CN104504374A - Method and system for automatically monitoring distance from human eyes to screen - Google Patents

Abstract

The invention discloses a method and system for automatically monitoring the distance from the human eye to the screen, wherein the method includes: obtaining user information; collecting the face image of the current user through a camera; according to the positions of the head and eyeballs in the face image, Calculate the pixel value of the pupil distance of the current user; calculate the distance from the human eye to the screen according to the pixel value of the pupil distance of the current user, the viewing angle and resolution of the camera, and the user information. By adopting the method and system disclosed in the present invention, the distance from the human eye to the screen can be calculated quickly and accurately, and the user experience is improved.

Description

A method and system for automatically monitoring the distance from human eyes to screen

technical field

The present invention relates to the field of human-computer interaction technology, in particular to a method and system for automatically monitoring the distance from the human eye to the screen

Background technique

At present, due to the rapid popularization of smart devices, especially handheld smart devices, it brings a lot of convenience and enjoyment to people's life, but it makes the vision protection work more and more severe. According to the latest survey data in 2009, the incidence of myopia among urban middle and high school students is as high as 84.80%, and that of urban middle and high school students is as high as 53.65%. The incidence of myopia tends to be younger. In addition, even if the degree of myopia in adults generally no longer develops, due to the increase in the time they use smart devices every day, it leads to eye fatigue, which makes the onset of diseases such as presbyopia more advanced. Studies have shown that when the eye-screen distance exceeds a reasonable range, especially if the distance is too close, vision will be significantly damaged. Since existing treatment methods are difficult to completely solve problems such as myopia and visual fatigue, how to develop good eye habits in human-computer interaction has become a social problem that needs to be solved urgently.

At this stage, face detection technology is widely used in smart devices, and some devices monitor the human eye line of sight, but there is less monitoring of the distance from the human eye to the screen, which is difficult to give users in use, especially those who have not yet developed good eye habits. Scientific and reasonable advice for underage users. However, the existing distance and attitude monitoring needs to cooperate with special equipment such as multi-front cameras such as Microsoft Kinect. Now there is an urgent need for a technology and technology that uses the existing single front camera of the smart terminal and combines face detection and recognition to perform distance monitoring. method.

At present, the method of calculating the eye-screen distance is to calibrate the standard distance by the user before monitoring the distance from the human eye to the screen, and then use this distance as a standard to monitor the distance from the eye to the screen, so the distance from the human eye to the screen cannot be directly estimated . On the one hand, the effectiveness of distance monitoring is compromised. Users can choose a closer distance during calibration, so that in subsequent use, even if the distance from the screen is too close, the reminder will not be triggered, which is especially serious for children; On the one hand, it increases the user's workload before use and increases the difficulty of use.

Contents of the invention

The purpose of the present invention is to provide a method and system for automatically monitoring the distance from the human eye to the screen, which can quickly and accurately calculate the distance from the human eye to the screen and improve user experience.

The purpose of the present invention is achieved through the following technical solutions:

A method for automatically monitoring the distance from a human eye to a screen, the method comprising:

Obtain user information;

Collect the face image of the current user through the camera;

Calculate the pixel value of the pupil distance of the current user according to the position of the head and eyeballs in the face image;

Calculate the distance from the human eye to the screen according to the pixel value of the current user's pupil distance, the viewing angle and resolution of the camera, and the user information.

Further, the calculation of the pixel value of the pupil distance of the current user includes:

Locate the current user's head and eyeballs, and obtain the initial pupil distance pixel value;

Calculate the average value μ and standard deviation σ of the initial pupil distance pixel value and the pupil distance pixel value in the previous T seconds, remove the pupil distance pixel value beyond the range of μ±σ, and calculate the average value of the remaining pupil distance pixel value as the current user The pixel value of the pupil distance.

Further, calculating the distance from the human eye to the screen according to the current user's pupil distance pixel value and the user information includes:

Calculate the function F ₁ (A, I, V, H) representing the distance X from the human eye to the screen, expressed as:

Among them, A represents the pixel value of the pupil distance of the current user, V represents the viewing angle of the camera, H represents the resolution of the camera, I represents the user information, and w ₁ represents the age of the user in the user information.

