CN109993713A - Image distortion correction method and device for vehicle head-up display system - Google Patents

Abstract

The application proposes a kind of vehicle-mounted head-up display system pattern distortion antidote and device, wherein method includes: to obtain image to be projected；Correction process is carried out to the image to be projected using preset correction model, the image to be projected after being corrected；The image input vehicle-mounted head-up display system of target to be projected after correction is carried out projection to show, wherein preset correction model is to generate using training dataset corresponding with the vehicle-mounted head-up display system of target and the vehicle-mounted head-up display system training of target.This method is before carrying out Projection Display to image, correction process is carried out to image first with correction model, Projection Display is carried out to vehicle-mounted head-up display system is inputted again after image flame detection processing, distortion correction is carried out using correction model, compared to by way of increasing optical element, design difficulty is low and at low cost.

Description

Image distortion correction method and device for vehicle head-up display system

technical field

The present application relates to the field of display technology, and in particular, to a method and device for correcting image distortion of a vehicle head-up display system.

Background technique

With the development of technology, more and more head-up display devices are used in vehicles, which has gradually developed into a trend. A head-up display device on a vehicle projects an image in front of the vehicle through the vehicle's front windshield. Since the windshield is an irregular curved surface, the image projected through the windshield to the outside of the vehicle will produce distortion and phase difference, resulting in poor display quality of the image.

At present, optical methods are often used for correction, such as adding a non-continuous curved mirror or other optical elements before the windshield to correct the degradation of the imaging effect caused by the windshield. However, this correction method requires different optical elements to be designed for different windshields, which is not only difficult to design, but also increases the cost of the vehicle.

SUMMARY OF THE INVENTION

The present application proposes a method and device for correcting image distortion of a vehicle head-up display system, which are used to solve the problems of high design difficulty and high cost in the related art method for performing distortion correction by adding optical elements.

An embodiment of the present application provides an image distortion correction method for a vehicle head-up display system, including:

Get the image to be projected;

Using a preset correction model to perform correction processing on the image to be projected to obtain a corrected image to be projected;

Input the corrected image to be projected into the target vehicle head-up display system for projection display, wherein the preset correction model is to use the training data set corresponding to the target vehicle head-up display system and the target vehicle head-up display system. Display system training generated.

The method for correcting the image distortion of the vehicle head-up display system according to the embodiment of the present application, by acquiring the image to be projected, using a preset correction model to correct the image to be projected, to obtain the corrected image to be projected, and correcting the projected image to be projected. The image is input to the target vehicle head-up display system for projection display, wherein the preset correction model is generated using the training data set corresponding to the target vehicle head-up display system and the target vehicle head-up display system. Therefore, before the image is projected and displayed, the correction model is used to correct the image, and the image is corrected and then input to the vehicle head-up display system for projection display, and the correction model is used for distortion correction. way, the design difficulty is low, and the cost is low.

Another embodiment of the present application provides an image distortion correction device for a vehicle head-up display system, including:

a first acquisition module, used for acquiring the image to be projected;

a correction module, configured to perform correction processing on the image to be projected by using a preset correction model to obtain a corrected image to be projected;

The display module is used to input the corrected image to be projected into the target vehicle head-up display system for projection display, wherein the preset correction model is to use the training data set corresponding to the target vehicle head-up display system and the The target vehicle head-up display system is trained and generated.

The device for correcting the image distortion of the vehicle head-up display system according to the embodiment of the present application obtains the image to be projected, uses a preset correction model to perform correction processing on the image to be projected, and obtains the corrected image to be projected. The image is input to the target vehicle head-up display system for projection display, wherein the preset correction model is generated using the training data set corresponding to the target vehicle head-up display system and the target vehicle head-up display system. Therefore, before the image is projected and displayed, the correction model is used to correct the image, and then the image is corrected and then input to the vehicle head-up display system for projection display, and the correction model is used for distortion correction. Compared with the method of adding optical elements , low design difficulty and low cost.

Another embodiment of the present application provides a computer device, including a processor and a memory;

Wherein, the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to realize the image of the vehicle head-up display system according to the embodiment of the above aspect Distortion correction method.

Another embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the image distortion correction method of the vehicle head-up display system according to the above-mentioned embodiment of the first aspect.

