through multiple sensors installed in the image acquisition unit. Specifically, when the driver enters the vehicle, the HUD in the vehicle can be activated to show the driver's current driving position.

[0100] It should be noted that the HUD can be activated automatically after the vehicle is detected to be starting, or it can be activated in response to a driver's trigger operation. There is no limitation on the activation method here.

[0101] Step S3012: Collect pose information corresponding to at least one driving position, integrate the pose information to generate driving pose information.

[0102] Different driving positions correspond to different pose information. HUD can integrate at least one pose information it acquires to obtain more comprehensive driving pose information, so as to more accurately adjust the imaging size and imaging distance of the HUD virtual image.

[0103] Step S302: Based on the driver's posture information, determine the imaging size and imaging distance of the vehicle head-up display system. For detailed explanation, please refer to the relevant descriptions in the above embodiments; they will not be repeated here.

[0104] Step S303: Adjust the projection state of the vehicle head-up display system for driving information according to the imaging size and imaging distance.

[0105] Specifically, step S303 includes:

[0106] Step S3031: Obtain the current projection status of driving information on the windshield of the actual vehicle.

[0107] The current projection state is the virtual image projection state formed based on driving information after the HUD is activated. Specifically, the current projection state is determined by combining the previous driving posture information. Since the driver adjusts their driving position to ensure driving comfort based on actual driving conditions, the driving posture information is not static. Whenever the driver's driving posture information changes, in order to ensure the best display effect of the virtual image, the HUD will recalculate the imaging size and imaging distance for the virtual image based on the current driving posture information.

[0108] In step S3032, the imaging size and imaging distance are sent to the adjustment system corresponding to the vehicle head-up display system, and the current projection state is dynamically adjusted by the adjustment system.

[0109] As mentioned above, the HUD has a corresponding adjustment system, which is used to dynamically adjust the current projection state of the virtual image so that the adjusted projection state can meet the virtual image projection for driving information, so as to obtain the best display effect for the current driving posture information.

[0110] The adjustment method for the vehicle head-up display system provided in this embodiment detects multiple driving positions for the driver and integrates the pose information corresponding to different driving positions. This yields the driver's pose information, facilitating subsequent adjustment of the imaging size and distance of the virtual image generated by the HUD based on different pose information, thus making the adjustment of the imaging size and distance more precise. By adjusting the projection state of the virtual image generated by the HUD through the imaging size and distance, the virtual image projected onto the windshield better meets the driver's observation of driving information, further improving vehicle driving safety.

[0111] This embodiment also provides an adjustment device for a vehicle head-up display system, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0112] This embodiment provides an adjustment device for a vehicle head-up display system, such as... Figure 4 As shown, it includes:

[0113] The acquisition module 401 is used to acquire the driver's driving posture information.

[0114] The imaging information determination module 402 is used to determine the imaging size and imaging distance of the vehicle head-up display system based on the driver's posture information.

[0115] The adjustment module 403 is used to adjust the projection state of the vehicle head-up display system for driving information according to the imaging size and imaging distance.

[0116] In some optional implementations, the imaging information determination module 402 described above may include:

[0117] The coordinate analysis unit is used to analyze driver posture information and determine the spatial coordinates of key parts corresponding to the driver.

[0118] The imaging position acquisition unit is used to acquire the imaging position coordinates of the vehicle head-up display system.

[0119] The imaging parameter determination unit is used to determine the imaging size and imaging distance based on the spatial coordinates of the key parts and the imaging position coordinates.

[0120] In some optional implementations, the coordinate analysis unit described above may include:

[0121] The body position determination subunit is used to determine the driver's body spatial position coordinates based on driving posture information.

[0122] The position analysis subunit is used to analyze the body's spatial position coordinates and determine the driver's head spatial position coordinates, forehead spatial position coordinates, and eye spatial position coordinates.

[0123] The first determining subunit is used to determine the spatial coordinates of key parts by using the spatial coordinates of the head, forehead, and eyes.

[0124] In some optional embodiments, the imaging parameter determination unit may include:

[0125] The coordinate transformation subunit is used to transform the spatial coordinates and imaging coordinates of key parts to the same coordinate system, and to determine the target head coordinates, target forehead coordinates, target eye coordinates and target imaging position coordinates in the same coordinate system.

[0126] The tilt angle determination subunit is used to determine the driver's body tilt angle based on the target eye coordinates.

[0127] The deflection angle determination subunit is used to determine the driver's head deflection angle based on the target imaging position coordinates and the target forehead coordinates.