Further, the method also includes:

Score the distance X of the current user's eye to the screen according to the preset distance value Y from the human eye to the screen, expressed as:

Among them, S represents the score, and δ represents the error;

When the obtained score S does not reach the predetermined score value, a prompt message including correcting the distance from the human eye to the screen is sent to the user.

A system for automatically monitoring the distance from human eyes to the screen, the system comprising:

A user information acquisition module, configured to acquire user information;

Face image acquisition module, used to collect the current user's face image through the camera;

The pupil distance pixel value calculation module is used to calculate the pupil distance pixel value of the current user according to the positions of the head and eyeballs in the face image;

The human eye-to-screen distance calculation module is used to calculate the distance from the human eye to the screen according to the pixel value of the current user's pupil distance, the viewing angle and resolution of the camera, and the user information.

Further, the calculation of the pixel value of the pupil distance of the current user includes:

Locate the current user's head and eyeballs, and obtain the initial pupil distance pixel value;

Calculate the average value μ and standard deviation σ of the initial pupil distance pixel value and the pupil distance pixel value in the previous T seconds, remove the pupil distance pixel value beyond the range of μ±σ, and calculate the average value of the remaining pupil distance pixel value as the current user The pixel value of the pupil distance.

Further, calculating the distance from the human eye to the screen according to the current user's pupil distance pixel value and the user information includes:

Calculate the distance X from the human eye to the screen, expressed as:

Among them, A represents the pixel value of the pupil distance of the current user, V represents the viewing angle of the camera, H represents the resolution of the camera, I represents the user information, and w ₁ represents the age of the user in the user information.

Further, the system also includes:

The scoring module is used to score the distance X of the current user's eye to the screen according to the preset distance value Y from the human eye to the screen, expressed as:

Among them, S represents the score, and δ represents the error;

The prompting module is configured to send a prompt message to the user including correcting the distance from the human eye to the screen when the obtained score S does not reach the predetermined score value.

It can be seen from the above-mentioned technical solution provided by the present invention that the distance from the human eye to the screen is calculated according to the user information combined with the resolution and viewing angle of the camera, and the pixel value of the collected pupil distance; the distance judgment does not require user pre-calibration, and the process is simple , which improves the user experience; in addition, it can quickly and accurately calculate the distance from the human eye to the screen, so as to correct the unhealthy distance from the human eye to the screen, reduce the negative health impact of incorrect use on the user, and provide users with intelligent, humane services.

Description of drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings that need to be used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For Those of ordinary skill in the art can also obtain other drawings based on these drawings on the premise of not paying creative work.

FIG. 1 is a flow chart of a method for automatically monitoring the distance from human eyes to the screen provided by Embodiment 1 of the present invention;

FIG. 2 is a schematic diagram of a user equipment provided in Embodiment 1 of the present invention;

Fig. 3 is a flowchart of another method for automatically monitoring the distance from the human eye to the screen provided by Embodiment 1 of the present invention;

FIG. 4 is a schematic diagram of a system for automatically monitoring the distance from human eyes to the screen provided by Embodiment 2 of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

Embodiment one

Embodiment 1 of the present invention provides a method for automatically monitoring the distance from the human eye to the screen, which mainly includes the following steps:

Step 11, acquiring user information.

Step 12, collect the face image of the current user through the camera.

Step 13. Calculate the pixel value of the pupil distance of the current user according to the positions of the head and eyeballs in the face image.

The interpupillary distance is the distance between two pupils.

In the embodiment of the present invention, the calculation of the pixel value of the pupil distance of the current user includes: positioning the head and eyeballs of the current user to obtain the pixel value of the initial pupil distance; calculating the pixel value of the initial pupil distance and the pixel value of the pupil distance of the previous T seconds The average value μ and standard deviation σ of the value, remove the IPD pixel values exceeding the range of μ±σ, and calculate the average value of the remaining IPD pixel values as the current user’s IPD pixel value.

Step 14: Calculate the distance from the human eye to the screen according to the pixel value of the current user's pupil distance, the viewing angle and resolution of the camera, and the user information.

In the embodiment of the present invention, calculating the distance from the human eye to the screen according to the current user's pupil distance pixel value and the user information includes:

Calculate the function F ₁ (A, I, V, H) representing the distance X from the human eye to the screen, expressed as:

Among them, A represents the pixel value of the pupil distance of the current user, V represents the viewing angle of the camera, H represents the resolution of the camera, I represents the user information, w ₁ represents the age of the user in the user information, and 48.54 and 0.76 are two constants in the formula , is a form of the formula.

