WO2022142146A1

WO2022142146A1 - Image quality adjusting method, device, projector, and computer-readable storage medium

Info

Publication number: WO2022142146A1
Application number: PCT/CN2021/098979
Authority: WO
Inventors: 陈昌陶; 冉鹏; 王鑫
Original assignee: 成都极米科技股份有限公司
Priority date: 2020-12-31
Filing date: 2021-06-08
Publication date: 2022-07-07
Also published as: CN112804504A; CN112804504B

Abstract

Disclosed are an image quality adjusting method, a device, a projector, and a computer-readable storage medium. The image quality adjusting method is applicable in the projector. The projector comprises at least two front cameras and at least two rear cameras. The method comprises: determining position information of a projection point on the basis of projection images captured by front cameras, determining, on the basis of facial images captured by rear cameras, pupil center position information of the facial images, calculating, on the basis of the position information of the projection point, of a preset parameter, and of the pupil center position information, the distance from the center of an area of focus of the eyes to the projection point, where the area of focus of the eyes is an area of focus of the eyes in a projection screen, and employing a super-resolution image generating technique to adjust the display resolution of the area of focus of the eyes. The present invention implements the technical effects of increasing the image quality of the projector and allowing a user to acquire super-resolution visual experience.

Description

Image quality adjustment method, device, projector, and computer-readable storage medium

technical field

The present invention relates to the field of image processing, and in particular, to an image quality adjustment method, device, projector and computer-readable storage medium.

Background technique

Limited by network bandwidth, video resource resolution, and projector resolution, it is difficult for existing projectors to achieve 8K or higher resolution. Therefore, how to improve the projector's image quality so that users can obtain ultra-high resolution The high-rate visual experience is a problem that needs to be solved urgently.

SUMMARY OF THE INVENTION

The purpose of the embodiments of the present invention is to provide an image quality adjustment method, device, projector, and computer-readable storage medium, so as to improve the image quality of the projector and enable users to obtain an ultra-high-resolution visual experience.

In order to achieve the above purpose, the technical solutions adopted in the embodiments of the present invention are as follows:

In a first aspect, an embodiment of the present invention provides an image quality adjustment method, which is applied to a projector, where the projector includes at least two front cameras and at least two rear cameras, and the method includes: according to the front camera According to the projection image collected by the rear camera, the position information of the projection point is determined; according to the face image collected by the rear camera, the pupil center position information of the face image is determined; according to the position information of the projection point, preset parameters and the pupil center position information, calculate the distance from the center of the area of interest of the human eye to the projection point, wherein the area of interest of the human eye is the area that the human eye pays attention to in the projection screen; using super-resolution image generation technology, adjust The display resolution of the area of interest to the human eye.

In a second aspect, an embodiment of the present invention provides an image quality adjustment device, which is applied to a projector. The projector includes at least two front cameras and at least two rear cameras, and the device includes a determination module and a calculation module. , Adjust the module. Wherein, the determining module is used to determine the position information of the projection point according to the projection image collected by the front camera, and also used to determine the center position of the pupil of the face image according to the face image collected by the rear camera information; a calculation module for calculating the distance from the center of the area of interest of the human eye to the projection point according to the position information of the projection point, the preset parameters and the position information of the pupil center, wherein the area of interest of the human eye is is the area that the human eye pays attention to in the projection screen; the adjustment module is used to adjust the display resolution of the area of interest to the human eye by adopting the super-resolution image generation technology.

In a third aspect, an embodiment of the present invention further provides a projector, the projector includes: a front camera, a rear camera, a processor and a memory; the memory is used to store a program, when the program is processed by the process When the processor is executed, the processor is made to implement the image quality adjustment method described in the first aspect.

In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the image described in the first aspect is implemented. quality adjustment method.

Compared with the prior art, the embodiments of the present invention provide an image quality adjustment method, device, projector and computer-readable storage medium. First, the position information of the projection point is determined according to the projection image collected by the front camera, and then the position information of the projection point is determined. , according to the face image collected by the rear camera, determine the pupil center position information of the face image, and then calculate the attention of the human eye according to the position information of the projection point, the preset parameters and the pupil center position information The distance from the center of the area to the projection point, and finally, the super-resolution image generation technology is used to adjust the display resolution of the area of interest to the human eye. That is, the position of the center of the area of interest of the human eye is determined by the distance from the center of the area of interest of the human eye to the projection point, thereby further determining the area of interest of the human eye, and by improving the resolution of the area of interest of the human eye, the projector can be improved. The high-quality picture quality enables users to obtain the technical effect of ultra-high-resolution visual experience.