[0128] The distance determination subunit is used to determine the target distance from the driver's head to the virtual image based on the target imaging position coordinates and the target head coordinates. The virtual image is generated by the projection of the vehicle display system.

[0129] The imaging parameter determination subunit is used to input the body tilt angle, head deflection angle, and target distance into the preset imaging adjustment model, and output the imaging size and imaging distance through the preset imaging adjustment model. The preset imaging adjustment model is pre-trained based on a deep learning algorithm.

[0130] In some optional embodiments, the imaging parameter determination unit may further include:

[0131] The training subunit is used to train a preset imaging adjustment model based on deep learning algorithms.

[0132] In some optional implementations, the training subunit described above may specifically be used to: detect whether the imaging function of the vehicle head-up display system is activated for the first time; when the imaging function of the vehicle head-up display system is activated for the first time, obtain the driver's pose reference value; based on the pose reference value, determine the imaging size calibration value and imaging distance calibration value of the vehicle head-up display system; in response to the adjustment operation of the imaging size calibration value and imaging distance calibration value, determine the adjusted target imaging size and target imaging distance; and based on the pose reference value, target imaging size, and target imaging distance, use a deep learning algorithm to iteratively train a preset imaging adjustment model.

[0133] In some optional implementations, the acquisition module 401 described above may include:

[0134] A position detection unit is used to detect at least one driving position of the driver.

[0135] The pose information generation unit is used to collect pose information corresponding to at least one driving position, integrate the pose information, and generate driving pose information.

[0136] In some alternative implementations, the adjustment module 403 may include:

[0137] The projection state acquisition unit is used to acquire the current projection state of driving information on the windshield of the actual vehicle.

[0138] The projection state adjustment unit is used to send the imaging size and imaging distance to the adjustment system corresponding to the vehicle head-up display system, and dynamically adjust the current projection state through the adjustment system.

[0139] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0140] In this embodiment, the adjustment device of the vehicle head-up display system is presented in the form of a functional unit. Here, a unit refers to an ASIC circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0141] The adjustment device for the vehicle head-up display system provided in this embodiment detects the driver's driving posture information and calculates the imaging size and imaging distance of the virtual image generated by the HUD on the windshield in real time based on the detected driving posture information. Then, it dynamically adjusts the state of the vehicle head-up display system projecting driving information on the windshield according to the imaging size and imaging distance, so that the projection state of the virtual image generated for the driving information meets the current actual situation of the driver, realizing adaptive dynamic adjustment of the HUD imaging effect and ensuring the best HUD display effect to the greatest extent.

[0142] This invention also provides a vehicle-mounted device having the above-described features. Figure 4 The adjustment device for the vehicle head-up display system shown.

[0143] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a vehicle-mounted device provided in an optional embodiment of the present invention, such as... Figure 5 As shown, the in-vehicle device includes one or more processors 10, memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the in-vehicle device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). Figure 5 Take a processor 10 as an example.

[0144] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0145] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0146] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the in-vehicle device, etc. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0147] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0148] The on-board equipment also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0149] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0150] The vehicle-mounted device also includes a communication interface for data communication between the vehicle-mounted device and other devices or communication networks.

[0151] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0152] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for adjusting a vehicle head-up display system, characterized in that, The method includes: Obtain the driver's driving posture information; Based on the driver's posture information, the imaging size and imaging distance of the vehicle head-up display system are determined; Adjust the projection state of the vehicle head-up display system for driving information according to the imaging size and the imaging distance; The step of determining the imaging size and imaging distance of the in-vehicle head-up display system based on the driver's posture information includes: Analyzing the driving posture information to determine the spatial coordinates of key parts corresponding to the driver includes: determining the driver's body spatial coordinates based on the driving posture information; analyzing the body spatial coordinates to determine the driver's head spatial coordinates, forehead spatial coordinates, and eye spatial coordinates; and using the head spatial coordinates, forehead spatial coordinates, and eye spatial coordinates to determine the spatial coordinates of the key parts. Obtain the imaging position coordinates of the vehicle head-up display system; Determining the imaging size and imaging distance based on the spatial coordinates of the key components and the imaging position coordinates includes: The spatial coordinates of the key parts and the imaging coordinates are transformed to the same coordinate system to determine the target head coordinates, target forehead coordinates, target eye coordinates, and target imaging coordinates in the same coordinate system. Based on the target eye coordinates, the driver's body tilt angle is determined. The body tilt angle is determined according to the horizontal angle between the vertical height coordinates of the driver's eyes. The vertical height coordinates of the driver's eyes are determined according to the target eye coordinates. Based on the target imaging position coordinates and the target forehead coordinates, the driver's head deflection angle is determined, and the head deflection angle is determined according to the horizontal angle between the target forehead coordinates and the target imaging position coordinates; Based on the target imaging position coordinates and the target head coordinates, the target distance from the driver's head to the virtual image is determined, wherein the virtual image is generated by the projection of the vehicle display system; The body tilt angle, the head deflection angle, and the target distance are input into a preset imaging adjustment model, and the imaging size and the imaging distance are output through the preset imaging adjustment model. The preset imaging adjustment model is obtained by pre-training based on a deep learning algorithm.