In addition, the method further includes: scoring the distance X of the current user's eye to the screen according to the preset distance value Y from the human eye to the screen, expressed as:

Among them, S represents the score, and δ represents the error;

When the obtained score S does not reach the predetermined score value, a prompt message including correcting the distance from the human eye to the screen is sent to the user.

For ease of understanding, further description will be made below in conjunction with accompanying drawings 2-3.

The method provided by the embodiment of the present invention can be implemented by user equipment UE as shown in FIG. 2 , and the user equipment can be but not limited to smart phones, smart handheld terminals, tablet computers, notebook computers, personal computers and other devices. The user equipment further includes a camera 21 and a screen 22 . The camera 21 can be adjusted to face the operator (for example, a front-facing camera of a smart phone) to collect images of the user's eyes. The content displayed on the screen 22 includes but not limited to text, video, game, icon, image and so on.

As shown in Figure 3, the method for automatically monitoring the distance from the human eye to the screen provided by the embodiment of the present invention mainly includes the following steps:

Step 301, start initialization.

The specific method of monitoring the distance from the human eye to the screen and the camera information are initialized on the UE here.

Step 302, acquire user information.

This information can be obtained from the buffer area of the UE, or the user is prompted to input; the information is all or part of the user's race, gender, and age; if the information acquisition fails in this step, then go to step 311; otherwise, if the acquisition is successful, Then step 303 starts.

Step 303, start monitoring.

Step 304, capture the user's face image.

The UE captures an image of the operator through its camera 21, which can be adjusted to face the operator. If the face image capture fails in this step, then proceed to step 311; otherwise, if the image capture is successful, then proceed to step 305.

Step 305 , using the portrait recognition technology to locate the operator's head and eyeballs, and obtain the initial pixel value of the interpupillary distance.

Step 306, storing the obtained initial pupil distance pixel value into its buffer.

Step 307, obtain the apparent pupil distance pixel value calculated from the buffer. The pixel value of the apparent pupil distance may be the transformation of historical data in the buffer, for example, its average or follow the first-in-first-out principle. Exemplarily, select a total of N pupil distance pixel values in the past T seconds (T is a positive real number) (N is an integer > 0), calculate the average value μ and standard deviation σ, and remove the pupil distance exceeding the range of μ±σ Pixel value, average the remaining M (M is an integer > 0) to obtain the apparent pupil distance pixel value. If the acquisition fails, go to step 311; otherwise, if the apparent pupil distance pixel value is successfully obtained, go to step 307.

Step 308, estimating the distance from the human eye to the screen.

In the embodiment of the present invention, the user information obtained in step 302, the apparent pupil distance pixel value obtained in step 307, and the parameters of the camera (viewing angle and resolution) are used to estimate the distance from the human eye to the screen.

Exemplarily, use X to represent the distance from the human eye to the screen, A to represent the pixel value of the current user's pupil distance, V to represent the viewing angle of the camera, H to represent the resolution of the camera, I to represent the user information, w ₁ to represent the age of the user; then the The calculation formula can be expressed as:

Step 309 , judging whether the estimated distance from the human eye to the screen meets the requirement.

In the embodiment of the present invention, compare the preset distance value Y from the human eye to the screen as a standard value with the distance from the human eye to the screen obtained in step 308 to determine whether the current user status meets the requirements; if not, go to Go to step 310; if yes, go to step 311.

Exemplarily, the evaluation function F ₂ (X, δ, Y) representing the distance score S from the human eye to the screen can be calculated, and its formula is:

Among them, S represents the score.

The average interpupillary distance of adult males in my country is about 62mm, and that of females is about 58mm, and the fluctuation generally does not exceed 10%. During the development process of children in my country, the interpupillary distance between the ages of 5 and 15 has been increasing and changing, from an average of 52.2mm to 60.1mm. Reach adult levels and remain stable. Just because the interpupillary distance maintains a similar level in the same race and age group, it can be used as a "standard ruler" to monitor the distance from the human eye to the screen with an error of 10%. That is, δ in the above formula represents the error, and

Step 310, sending a prompt message including correcting the distance from the human eye to the screen to the user.