Description of drawings

In order to illustrate the technical solutions of the present invention more clearly, the accompanying drawings required in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be It is regarded as the limitation of the protection scope of the present invention. In the various figures, similar components are numbered similarly.

FIG. 1 shows a schematic block diagram of the steps of the image quality adjustment method provided by the embodiment of the present application;

FIG. 2 shows a schematic block diagram of a sub-step flow of determining pupil center position information provided by an embodiment of the present application;

Fig. 3 shows the geometrical relationship diagram of the pupil center, the projector and the projection screen provided by the embodiment of the present application;

4 shows a schematic block diagram of a sub-step flow for calculating the distance from the center of the area of interest to the human eye to the projection point provided by an embodiment of the present application;

FIG. 5 shows a schematic block diagram of a sub-step flow of adjusting display resolution provided by an embodiment of the present application;

FIG. 6 shows a schematic block diagram of the structure of an image quality adjustment apparatus provided by an embodiment of the present application.

Description of main component symbols:

100-projector; 101-first front camera; 102-second front camera; 103-first rear camera; 104-second rear camera; 105-first front camera imaging surface; 106-th 2 Front camera imaging plane; 107-first rear camera imaging plane; 108-second rear camera imaging plane; 109-left pupil center; 110-right pupil center; 111- center of the area of interest of the human eye; 112- Projection point; 200-image quality adjustment device; 210-determination module; 220-calculation module; 230-adjustment module.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments.

The components of the embodiments of the invention generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations. Thus, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but is merely representative of selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present invention.

Hereinafter, the terms "comprising", "having" and their cognates, which may be used in various embodiments of the present invention, are only intended to denote particular features, numbers, steps, operations, elements, components, or combinations of the foregoing, and should not be construed as first excluding the presence of or adding one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing or the possibility of a combination of the foregoing.

Furthermore, the terms "first", "second", "third", etc. are only used to differentiate the description and should not be construed as indicating or implying relative importance.

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of this invention belong. The terms (such as those defined in commonly used dictionaries) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized or overly formal meaning, unless explicitly defined in the various embodiments of the present invention.

Example 1

Referring to FIG. 1 , FIG. 1 shows a schematic block diagram of the steps of the image quality adjustment method provided by the embodiment of the present application.

As shown in FIG. 1 , the image quality adjustment method provided by the embodiment of the present application is applied to a projector, where the projector includes at least two front cameras and at least two rear cameras, and the method includes S110 to S140 .

S110: Determine the position information of the projection point according to the projection image collected by the front camera.

It can be understood that the number of the front camera and the rear camera can be specifically set according to requirements. In this embodiment, the number of both the front camera and the rear camera is taken as an example for further description. The projection point is any point on the screen projected by the projector, and should not be understood as the light source point. Preferably, the projection point is a point where the mid-perpendicular lines of the two front cameras intersect with the projection screen. The projection image collected by the front camera is a two-dimensional lattice data, and the position information of the projection point is the number of rows and columns on the projection image.

S120: Determine the pupil center position information of the face image according to the face image collected by the rear camera.

In this embodiment, after the rear camera collects the face image, the face image is input into the deep learning model to obtain the position information of the human eye; according to the position information of the human eye and the face image, the pupil center positioning algorithm is used to determine the pupil Center location information.

It is understandable that the deep learning model can use algorithms such as the RetinaFace face recognition algorithm.

Specifically, the pupil center position information includes the center coordinates of the pupil area and the distance between the center of the left pupil and the center of the right pupil. As shown in Figure 2, determining the pupil center position information specifically includes the following steps:

S121: Obtain a human eye image according to the human face image and the human eye position information.

Specifically, according to the face image and the position information of the human eye collected by the rear camera, the image of the human eye region is obtained.

S122: Perform the first image binarization segmentation on the human eye image to determine the eyeball region.