Additional aspects and advantages of the present application will be set forth, in part, in the following description, and in part will be apparent from the following description, or learned by practice of the present application.

Description of drawings

The above and/or additional aspects and advantages of the present application will become apparent and readily understood from the following description of embodiments taken in conjunction with the accompanying drawings, wherein:

1 is a schematic flowchart of an image distortion correction method for a vehicle head-up display system provided by an embodiment of the present application;

FIG. 2 is a schematic flowchart of another method for correcting image distortion of a vehicle head-up display system according to an embodiment of the present application;

3 is a schematic flowchart of another method for correcting image distortion of a vehicle head-up display system according to an embodiment of the present application;

4 is a schematic structural diagram of an image distortion correction device for a vehicle head-up display system provided by an embodiment of the present application;

Figure 5 shows a block diagram of an exemplary computer device suitable for use in implementing embodiments of the present application.

Detailed ways

The following describes in detail the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary, and are intended to be used to explain the present application, but should not be construed as a limitation to the present application.

The following describes the image distortion correction method and device of the vehicle head-up display system according to the embodiments of the present application with reference to the accompanying drawings.

In the embodiments of the present application, in view of the problems of high design difficulty and high cost in the method of performing distortion correction by adding optical elements in the related art, an image distortion correction method for a vehicle head-up display system is proposed.

FIG. 1 is a schematic flowchart of a method for correcting image distortion of a vehicle head-up display system according to an embodiment of the present application.

The image distortion correction method of the vehicle head-up display system of the embodiment of the present application can be performed by the image distortion correction device of the vehicle head-up display system provided by the embodiment of the present application, and the device can be configured in a computer device to treat the image distortion by using a preset correction model. The projected image is corrected and then projected and displayed, so as to realize the distortion correction of the projected image.

As shown in Figure 1, the image distortion correction method of the vehicle head-up display system includes:

Step 101: Acquire an image to be projected.

In this embodiment, the vehicle head-up display system installed on the vehicle can project and display a video such as a film or an image, and the image to be projected can be a video frame image or a single image.

Step 102 , using a preset correction model to perform correction processing on the image to be projected, to obtain a corrected image to be projected.

The preset correction model is generated by using the training data set corresponding to the target vehicle head-up display system and the training of the target vehicle head-up display system, and is used to perform correction processing on the image, so that the corrected image is distorted. Among them, the training dataset contains a large number of images.

After the image to be projected is acquired, a preset correction model is used to perform correction processing on the image to be projected to obtain a corrected image to be projected. Here, the corrected image to be projected is a distorted image.

Step 103: Input the corrected image to be projected into the target vehicle head-up display system for projection display.

After the corrected image to be projected is acquired, the corrected image to be projected is input into the target vehicle head-up display system for projection display. After passing through the front windshield, the projected and displayed image has little or no distortion, thereby greatly improving the projection display quality.

When the video is projected and displayed, a preset correction model can be used to perform correction processing on each frame of image, and after the correction processing, it is input into the target vehicle head-up display system for projection display. As a result, when the user watches the video, the projected and displayed picture has little or no distortion, which improves the user's viewing experience.

Under normal circumstances, if the image to be projected is directly input into the target vehicle head-up display system, the projection display will distort the image due to the effect of the windshield. In this embodiment, the image to be projected is subjected to a preset correction model for correction processing, so that the corrected image is distorted. When the corrected image to be projected is input to the target vehicle head-up display system and projected onto the windshield, after the corrected image is distorted by the windshield, the final projected image is displayed normally.

In the related art, a discontinuous curved mirror or other optical elements are usually added before the windshield to compensate for the decrease in the imaging effect caused by the windshield. However, adding optical elements is not only difficult to design, but also high in cost. The volume of the display system is also relatively large.

However, in the embodiment of the present application, when the target vehicle head-up display system is used to project and display the image to be projected, the image to be projected is first corrected by the correction model, and then the corrected image to be projected is projected and displayed, thus, Using the correction model to correct the distortion has lower cost, reduces the volume of the vehicle head-up display system, and does not need to consider the parameters of the front windshield.

Before using the preset correction model to correct the image to be projected, the preset correction model may be obtained through deep learning. The following description will be made with reference to FIG. 2 , which is a schematic flowchart of another image distortion correction method for a vehicle head-up display system provided by an embodiment of the present application.

