A visual function evaluation method and device based on adaptive distance correction and a medium

Abstract

The application relates to the field of computer vision and medical auxiliary technology, in particular to a visual function evaluation method and device based on adaptive distance correction and a medium, and the main steps comprise the following: acquiring image feature parameters of a two-dimensional code marker in a video stream based on ArUco technology, combining a pinhole imaging model and a distortion correction algorithm, and calculating a real-time distance D of a user and a camera; mapping the real-time distance D to a preset multi-gear distance gradient, and determining a matching gear K of the real-time distance D; according to the matching gear K and a preset visual angle alpha, the physical width w of a current visual target is calculated; the E-shaped visual target corresponding to the physical width w of the current visual target is rendered by controlling a screen; and input of a user's orientation judgment on the E-shaped visual target is received to obtain direction judgment data. The application solves the visual target size distortion problem under a dynamic distance, and improves the accuracy of home visual self-test.

Description

Technical Field

[0001] This application relates to the fields of computer vision and medical assistance technology, and in particular to a visual function assessment method, device and medium based on adaptive distance correction. Background Technology

[0002] Current clinical visual function assessments rely on standardized testing environments with fixed distances. Visual acuity testing requires users to fixate on a static visual acuity chart at a preset standard distance (e.g., 5 meters), accommodative amplitude measurement requires head movement in a specific position, and central visual field testing requires a professional perimeter to fix the head position. These methods place stringent requirements on testing space and equipment deployment, making it difficult to meet the standard distance and equipment conditions in a home setting, resulting in low feasibility for self-testing. More importantly, distance fluctuations significantly distort the actual visual angle of the optotype, causing inaccurate assessment results.

[0003] In existing solutions, the three types of visual function tests are performed using independent devices: the standard visual acuity chart only supports a single test type, accommodation amplitude testing requires the use of an optometer and a proximity tool, and central visual field assessment relies on large perimeter hardware. Users need to switch between different devices and repeatedly adjust their posture, resulting in a lengthy and inconsistent workflow. More importantly, distance calibration requires manual handheld rangefinder operation, which introduces human error, such as deviations in the measurement angle, and cannot respond to distance changes in real time. This discrete architecture and reliance on manual intervention severely limit testing efficiency and accessibility.

[0004] While mobile devices have attempted to integrate basic vision tests, they lack the ability to adaptively correct for dynamic distances. Most existing apps default to a fixed shooting distance or rely on manual distance input by the user, failing to automatically track changes in actual location. When slight user movement causes distance fluctuations, the mapping between the physical size of the optotype and the viewing angle becomes invalid, resulting in inaccurate vision calculations. Especially in accommodation and visual field tests, dynamic distance changes are core measurement parameters, and traditional solutions, lacking real-time distance measurement technology, are completely incapable of enabling home use of such functions. Summary of the Invention

[0005] This application provides a visual function assessment method based on adaptive distance correction, which solves the problem of visual target size distortion under dynamic distance and improves the accuracy of home vision self-testing.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a visual function assessment method based on adaptive distance correction, comprising: Use the mobile device's camera to capture a video stream of the QR code tag worn by the user; Based on ArUco technology, the image feature parameters of the QR code marker in the video stream are obtained. Combined with the pinhole imaging model and distortion correction algorithm, the real-time distance D between the user and the camera is calculated. The real-time distance D is mapped to a preset multi-level distance gradient, and the matching level K of the real-time distance D is determined. The matching level K is the distance tolerance range of the real-time distance D. Based on the matching level K and the preset viewing angle α, the physical width w of the current target is calculated using the following formula: w = 2D tan(α / 2); Control the screen to render the E-shaped icon corresponding to the physical width w of the current icon; Receive user input regarding the orientation of the E-shaped visual target and obtain orientation judgment data; When a change in the real-time distance D is detected, and the change exceeds the distance tolerance range of the matching gear K corresponding to the real-time distance D, the screen of the mobile device is switched to the shooting interface of the camera, and the user is reminded to return to the initial position with text until the real-time distance D is within the distance tolerance range of the matching gear K corresponding to the real-time distance D. When a different user is detected, the matching level K and the physical width w of the current target are recalculated, and the screen is re-controlled to render the E-shaped target corresponding to the physical width w of the current target. After receiving a user's instruction to stop the vision test, the vision test result is output based on the direction judgment data, the preset angle α, the matching level K, and the real-time distance D.

[0007] In a preferred example of this application, it may further be configured to include: When controlling the screen to render the E-shaped icon corresponding to the physical width w of the current icon, multiple E-shaped icons are generated by rendering the screen line by line according to a preset ratio.

[0008] In a preferred embodiment of this application, the E-shaped logo may be further configured as a Qualcomm E-shaped logo.

[0009] In a preferred embodiment of this application, after outputting the vision test results, the method may further include: Determine whether the user has initiated a field of view test request; if so, obtain the real-time distance D. Determine whether the real-time distance D is within the preset fixed distance range for field of view testing; if not, generate a reminder. Receive user's visual field test input data and output visual field test results.

[0010] In a preferred embodiment of this application, after outputting the vision test results, the method may further include: Determine whether the user has initiated an adjustment range test request. If so, obtain the real-time distance D and receive the user's adjustment range test input data. Based on the adjustment range test input data and the real-time distance D, the adjustment range test result is output.