Specifically, the eyeball pixel grayscale threshold and pupil pixel grayscale threshold are set, the eyeball pixel grayscale threshold is greater than the pupil threshold pixel grayscale, the first image binarization segmentation is performed on the human eye image, and the pixel grayscale is lower than the eyeball pixel grayscale. The region of the pixel grayscale threshold is determined as the eyeball region in the center of the eyeball, and the eyeball region includes the pupil and iris regions in the eyeball.

S123: Perform a second image binarization segmentation on the eyeball region of the human eye image to determine the pupil region.

Specifically, the second image binarization segmentation is performed on the eyeball area, and the area where the pixel grayscale is lower than the pupil pixel grayscale threshold is determined as the pupil area in the center of the eyeball.

S124: Perform contour extraction and ellipse fitting on the image of the pupil area to obtain the center coordinates of the pupil area.

S125: Obtain the distance between the center of the left pupil and the center of the right pupil according to the center coordinates of the corresponding pupil regions of the left pupil and the right pupil.

Specifically, the center coordinates of the left pupil area and the center coordinates of the right pupil area are substituted into the distance formula between the two points to obtain the distance between the center of the left pupil and the center of the right pupil.

In this embodiment, according to the distance from the center of the pupil to the left border of the eyeball and the distance from the center of the pupil to the right border of the eyeball, the corrected pupil center position information is obtained through a fifth preset formula. Let the formula be:

Wherein, Y' represents the corrected pupil center position information, Y represents the pupil center position information, Q ₁ represents the distance from the pupil center to the left border of the eyeball, Q ₂ represents the pupil center to the The distance to the right edge of the eyeball.

Specifically, the uncorrected pupil center position information is the eyeball center position information, and the pupil center position information is corrected according to the deviation distance from the pupil center to the eyeball center.

Taking the middle position of the center of the left pupil and the center of the right pupil as the focus position of the rear camera, the focal length of the rear camera is adjusted by calculating the sharpness of the human eye region in the face image.

Specifically, the method for calculating the sharpness of the human eye region in the face image includes but is not limited to: Brenner gradient function, Tenengrad gradient function, Laplacian gradient function, SMD (grayscale variance) function, SMD2 (grayscale variance product) function, variance function, energy gradient function, Vollath function, entropy function.

S130: Calculate the distance from the center of the area of interest of the human eye to the projection point according to the location information of the projection point, the preset parameters, and the location information of the pupil center, where the area of interest of the human eye is the projection screen of the human eye area of interest.

Please refer to FIG. 3 , which shows a geometrical relationship diagram of the pupil center, the projector and the projection screen in this embodiment. The projector 100 includes a first front camera 101 , a second front camera 102 , a first rear camera 103 and a second rear camera 104 . Each camera has a corresponding imaging plane, that is, the first front camera 101 corresponds to the first front camera imaging plane 105 , the second front camera 102 corresponds to the second front camera imaging plane 106 , and the first rear camera 103 Corresponding to the imaging plane 107 of the first rear camera, and corresponding to the imaging plane 108 of the second rear camera 104 . The left pupil center 109 and the right pupil center 110 are the positions of the pupil centers when the user watches the projection screen, the center 111 of the area of interest of the human eye is the center of the user's area of interest on the projector 100, and the projection point 112 is any point on the projection screen.

In this embodiment, the front camera includes a first front camera 101 and a second front camera 102, the rear camera includes a first rear camera 103 and a second rear camera 104, the first rear camera 104 The focal lengths of the front camera 101 and the second front camera 102 are the same, the focal lengths of the first rear camera 103 and the second rear camera 104 are the same, and the projection of the first front camera 101 to the The distance of the screen is equal to the distance from the second front camera 102 to the projection screen. The first connection is determined according to the first front camera 101 and the second front camera 102, and the first connection is determined according to the first front camera 101 and the second front camera 102. The rear camera 103 and the second rear camera 104 determine a second connection line, and the first connection line is parallel to the second connection line.

Preset preset parameters, the preset parameters include the distance parameter of the front camera, the distance parameter of the rear camera and the focal length of the front camera, wherein the distance parameter of the front camera is the first front camera and the second front camera The distance between cameras, the rear camera distance parameter is the distance between the first rear camera and the second rear camera.