Before using the preset correction model to correct the image to be projected, as shown in FIG. 2 , the image distortion correction method of the vehicle head-up display system further includes:

Step 201: Acquire a training data set corresponding to the target vehicle head-up display system, wherein the training data set includes an input image set.

Among them, the training dataset contains an input image set, and the input image set contains a large number of images. When acquiring a training data set, a large number of images can be collected, which make up the input image set, or a video can be used as the input image set, and each frame of the image in the video is an image in the input image set.

Step 202, using the target vehicle head-up display system to project and display each input image in the input image set in turn, and collect the output image corresponding to each input image.

In this embodiment, when the target vehicle head-up display system is projected, the position of the human eye of the person viewing the projected image can be recorded, and then an image acquisition device, such as a camera, can be placed at the position of the human eye when viewing the projected image.

In the process of projecting and displaying each input image in the target vehicle head-up display system in turn, the projected image corresponding to each input image is captured by the image acquisition device placed at the position of the human eye. Here, each input image corresponds to The projected image is called the output image.

It can be understood that the output image of each input image is a distorted image.

Step 203: Perform deep learning on each input image and the corresponding output image to determine an image processing model corresponding to the target vehicle head-up display system.

After obtaining the output image corresponding to each input image in the input image set, each input image and its corresponding output image can be used to obtain the image processing model corresponding to the target vehicle head-up display system through deep learning. Among them, the image processing model can be used to determine the relationship between the input image and the output image.

Specifically, the input images in the input image set are used as training samples, and the image processing model is obtained by performing deep learning on the initial image processing model. In the training iteration process, the loss function is calculated according to the image predicted by the model and the output image actually corresponding to the input image, and the model parameters are adjusted according to the calculation result until the training is completed.

Step 204: Determine a reference image corresponding to each input image according to the image processing model and each input image.

In this embodiment, each output image is an image projected and displayed by each input image, the relationship between the input image and the output image can be determined according to the image processing model, and each output image is an image with distortion. Then, in order to make the input image projected by the vehicle head-up display system without distortion, the input of the image processing model can be determined according to the image processing model and each input image, then the input of the determined image processing model here is called the reference. image.

For example, P1 represents the input image, P2 represents the output image corresponding to the input image P1, _C1 represents the image processing model, and the relationship between the input image and the corresponding output image can be expressed as P2= _C1 (P1). Then, to make the projected image to be displayed as P1, that is, to make the projected image displayed normally, then the modulo P1=C ₁ (P0), where P0 is the reference image. Thus, in the case where the image P1 and the image processing model _C1 have been input, the reference image can be determined from P1 and _C1 .

Step 205: Perform deep learning on the reference image and the input image corresponding to each input image to determine a preset correction model.

In this embodiment, it can be considered that when the image to be displayed is a reference image, the image projected and displayed through the front windshield is a normal image. Therefore, in order to enable the image to be displayed to be projected and displayed normally, certain processing should be performed on the image to be displayed, so that the image to be displayed can be displayed normally.

After acquiring each input image and its corresponding reference image, the input image can be used to train the initial correction model to obtain the correction model corresponding to the target vehicle head-up display system. In the training iteration process, the loss function is calculated according to the image predicted by the initial correction model and the reference image actually corresponding to the input image, and the model parameters are adjusted according to the calculation result until the training is completed.

Since the hardware parameters of the front windshield of each vehicle and the on-board head-up display system may not be completely consistent, for different vehicles, the correction model corresponding to the on-board head-up display system of each vehicle can be obtained by using the above method.

In practical applications, the resolution of the image capture device used to capture the output image may not be the same as the resolution of the input image. When the resolutions are inconsistent, the resolution of the collected output image will be inconsistent with that of the input image. Therefore, the image processing model determined according to the input image and the output image will be inaccurate, resulting in an inaccurate correction model.

Therefore, before deep learning is performed on each input image and the corresponding output image, and the image processing model corresponding to the target vehicle head-up display system is determined, the first resolution of the image acquisition device and the second resolution of the input image can be determined first. Consistent. When it is determined that the resolution of the input image is consistent with that of the image acquisition device, the resolution of the output image collected by the image acquisition device is consistent with the input image, and deep learning is performed on each input image and output image to obtain an image processing model.