2. The adjustment method for the vehicle head-up display system according to claim 1, characterized in that, Training the preset imaging adjustment model based on a deep learning algorithm includes: Detect whether the imaging function of the vehicle head-up display system is activated for the first time; When the imaging function of the vehicle head-up display system is activated for the first time, the driver's positional reference value is obtained; Based on the pose reference value, determine the imaging size calibration value and imaging distance calibration value of the vehicle head-up display system; In response to the adjustment operation of the imaging size calibration value and the imaging distance calibration value, the adjusted target imaging size and target imaging distance are determined; Based on the pose reference value, the target imaging size, and the target imaging distance, the preset imaging adjustment model is iteratively trained using the deep learning algorithm.

3. The adjustment method for the vehicle head-up display system according to any one of claims 1-2, characterized in that, The acquisition of the driver's driving posture information includes: Detect at least one driving position of the driver; The pose information corresponding to at least one driving position is collected, and the pose information is integrated to generate the driving pose information.

4. The adjustment method for the vehicle head-up display system according to any one of claims 1-2, characterized in that, Adjusting the projection state of the vehicle head-up display system for driving information according to the imaging size and the imaging distance includes: Obtain the current projection status of the driving information on the windshield of the actual vehicle; The imaging size and imaging distance are sent to the adjustment system corresponding to the vehicle head-up display system, and the current projection state is dynamically adjusted by the adjustment system.

5. An adjustment device for a vehicle head-up display system, characterized in that, The device includes: The acquisition module is used to acquire the driver's driving posture information; The imaging information determination module is used to determine the imaging size and imaging distance of the vehicle head-up display system based on the driver's posture information. An adjustment module is used to adjust the projection state of the vehicle head-up display system for driving information according to the imaging size and the imaging distance; The step of determining the imaging size and imaging distance of the in-vehicle head-up display system based on the driver's posture information includes: Analyzing the driving posture information to determine the spatial coordinates of key parts corresponding to the driver includes: determining the driver's body spatial coordinates based on the driving posture information; analyzing the body spatial coordinates to determine the driver's head spatial coordinates, forehead spatial coordinates, and eye spatial coordinates; and using the head spatial coordinates, forehead spatial coordinates, and eye spatial coordinates to determine the spatial coordinates of the key parts. Obtain the imaging position coordinates of the vehicle head-up display system; Determining the imaging size and imaging distance based on the spatial coordinates of the key components and the imaging position coordinates includes: The spatial coordinates of the key parts and the imaging coordinates are transformed to the same coordinate system to determine the target head coordinates, target forehead coordinates, target eye coordinates, and target imaging coordinates in the same coordinate system. Based on the target eye coordinates, the driver's body tilt angle is determined. The body tilt angle is determined according to the horizontal angle between the vertical height coordinates of the driver's eyes. The vertical height coordinates of the driver's eyes are determined according to the target eye coordinates. Based on the target imaging position coordinates and the target forehead coordinates, the driver's head deflection angle is determined, and the head deflection angle is determined according to the horizontal angle between the target forehead coordinates and the target imaging position coordinates; Based on the target imaging position coordinates and the target head coordinates, the target distance from the driver's head to the virtual image is determined, wherein the virtual image is generated by the projection of the vehicle display system; The body tilt angle, the head deflection angle, and the target distance are input into a preset imaging adjustment model, and the imaging size and the imaging distance are output through the preset imaging adjustment model. The preset imaging adjustment model is obtained by pre-training based on a deep learning algorithm.

6. A vehicle-mounted display device, characterized in that, include: The system includes a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the adjustment method of the vehicle head-up display system according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the adjustment method of the vehicle head-up display system according to any one of claims 1 to 4.

Images