Specifically, the front camera distance parameter T is preset, that is, the distance between the first front camera and the second front camera is preset as T; the front camera distance parameter T ₁ is preset, that is, the first rear camera The distance between the camera and the second rear camera is T ₁ ; the focal length of the front camera is preset to be f.

According to the position information of the projection point, the preset parameters and the pupil center position information, calculate the distance from the center of the area of interest of the human eye to the projection point, as shown in FIG. The distance of the projection point includes the following steps:

S131: Use a first preset formula to calculate the distance from the projection screen to the front camera, where the first preset formula is:

Z represents the distance from the projection screen to the front camera, f represents the focal length of the front camera, T represents the distance between the first front camera and the second front camera, X _l represents The abscissa of the projected image obtained by the first front camera of the projection point, that is, the abscissa of the projection point on the imaging plane of the first front camera, X _r indicates that the projection point is in the The abscissa of the projected image obtained by the second front camera, that is, the abscissa of the projector point on the imaging plane of the second front camera.

Specifically, according to the properties of similar triangles, we can get:

After deformation, we get

S132: Using a second preset formula, calculate the vertical distance from the center of the left pupil to the second connecting line, and the vertical distance from the center of the right pupil to the second connecting line, wherein the second preset formula is:

Z ₁ represents the vertical distance from the center of the pupil to the second connecting line, f ₁ represents the focal length of the rear camera, T ₁ represents the distance between the first rear camera and the second rear camera, Y _l1 represents the abscissa of the projected image obtained by the human eye at the rear first camera, that is, the abscissa of the image plane of the human eye at the rear first camera, and Y _r1 indicates that the human eye is at the rear the abscissa of the projected image obtained by the second camera, that is, the abscissa of the image plane of the human eye on the second rear camera;

Specifically, according to the properties of similar triangles, we can get:

After deformation, we get

S133: Using a third preset formula to calculate the inclination angle of the human eye, wherein the third preset formula is:

θ represents the inclination angle of the human eye, Z ₁₁ represents the vertical distance from the center of the left pupil to the second connecting line, Z ₁₂ represents the vertical distance from the center of the right pupil to the second connecting line, and Q represents the The distance from the center of the left pupil to the center of the right pupil.

S134: Use a fourth preset formula to calculate the distance from the center of the area of interest to the human eye to the projection point, where the fourth preset formula is:

M represents the distance from the center of the region of interest to the human eye to the projection point, and W represents the distance from the first connecting line to the second connecting line.

S140: Using a super-resolution image generation technology, adjust the display resolution of the region of interest to the human eye.

Specifically, the position information of the center of the area of interest of the human eye is determined by the distance from the center of the area of interest of the human eye to the projection point, and the preset range around the center of the area of interest of the human eye is determined as the area of interest of the human eye, and the preset range can be determined according to It actually needs to be set manually.

Further, in order to improve the display resolution of the area of interest of the human eye, as shown in FIG. 5 , the super-resolution image generation technology is used to adjust the display resolution of the area of interest of the human eye, which specifically includes the following steps:

S141: Preprocess the image of the region of interest of the human eye to obtain a preprocessed image.

Specifically, the preprocessing performed on the image of the region of interest of the human eye includes, but is not limited to, histogram equalization processing, median filtering processing, and normalization processing.

S142: Input the preprocessed image into a super-resolution reconstruction network model to obtain a super-resolution reconstructed preprocessed image.

Specifically, super-resolution reconstruction network models include but are not limited to super-resolution convolutional neural network models (Super-Resolution Convolutional Neural Network, SRCNN), fast super-resolution convolutional neural network models (Fast Super-Resolution Convolutional Neural Networks, FSRCNN) , Efficient Sub-Pixel Convolutional Neural Network (ESPCN) and Deep Convolutional Networks (VDSR).

S143: Fill the preprocessed image after super-resolution reconstruction into the region of interest of the human eye.

Specifically, the preprocessed image reconstructed by the super-resolution is filled into the area of interest of the human eye, the resolution of the image in the area of interest of the human eye is improved, and the user can obtain a super-high-resolution visual experience.