In the embodiment of the present application, before deep learning is performed on each input image and its corresponding output image, it is determined that the resolution of the image acquisition device is consistent with that of the input image, and when the resolution is determined to be consistent, the input image and corresponding Deep learning of the output image can ensure the accuracy of the correction model.

In practical applications, the resolution of the input image may be inconsistent with the resolution of the image acquisition device. The following describes how to determine the correction model when the resolutions are inconsistent with reference to FIG. 3 . FIG. 3 is a schematic flowchart of another method for correcting image distortion of a vehicle head-up display system according to an embodiment of the present application.

Before using the preset correction model to correct the image to be projected, as shown in FIG. 3 , the image distortion correction method of the vehicle head-up display system further includes:

Step 301: Acquire a training data set corresponding to the target vehicle head-up display system, wherein the training data set includes an input image set.

Step 302 , using the target vehicle head-up display system to project and display each input image in the input image set in turn, and collect the output image corresponding to each input image.

In this embodiment, steps 301 to 302 are similar to the above-mentioned steps 201 to 202, and thus are not repeated here.

Step 303: Determine a scaling matrix between each output image and the corresponding input image according to the first resolution of the image acquisition device and the second resolution corresponding to the input image.

Because if the resolution of the image capture device is inconsistent with the resolution of the input image, the resolution corresponding to the output image captured by the image capture device is inconsistent with the resolution corresponding to the input image. Performing deep learning on images will result in lower accuracy of the resulting image processing model.

In order to ensure the accuracy of the image processing model, in this embodiment, when the first resolution of the image acquisition device is inconsistent with the second resolution corresponding to the input image, according to the first resolution of the image acquisition device and the corresponding The second resolution of , determines the scaling matrix between each output image and the corresponding input image.

For example, the input image is P1, the output image corresponding to the input image P1 is P2, the scaling matrix between P1 and P2 is M, and the relationship between P1 and P2 can be expressed as P2=M*P1.

Since the resolution between the input images in the input image set may or may not be the same. Therefore, a scaling matrix between each input image in the input image set and the corresponding output image is determined. It can be understood that the scaling matrices corresponding to each pair of input images and output images may or may not be the same.

Step 304: Perform scaling processing on each input image according to the scaling matrix between each output image and the corresponding input image to obtain a scaled image.

In this embodiment, scaling processing is performed on each input image according to the scaling matrix between each output image and the corresponding input image, and a scaled image of each input image can be obtained. The resolution of the scaled image corresponding to each input image is consistent with the resolution of the image acquisition device.

For example, if the resolution corresponding to the input image is greater than the resolution of the image acquisition device, then the input image is scaled by using the scaling matrix, and the resolution of the obtained scaled image is consistent with the resolution of the image acquisition device. Thus, the resolution of the output image captured by the image capturing device is consistent with the resolution of the zoomed image.

Step 305: Perform deep learning on each zoomed image and the corresponding output image to determine an image processing model corresponding to the target vehicle head-up display system.

In this embodiment, each zoomed image has the same resolution as the corresponding output image, and deep learning is performed on each zoomed image and the corresponding output image to obtain an image processing model corresponding to the target vehicle head-up display system. The specific process is the same as the process of performing deep learning on the input image and the output image described in the foregoing embodiment, and details are not repeated here.

Step 306: Determine a reference image corresponding to each input image according to the image processing model and each input image.

Step 307: Perform deep learning on the reference image and the input image corresponding to each input image to determine a preset correction model.

In this embodiment, steps 306 to 307 are similar to the above-mentioned steps 204 to 205, and thus are not repeated here.

In this embodiment of the present application, when the first resolution of the image capture device is inconsistent with the second resolution corresponding to the input image, firstly determine each of the first resolutions of the image capture device and the second resolution corresponding to the input image The scaling matrix between the output image and the corresponding input image, the scaling matrix is used to scale each input image, and each scaled image obtained by the scaling process and the corresponding output image are used to obtain an image processing model, thus ensuring image processing. The accuracy of the model and the accuracy of the corrected model.

In practical applications, the training data set corresponding to the target vehicle head-up display system can be obtained through collection. In order to improve efficiency, in an embodiment of the present application, a preset image generation function can also be used to generate the target vehicle head-up display system. the corresponding training dataset.