The prompt information includes, but is not limited to, direct text, image, and video through the screen 22 or direct prompting methods such as sound, vibration, and flash through the UE.

After the operation of this step is completed, go to step 311.

Step 311, judging whether to end.

Specifically:

1. If the judgment is over, then go to step 312, including the following situations: 1) If you jump from step 302, and fail to obtain information for a long time or multiple times, then go to step 312; 2) if Jump from step 304 and fail to capture images for a long time or multiple times, then go to step 312; 3) If jump from step 307, and obtain the apparent pupillary distance for a long time or multiple times If the pixel value fails, go to step 312; 4) If jump from step 310, and the user actively shuts down, UE power saving, and does not need distance monitoring, etc., go to step 312.

2. If it is determined to continue, it includes the following situations: 1) If it jumps from step 302, continue to prompt and wait for the user to input user information; 2) If it jumps from step 304, continue to capture the user’s profile Face image; 3) If it jumps from step 307, then continue to obtain the apparent pupil distance pixel value, or return to step 303 to start a new process; 4) If it jumps from step 310, continue to process the user Monitoring, return to step 303.

Step 312, end the process.

The embodiment of the present invention calculates the distance from the human eye to the screen according to the user information combined with the resolution, viewing angle, and pixel value of the collected interpupillary distance; the distance judgment does not require the user to pre-calibrate, the process is simple, and the user experience is improved; In addition, It can quickly and accurately calculate the distance from the human eye to the screen, so as to correct the unhealthy distance from the human eye to the screen, reduce the negative health impact of incorrect use on users, and provide users with intelligent and humanized services.

Embodiment two

FIG. 4 is a schematic diagram of a system for automatically monitoring the distance from human eyes to the screen provided by Embodiment 2 of the present invention. As shown in Figure 4, the system mainly includes:

User information acquisition module 41, configured to acquire user information;

Facial image acquisition module 42, for collecting the facial image of current user by camera;

Pupil distance pixel value calculation module 43, for calculating the current user's pupil distance pixel value according to the positions of the head and eyeballs in the face image;

The eye-to-screen distance calculation module 44 is used to calculate the distance from the human eye to the screen according to the pixel value of the current user's pupil distance, the viewing angle and resolution of the camera, and the user information.

Further, the calculation of the pixel value of the pupil distance of the current user includes:

Locate the current user's head and eyeballs, and obtain the initial pupil distance pixel value;

Calculate the average value μ and standard deviation σ of the initial pupil distance pixel value and the pupil distance pixel value in the previous T seconds, remove the pupil distance pixel value beyond the range of μ±σ, and calculate the average value of the remaining pupil distance pixel value as the current user The pixel value of the pupil distance.

Further, calculating the distance from the human eye to the screen according to the current user's pupil distance pixel value and the user information includes:

Calculate the distance X from the human eye to the screen, expressed as:

Among them, A represents the pixel value of the pupil distance of the current user, V represents the viewing angle of the camera, H represents the resolution of the camera, I represents the user information, and w ₁ represents the age of the user in the user information.

Further, the system also includes:

The scoring module 45 is used to score the distance X from the current user's eyes to the screen according to the preset distance value Y from the eyes to the screen, expressed as:

Among them, S represents the score, and δ represents the error;

The prompting module 46 is configured to send a prompt to the user including correcting the distance from the human eye to the screen when the obtained score S does not reach the predetermined score value.

It should be noted that the specific implementation manners of the functions implemented by the various functional modules included in the above system have been described in detail in the previous embodiments, so details will not be repeated here.

Those skilled in the art can clearly understand that for the convenience and brevity of description, only the division of the above-mentioned functional modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional modules according to needs. The internal structure of the system is divided into different functional modules to complete all or part of the functions described above.

Through the above description of the implementation manners, those skilled in the art can clearly understand that the above embodiments can be implemented by software, or by means of software plus a necessary general hardware platform. Based on this understanding, the technical solutions of the above-mentioned embodiments can be embodied in the form of software products, which can be stored in a non-volatile storage medium (which can be CD-ROM, U disk, mobile hard disk, etc.), including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute the methods described in various embodiments of the present invention.

The above is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person familiar with the technical field can easily conceive of changes or changes within the technical scope disclosed in the present invention. Replacement should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be determined by the protection scope of the claims.