In this embodiment, the position information of the projection point is determined according to the projection image collected by the front camera, and the pupil center position information of the face image is determined according to the face image collected by the rear camera. The position information, preset parameters and the pupil center position information of the projection point, calculate the distance from the center of the area of interest of the human eye to the projection point, and use super-resolution image generation technology to adjust the display of the area of interest of the human eye resolution. That is, the position of the center of the area of interest of the human eye is determined by the distance from the center of the area of interest of the human eye to the projection point, thereby further determining the area of interest of the human eye, and by improving the resolution of the area of interest of the human eye, the projector can be improved. The high-quality picture quality enables users to obtain the technical effect of ultra-high-resolution visual experience.

Example 2

Referring to FIG. 6 , FIG. 6 shows a schematic block diagram of the structure of an image quality adjustment apparatus provided by an embodiment of the present application. The image quality adjustment apparatus 200 is applied to a projector, and the projector includes at least two front cameras and at least two rear cameras. The image quality adjustment apparatus 200 includes a determination module 210 , a calculation module 220 and an adjustment module 230 .

Wherein, the determining module 210 is used for determining the position information of the projection point according to the projection image collected by the front camera, and is also used for determining the pupil center of the face image according to the face image collected by the rear camera location information;

The calculation module 220 is configured to calculate the distance from the center of the area of interest of the human eye to the projection point according to the position information of the projection point, the preset parameter and the position information of the pupil center, wherein the area of interest of the human eye is a human The area of interest of the eye within the projection screen;

The adjustment module 230 is configured to adjust the display resolution of the area of interest of the human eye by adopting the super-resolution image generation technology.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may also be implemented in other manners. The apparatus embodiments described above are only schematic, for example, the flowcharts and structural diagrams in the accompanying drawings show possible implementation architectures and functions of apparatuses, methods and computer program products according to various embodiments of the present invention and operation. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more functions for implementing the specified logical function(s) executable instructions. It should also be noted that, in alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flow diagrams, and combinations of blocks in the block diagrams and/or flow diagrams, can be implemented using dedicated hardware-based systems that perform the specified functions or actions. be implemented, or may be implemented in a combination of special purpose hardware and computer instructions.

In addition, each functional module or unit in each embodiment of the present invention may be integrated to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.

The functions, if implemented in the form of software function modules and sold or used as independent products, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .

The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention. should be included within the protection scope of the present invention.

Claims

An image quality adjustment method, characterized in that it is applied to a projector, wherein the projector includes at least two front-facing cameras and at least two rear-facing cameras, and the method includes:

Determine the position information of the projection point according to the projection image collected by the front camera;

According to the face image collected by the rear camera, determine the pupil center position information of the face image;

According to the position information of the projection point, the preset parameters and the position information of the pupil center, the distance from the center of the area of interest of the human eye to the projection point is calculated, wherein the area of interest of the human eye is the area that the human eye pays attention to in the projection screen Area;

The super-resolution image generation technology is used to adjust the display resolution of the area of interest of the human eye.
The image quality adjustment method according to claim 1, wherein the step of determining the pupil center position information of the face image comprises:

Inputting the face image into a deep learning model to obtain eye position information;

According to the human eye position information and the face image, the pupil center positioning algorithm is used to determine the pupil center position information.
The image quality adjustment method according to claim 2, wherein the pupil center position information includes the center coordinates of the pupil area and the distance between the center of the left pupil and the center of the right pupil. and the face image, using the pupil center positioning algorithm to determine the steps of the pupil center position information, including:

Obtain a human eye image according to the human face image and the human eye position information;

Perform the first image binarization segmentation on the human eye image to determine the eyeball area;

Perform a second image binarization segmentation on the eyeball area of the human eye image to determine the pupil area;

Perform contour extraction and ellipse fitting on the image of the pupil area to obtain the center coordinates of the pupil area;

According to the center coordinates of the corresponding pupil regions of the left pupil and the right pupil, the distance between the center of the left pupil and the center of the right pupil is obtained.
The image quality adjustment method according to claim 1, wherein the front camera comprises a first front camera and a second front camera, and the rear camera comprises a first rear camera and a second rear camera cameras, the focal lengths of the first front camera and the second front camera are equal, the focal lengths of the first rear camera and the second rear camera are equal, and the distance from the first front camera to the The distance of the projection screen is equal to the distance from the second front camera to the projection screen, the first connection is determined according to the first front camera and the second front camera, and the first connection is determined according to the first rear camera. The camera and the second rear camera determine a second connection line, the first connection line is parallel to the second connection line, and the position information of the projection point, preset parameters and the pupil center position are determined. information, the steps of calculating the distance from the center of the area of interest to the projection point, including:

A first preset formula is used to calculate the distance from the projection screen to the front camera, where the first preset formula is:

Z represents the distance from the projection screen to the front camera, f represents the focal length of the front camera, T represents the distance between the first front camera and the second front camera, and X l represents the the abscissa of the projection image obtained by the projection point at the first front camera, and X r represents the abscissa of the projection image obtained by the projection point at the second front camera;

A second preset formula is used to calculate the vertical distance from the center of the left pupil to the second connecting line, and the vertical distance from the center of the right pupil to the second connecting line, wherein the second preset formula is:

Z 1 represents the vertical distance from the center of the pupil to the second connecting line, f 1 represents the focal length of the rear camera, T 1 represents the distance between the first rear camera and the second rear camera, Y l1 represents the abscissa of the projected image obtained by the human eye on the first rear camera, and Y r1 represents the abscissa of the projected image obtained by the human eye on the second rear camera;

A third preset formula is used to calculate the inclination angle of the human eye, wherein the third preset formula is:

θ represents the inclination angle of the human eye, Z 11 represents the vertical distance from the center of the left pupil to the second connecting line, Z 12 represents the vertical distance from the center of the right pupil to the second connecting line, and Q represents the the distance from the center of the left pupil to the center of the right pupil;

A fourth preset formula is used to calculate the distance from the center of the area of interest to the human eye to the projection point, where the fourth preset formula is:

M represents the distance from the center of the region of interest to the human eye to the projection point, and W represents the distance from the first connecting line to the second connecting line.
The image quality adjustment method according to claim 4, further comprising:

Preset preset parameters, the preset parameters include the distance parameter of the front camera, the distance parameter of the rear camera and the focal length of the front camera, wherein the distance parameter of the front camera is the first front camera and the second front camera The distance between cameras, the rear camera distance parameter is the distance between the first rear camera and the second rear camera.
The image quality adjustment method according to claim 1, wherein after determining the pupil center position information of the face image according to the face image collected by the rear camera, the projection is performed according to the projection. The position information of the point, the preset parameters and the position information of the pupil center, before calculating the distance from the center of the area of interest of the human eye to the projection point, also includes:

According to the distance from the center of the pupil to the left border of the eyeball and the distance from the center of the pupil to the right border of the eyeball, through the fifth preset formula, the corrected pupil center position information is obtained, and the fifth preset formula is:

Wherein, Y' represents the corrected pupil center position information, Y represents the pupil center position information, Q 1 represents the distance from the pupil center to the left border of the eyeball, Q 2 represents the pupil center to the The distance to the right border of the eyeball;

Taking the middle position of the center of the left pupil and the center of the right pupil as the focus position of the rear camera, the focal length of the rear camera is adjusted by calculating the sharpness of the human eye region in the face image.
The image quality adjustment method according to claim 1, wherein the step of using a super-resolution image generation technology to adjust the display resolution of the area of interest of the human eye comprises:

Preprocessing the image of the area of interest of the human eye to obtain a preprocessed image;

Inputting the preprocessed image to a super-resolution reconstruction network model to obtain a preprocessed image after super-resolution reconstruction;

Filling the preprocessed image after the super-resolution reconstruction into the region of interest of the human eye.
An image quality adjustment device, characterized in that it is applied to a projector, the projector includes at least two front cameras and at least two rear cameras, and the device includes:

a determination module, configured to determine the position information of the projection point according to the projection image collected by the front camera, and also used to determine the pupil center position information of the face image according to the face image collected by the rear camera;

A calculation module, configured to calculate the distance from the center of the area of interest of the human eye to the projection point according to the position information of the projection point, the preset parameters and the position information of the pupil center, wherein the area of interest of the human eye is the human eye area of interest within the projection screen;

The adjustment module is used for adjusting the display resolution of the area of interest of the human eye by adopting the super-resolution image generation technology.
A projector, characterized in that the projector comprises:

front camera, rear camera, processor and memory;

A memory for storing a program which, when executed by the processor, causes the processor to implement the method of any one of claims 1-7.
A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method according to any one of claims 1-7 is implemented.