Since each input image and output image can be regarded as a matrix, each element value in the matrix corresponds to the gray value of each pixel in the image, then the image generation function can be used to generate an image, and the generated image can be used as input images in the image set.

During specific implementation, the number of images to be generated, the size of the image, the value of pixel points in the image, etc. can be set through the parameters in the image generation function. Thus, using the image generation function, the training dataset can be quickly acquired.

In order to improve the accuracy of the image processing model, after using each input image and the corresponding output image to obtain the image processing model, a plurality of newly generated input images and corresponding output images can be used to perform the training on the image processing model. Test, calculate the accuracy according to the image predicted by the model and the actual output image, and judge whether the accuracy of the image processing model is greater than the threshold.

When the accuracy of the image processing model is less than or equal to the threshold, it can be considered that the accuracy of the image processing model does not meet the requirements, then the preset image generation function can be adjusted to generate a new training data set to utilize the new training data set to continue training the image processing model.

When adjusting the preset image generation function, the value and/or the number of elements included in the preset image generation function may be adjusted. The value may refer to the number of generated images, or may be the value of pixels in the image.

During specific implementation, both the value and the included quantity of the preset image generation function may be adjusted, and the value or included quantity may also be adjusted. When adjusting, it can be realized by changing the value of the parameter corresponding to the value and/or the included quantity.

When the accuracy of the image processing model is greater than the threshold, it can be considered that the accuracy of the image processing model meets the requirements, then the image processing model and each input image can be directly used to obtain the reference image corresponding to each input image, and then use the input image With the reference image, obtain the rectified model.

In the embodiment of the present application, by judging whether the accuracy of the image processing model is greater than the threshold, when the accuracy does not meet the requirements, a new training data set is obtained by adjusting the preset image generation function, and the new training data set is used. Continuing to train the image processing model can improve the accuracy of the image processing model, thereby improving the accuracy of the correction model.

In order to realize the above embodiments, the embodiments of the present application also propose an image distortion correction device for a vehicle head-up display system. FIG. 4 is a schematic structural diagram of an image distortion correction device for a vehicle head-up display system according to an embodiment of the present application.

As shown in FIG. 4 , the image distortion correction device of the vehicle head-up display system includes: a first acquisition module 410 , a correction module 420 , and a display module 430 .

The first acquisition module 410 is used to acquire the image to be projected;

The correction module 420 is configured to perform correction processing on the image to be projected by using a preset correction model to obtain a corrected image to be projected;

The display module 430 is used to input the corrected image to be projected into the target vehicle head-up display system for projection display, wherein the preset correction model is to use the training data set corresponding to the target vehicle head-up display system and the target vehicle head-up display system. Display system training generated.

In a possible implementation manner of the embodiment of the present application, the apparatus may further include:

The second acquisition module is used to acquire a training data set corresponding to the target vehicle head-up display system, wherein the training data set includes an input image set;

The acquisition module is used for sequentially projecting and displaying each input image in the input image set by using the target vehicle head-up display system, and collecting the output image corresponding to each input image;

The first determination module is used to perform deep learning on each input image and the corresponding output image, and determine the image processing model corresponding to the target vehicle head-up display system;

The second determination module is used to determine the reference image corresponding to each input image according to the image processing model and each input image;

The third determination module is configured to perform deep learning on the reference image and the input image corresponding to each input image to determine a preset correction model.

In a possible implementation manner of the embodiment of the present application, the above-mentioned acquisition module is specifically configured to: use an image acquisition device to acquire an output image corresponding to each input image;

The device may also include:

The fourth determination module is configured to determine that the first resolution of the image acquisition device is consistent with the second resolution corresponding to the input image.

In a possible implementation manner of the embodiment of the present application, if the first resolution of the image acquisition device is different from the second resolution corresponding to the input image, the apparatus may further include:

a fifth determination module, configured to determine a scaling matrix between each output image and the corresponding input image according to the first resolution of the image acquisition device and the second resolution corresponding to the input image;

The above-mentioned first determination module is specifically used for:

Perform scaling processing on each input image according to the scaling matrix between each output image and the corresponding input image to obtain a scaled image;

Perform deep learning on each zoomed image and the corresponding output image to determine the image processing model corresponding to the target vehicle head-up display system.