Claims (8)

1. automatic monitoring human eye is to a method for screen distance, it is characterized in that, the method comprises:

Obtain user profile;

By the facial image of camera collection active user;

According to the position of head in facial image and eyeball, calculate the interpupillary distance pixel value of active user;

According to the interpupillary distance pixel value of active user, the visual angle of camera and resolution, and described user profile calculates the distance of human eye to screen.

2. method according to claim 1, is characterized in that, the interpupillary distance pixel value of described calculating active user comprises:

The head of location active user and eyeball, obtain initial interpupillary distance pixel value;

Calculate average value mu and the standard deviation sigma of this initial interpupillary distance pixel value and the interpupillary distance pixel value in T before second, remove the interpupillary distance pixel value more than μ ± σ scope, calculate the interpupillary distance pixel value of mean value as active user of remaining interpupillary distance pixel value.

3. method according to claim 1, is characterized in that, the described interpupillary distance pixel value according to active user and described user profile calculate human eye and comprises to the distance of screen:

Computational representation human eye is to the function F of the distance X of screen ₁(A, I, V, H), is expressed as:

$X\stackrel{\mathrm{\Δ}}{=}{F}_1(A,I,V,H)=(48.54+0.76w_1)\·H/(A\·V);$

Wherein, A represents the interpupillary distance pixel value of active user, and V represents the visual angle of camera, and H represents the resolution of camera, and I represents user profile, w ₁represent the age of user in user profile.

4., according to the method for claim 1 or 3, it is characterized in that, the method also comprises:

According to the distance value Y of the human eye preset to screen, the distance X of active user's human eye to screen is marked, is expressed as:

$S\stackrel{\mathrm{\Δ}}{=}{F}_2(X,\mathrm{\δ},Y)\stackrel{\mathrm{\Δ}}{=}100-(Y-\mathrm{\δ}-X);$

$\mathrm{\δ}\stackrel{\mathrm{\Δ}}{=}X\·0.1;$

Wherein, S represents scoring, and δ represents error;

When the scoring S obtained does not reach predetermined score value, then send to comprise to this user and correct the information of human eye to screen distance.

5. automatic monitoring human eye is to a system for screen distance, it is characterized in that, this system comprises:

User profile acquisition module, for obtaining user profile;

Man face image acquiring module, for the facial image by camera collection active user;

Interpupillary distance calculated for pixel values module, for the position according to head in facial image and eyeball, calculates the interpupillary distance pixel value of active user;

Human eye is to screen distance computing module, and for according to the interpupillary distance pixel value of active user, the visual angle of camera and resolution, and described user profile calculates the distance of human eye to screen.

6. system according to claim 5, is characterized in that, the interpupillary distance pixel value of described calculating active user comprises:

The head of location active user and eyeball, obtain initial interpupillary distance pixel value;

Calculate average value mu and the standard deviation sigma of this initial interpupillary distance pixel value and the interpupillary distance pixel value in T before second, remove the interpupillary distance pixel value more than μ ± σ scope, calculate the interpupillary distance pixel value of mean value as active user of remaining interpupillary distance pixel value.

7. system according to claim 5, is characterized in that, the described interpupillary distance pixel value according to active user and described user profile calculate human eye and comprises to the distance of screen:

Calculate human eye to the distance X of screen, be expressed as:

$X\stackrel{\mathrm{\Δ}}{=}{F}_1(A,I,V,H)=(48.54+0.76w_1)\·H/(A\·V);$

Wherein, A represents the interpupillary distance pixel value of active user, and V represents the visual angle of camera, and H represents the resolution of camera, and I represents user profile, w ₁represent the age of user in user profile.

8. according to the system of claim 1 or 3, it is characterized in that, this system also comprises:

Grading module, for marking to the distance X of active user's human eye to screen according to the distance value Y of the human eye preset to screen, is expressed as:

$S\stackrel{\mathrm{\Δ}}{=}{F}_2(X,\mathrm{\δ},Y)\stackrel{\mathrm{\Δ}}{=}100-(Y-\mathrm{\δ}-X);$

$\mathrm{\δ}\stackrel{\mathrm{\Δ}}{=}X\·0.1;$

Wherein, S represents scoring, and δ represents error;

Reminding module, during for not reaching predetermined score value as the scoring S obtained, then sends to comprise to this user and corrects the information of human eye to screen distance.