In a possible implementation manner of the embodiment of the present application, the above-mentioned second acquisition module is specifically used for:

Use the preset image generation function to generate the training data set corresponding to the target vehicle head-up display system;

The device may also include:

The judgment module is used to judge whether the accuracy of the image processing model is greater than the threshold;

The generation module is used to adjust the preset image generation function to generate a new training data set when the accuracy of the image processing model is less than or equal to the threshold.

In a possible implementation manner of the embodiment of the present application, the above generation module is specifically used for:

Adjust the value of the preset image generation function and/or the number of elements it contains.

It should be noted that the above explanation of the embodiment of the image distortion correction method of the vehicle head-up display system is also applicable to the image distortion correction device of the vehicle head-up display system of this embodiment, so it is not repeated here.

The device for correcting the image distortion of the vehicle head-up display system according to the embodiment of the present application obtains the image to be projected, uses a preset correction model to perform correction processing on the image to be projected, and obtains the corrected image to be projected. The image is input to the target vehicle head-up display system for projection display, wherein the preset correction model is generated using the training data set corresponding to the target vehicle head-up display system and the target vehicle head-up display system. Therefore, before the image is projected and displayed, the correction model is used to correct the image, and then the image is corrected and then input to the vehicle head-up display system for projection display, and the correction model is used for distortion correction. Compared with the method of adding optical elements , low design difficulty and low cost.

In order to implement the above embodiments, the embodiments of the present application further provide a computer device, including a processor and a memory;

Wherein, the processor runs the program corresponding to the executable program code by reading the executable program code stored in the memory, so as to realize the image distortion correction method of the vehicle head-up display system according to the above embodiment.

Figure 5 shows a block diagram of an exemplary computer device suitable for use in implementing embodiments of the present application. The computer device 12 shown in FIG. 5 is only an example, and should not impose any limitations on the functions and scope of use of the embodiments of the present application.

As shown in FIG. 5, computer device 12 takes the form of a general-purpose computing device. Components of computer device 12 may include, but are not limited to, one or more processors or processing units 16 , system memory 28 , and a bus 18 connecting various system components including system memory 28 and processing unit 16 .

Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of a variety of bus structures. For example, these architectures include, but are not limited to, Industry Standard Architecture (hereinafter referred to as: ISA) bus, Micro Channel Architecture (hereinafter referred to as: MAC) bus, enhanced ISA bus, video electronic standard Association (Video Electronics Standards Association; hereinafter referred to as: VESA) local bus and Peripheral Component Interconnection (Peripheral Component Interconnection; hereinafter referred to as: PCI) bus.

Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including both volatile and nonvolatile media, removable and non-removable media.

The memory 28 may include a computer system readable medium in the form of a volatile memory, such as a random access memory (Random Access Memory; hereinafter referred to as: RAM) 30 and/or a cache memory 32 . Computer device 12 may further include other removable/non-removable, volatile/non-volatile computer system storage media. For example only, storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 5, commonly referred to as a "hard disk drive"). Although not shown in FIG. 5, a magnetic disk drive for reading and writing to removable non-volatile magnetic disks (eg, "floppy disks") and removable non-volatile optical disks (eg, compact disk read only memory) may be provided. Disc Read OnlyMemory; hereinafter referred to as: CD-ROM), Digital Video Disc Read Only Memory (hereinafter referred to as: DVD-ROM) or other optical media) read and write optical disc drives. In these cases, each drive may be connected to bus 18 through one or more data media interfaces. Memory 28 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of various embodiments of the present application.

A program/utility 40 having a set (at least one) of program modules 42, which may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data , each or some combination of these examples may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the embodiments described herein.

Computer device 12 may also communicate with one or more external devices 14 (eg, keyboard, pointing device, display 24, etc.), may also communicate with one or more devices that enable a user to interact with computer device 12, and/or communicate with Any device (eg, network card, modem, etc.) that enables the computer device 12 to communicate with one or more other computing devices. Such communication may take place through input/output (I/O) interface 22 . In addition, the computer device 12 can also communicate with one or more networks (eg, Local Area Network (hereinafter referred to as: LAN), Wide Area Network (hereinafter referred to as: WAN) and/or public network, such as the Internet through the network adapter 20 ) ) communication. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18 . It should be understood that, although not shown, other hardware and/or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives and data backup storage systems.

The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28 , for example, implements the methods mentioned in the foregoing embodiments.

In order to realize the above-mentioned embodiments, the embodiments of the present application further propose a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, realizes the image distortion correction method of the vehicle head-up display system as described in the above-mentioned embodiments .

In the description of this specification, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implying the number of indicated technical features. Thus, a feature delimited with "first", "second" may expressly or implicitly include at least one of that feature. In the description of the present application, "plurality" means at least two, such as two, three, etc., unless expressly and specifically defined otherwise.

Any process or method description in the flowcharts or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing custom logical functions or steps of the process , and the scope of the preferred embodiments of the present application includes alternative implementations in which the functions may be performed out of the order shown or discussed, including performing the functions substantially concurrently or in the reverse order depending upon the functions involved, which should It is understood by those skilled in the art to which the embodiments of the present application belong.

The logic and/or steps represented in flowcharts or otherwise described herein, for example, may be considered an ordered listing of executable instructions for implementing the logical functions, may be embodied in any computer-readable medium, For use with, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch instructions from and execute instructions from an instruction execution system, apparatus, or apparatus) or equipment. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport the program for use by or in connection with an instruction execution system, apparatus, or apparatus. More specific examples (non-exhaustive list) of computer readable media include the following: electrical connections with one or more wiring (electronic devices), portable computer disk cartridges (magnetic devices), random access memory (RAM), Read Only Memory (ROM), Erasable Editable Read Only Memory (EPROM or Flash Memory), Fiber Optic Devices, and Portable Compact Disc Read Only Memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program may be printed, as the paper or other medium may be optically scanned, for example, followed by editing, interpretation, or other suitable medium as necessary process to obtain the program electronically and then store it in computer memory.

It should be understood that various parts of this application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented by any one of the following techniques known in the art, or a combination thereof: discrete with logic gates for implementing logic functions on data signals Logic circuits, application specific integrated circuits with suitable combinational logic gates, Programmable Gate Arrays (PGA), Field Programmable Gate Arrays (FPGA), etc.

Those skilled in the art can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium, and the program can be stored in a computer-readable storage medium. When executed, one or a combination of the steps of the method embodiment is included.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, and the like. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limitations to the present application. Embodiments are subject to variations, modifications, substitutions and variations.

Claims (14)

1. a kind of vehicle-mounted head-up display system pattern distortion antidote characterized by comprising

Obtain image to be projected；

Correction process is carried out to the image to be projected using preset correction model, the figure to be projected after being corrected Picture；

The image input vehicle-mounted head-up display system of target to be projected after the correction is carried out projection to show, wherein described Preset correction model is vehicle-mounted using training dataset corresponding with the vehicle-mounted head-up display system of the target and the target Head-up display system training generates.

2. the method as described in claim 1, which is characterized in that it is described using preset correction model to the figure to be projected Before progress correction process, further includes:

The corresponding training dataset of the vehicle-mounted head-up display system of the target is obtained, it includes input picture that wherein training data, which is concentrated, Collection；

It is projected using each input picture that the vehicle-mounted head-up display system of the target successively concentrates the input picture It has been shown that, acquires the corresponding output image of each input picture；

Deep learning is carried out to each input picture and corresponding output image, determines the vehicle-mounted head-up display system pair of the target The image processing model answered；

Model and each input picture are handled according to described image, determines the corresponding reference picture of each input picture；

Deep learning is carried out to the corresponding reference picture of each input picture and input picture, determines the preset correction mould Type.

3. method according to claim 2, which is characterized in that described to acquire the corresponding output image of each input picture, packet It includes:

The corresponding output image of each input picture is acquired using image capture device；

It is described that deep learning is carried out to each input picture and corresponding output image, determine the vehicle-mounted head-up display system of the target It unites before corresponding image processing model, further includes:

Determine that the first resolution second resolution corresponding with the input picture of described image acquisition equipment is consistent.

4. method as claimed in claim 3, which is characterized in that if described image acquisition equipment first resolution with it is described defeated It is different to enter the corresponding second resolution of image, then it is described that deep learning is carried out to each input picture and corresponding output image, Before determining the corresponding image processing model of the vehicle-mounted head-up display system of the target, further includes:

The first resolution and the corresponding second resolution of the input picture that equipment is acquired according to described image, determine each defeated Scaled matrix between image and corresponding input picture out；

It is described that deep learning is carried out to each input picture and corresponding output image, determine the vehicle-mounted head-up display system of the target It unites corresponding image processing model, comprising:

According to each output image between corresponding input picture scaled matrix, each input picture zoomed in and out into processing, Obtain zoomed image；

Deep learning is carried out to each zoomed image and corresponding output image, determines the vehicle-mounted head-up display system pair of the target The image processing model answered.

5. method according to claim 2, which is characterized in that the acquisition vehicle-mounted head-up display system of target is corresponding Training dataset, comprising:

Using preset image generating function, the corresponding training dataset of the vehicle-mounted head-up display system of the target is generated；

It is described that deep learning is carried out to each input picture and corresponding output image, determine the vehicle-mounted head-up display system of the target It unites after corresponding image processing model, further includes:

Judge whether the accuracy of described image processing model is greater than threshold value；

If it is not, being then adjusted to the preset image generating function, to generate new training dataset.

6. method as claimed in claim 5, which is characterized in that it is described that the preset image generating function is adjusted, Include:

Value to the preset image generating function and/or comprising number of elements be adjusted.

7. a kind of vehicle-mounted head-up display system pattern distortion apparatus for correcting characterized by comprising

First obtains module, for obtaining image to be projected；

Rectification module, for carrying out correction process to the image to be projected using preset correction model, after obtaining correction Image to be projected；

Display module, it is aobvious for the image input vehicle-mounted head-up display system of target to be projected after the correction to be carried out projection Show, wherein the preset correction model be using training dataset corresponding with the vehicle-mounted head-up display system of the target and What the vehicle-mounted head-up display system training of target generated.

8. device as claimed in claim 7, which is characterized in that further include:

Second obtains module, for obtaining the corresponding training dataset of the vehicle-mounted head-up display system of the target, wherein training number It include input picture collection according to concentrating；

Acquisition module, each input for successively being concentrated the input picture using the vehicle-mounted head-up display system of the target Image carries out projection and shows, acquires the corresponding output image of each input picture；

First determining module determines the target for carrying out deep learning to each input picture and corresponding output image The corresponding image processing model of vehicle-mounted head-up display system；

Second determining module determines that each input picture is corresponding for handling model and each input picture according to described image Reference picture；

Third determining module is determined for carrying out deep learning to the corresponding reference picture of each input picture and input picture The preset correction model.

9. device as claimed in claim 8, which is characterized in that the acquisition module is specifically used for: utilizing image capture device Acquire the corresponding output image of each input picture；

Described device further include:

4th determining module, for determining the first resolution corresponding with the input picture second of described image acquisition equipment Resolution ratio is consistent.

10. device as claimed in claim 9, which is characterized in that if described image acquisition equipment first resolution with it is described The corresponding second resolution of input picture is different, described device further include:

5th determining module, for acquiring the first resolution and the input picture corresponding second of equipment according to described image Resolution ratio determines each output image and the scaled matrix between corresponding input picture；

First determining module, is specifically used for:

According to each output image between corresponding input picture scaled matrix, each input picture zoomed in and out into processing, Obtain zoomed image；

Deep learning is carried out to each zoomed image and corresponding output image, determines the vehicle-mounted head-up display system pair of the target The image processing model answered.

11. device as claimed in claim 8, which is characterized in that described second obtains module, is specifically used for:

Using preset image generating function, the corresponding training dataset of the vehicle-mounted head-up display system of the target is generated；

Described device further include:

Judgment module, for judging whether the accuracy of described image processing model is greater than threshold value；

Generation module, when the accuracy for handling model when described image is less than or equal to threshold value, to the preset image Generating function is adjusted, to generate new training dataset.

12. device as claimed in claim 11, which is characterized in that the generation module is specifically used for:

Value to the preset image generating function and/or comprising number of elements be adjusted.

13. a kind of computer equipment, which is characterized in that including processor and memory；

Wherein, the processor is run by reading the executable program code stored in the memory can be performed with described The corresponding program of program code, with abnormal for realizing vehicle-mounted head-up display system image such as claimed in any one of claims 1 to 6 Become antidote.

14. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor Such as vehicle-mounted head-up display system pattern distortion antidote as claimed in any one of claims 1 to 6 is realized when execution.