[0011] Secondly, this application provides a visual function assessment device based on adaptive distance correction, the device comprising: The data acquisition module is used to access the camera of the mobile device and capture the video stream of the QR code tag worn by the user; The distance calculation module is used to obtain the image feature parameters of the QR code marker in the video stream based on ArUco technology, and calculate the real-time distance D between the user and the camera by combining the pinhole imaging model and distortion correction algorithm. The matching module is used to map the real-time distance D to a preset multi-level distance gradient and determine the matching level K of the real-time distance D, wherein the matching level K is the distance tolerance range of the real-time distance D. The unified viewing angle module is used to calculate the physical width w of the current target based on the matching level K and the preset viewing angle α. The calculation formula is as follows: w = 2D tan(α / 2); Control the screen to render the E-shaped icon corresponding to the physical width w of the current icon; The interaction module is used to receive user input regarding the orientation of the E-shaped visual target and obtain orientation judgment data; when a change in the real-time distance D is detected, and the change exceeds the distance tolerance range of the matching level K corresponding to the real-time distance D, the screen of the mobile device is switched to the camera's shooting interface, and the user is reminded with text to return to the initial position until the real-time distance D is within the distance tolerance range of the matching level K corresponding to it; when a different user is detected, the matching level K and the physical width w of the current visual target are recalculated, and the screen is re-controlled to render the E-shaped visual target corresponding to the physical width w of the current visual target; The output module is used to output the vision test result based on the direction judgment data, the preset angle α, the matching gear K, and the real-time distance D after receiving the user's instruction to stop the vision test.

[0012] Thirdly, this application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the visual function evaluation method based on adaptive distance correction as described in any of the preceding claims.

[0013] Fourthly, this application provides a computer-readable storage medium storing a program, wherein when the program is executed by a processor, it implements the visual function evaluation method based on adaptive distance correction as described in any of the preceding claims.

[0014] Fifthly, this application provides a computer program product including computer instructions that, when executed by a processor, implement the steps of the visual function evaluation method based on adaptive distance correction as described in any of the preceding claims.

[0015] In summary, compared with the prior art, the beneficial effects of the technical solution provided in this application include at least the following: This application utilizes the camera and computer vision technology of a mobile tablet device to achieve adaptive testing of visual function. Specifically, it acquires real-time distance data between the user and the device using ArUco QR code recognition technology, and combines this with pinhole imaging principles and distortion correction algorithms to accurately deduce the three-dimensional spatial position. In the vision test, this application dynamically calculates the physical size of the optotype to ensure that the visual angle of the optotype remains completely consistent at different distances.

[0016] Specifically, at a fixed viewing angle, the greater the distance, the larger the physical size of the visual target needs to be. In traditional testing, if the user does not strictly maintain a fixed distance, the physical size of the visual target on the screen remains unchanged, but the actual viewing angle will shrink or enlarge, leading to errors in visual acuity calculation. This application eliminates measurement deviations caused by distance differences by binding distance to a preset viewing angle and automatically rendering a sequence of visual targets of the corresponding size. This ensures that the perceived size of the visual targets remains constant when the user looks at the text displayed on the screen at different distances. In other words, the physical size of the visual targets is dynamically calculated based on real-time distance, ensuring that the viewing angle of the visual targets in the same line is the same at different distances.

[0017] This application allows users to complete the test within a free distance range without the need for external auxiliary tools, significantly improving the convenience of self-testing. Ultimately, the test results are converted into standardized visual acuity values ​​through real-time distance conversion, enabling relatively accurate visual acuity testing by a single operator. Attached Figure Description

[0018] Figure 1 This is a flowchart of a visual function assessment method based on adaptive distance correction, provided as an embodiment of this application.

[0019] Figure 2 This is a distance measurement location map of a visual function evaluation method based on adaptive distance correction, provided as an embodiment of this application.

[0020] Figure 3 This is a schematic diagram of the ranging angle calculation of a visual function evaluation method based on adaptive distance correction, provided as an embodiment of this application.

[0021] Figure 4 A high-pass visual target diagram illustrating a visual function assessment method based on adaptive distance correction provided in one embodiment of this application.

[0022] Figure 5 This is a block diagram of a visual function evaluation device based on adaptive distance correction, provided as an embodiment of this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] In one embodiment of this application, a visual function assessment method based on adaptive distance correction is provided. Please refer to [link to relevant documentation]. Figure 1 As shown, the method includes: S100: Activate the mobile device's camera to capture a video stream of the QR code marker worn by the user.

[0025] Specifically, the mobile device may include a tablet, mobile phone, or mobile computer. When performing distance measurement, such as... Figure 2 As shown in the figure, the relative positions of the user's position and the mobile device's position during ranging are illustrated, along with a schematic diagram of the QR code marker used for device calibration.

[0026] S200: Based on ArUco technology, obtain the image feature parameters of the QR code marker in the video stream, and combine the pinhole imaging model and distortion correction algorithm to calculate the real-time distance D between the user and the camera.

[0027] Specifically, the existing computer graphics technology ArUco is applied, which can achieve positioning accuracy within 2cm in outdoor environments ranging from 40cm to 20m. By identifying a pre-given QR code target with known length and width, the position and orientation of the target in three-dimensional space relative to the camera's optical center are deduced based on camera imaging principles, including pinhole imaging and distortion correction techniques.

[0028] When conducting vision, accommodation amplitude, and field of vision tests, the user places an eye-covering sticker with a QR code on the opposite eye. The program calls the camera to generate a real-time video stream. Based on the three specific matrices of the matrix QR code, the program uses MATLAB's QR code recognition statement to obtain the overall length, width, diagonal length, and length parameters of the three specific matrix cells of the QR code within the video. Referring to the corresponding real values ​​in the QR code, the program uses the pinhole imaging principle and distortion correction technology to infer the three-dimensional position and angle of the QR code from the camera.

[0029] S300: Map the real-time distance D to a preset multi-level distance gradient, and determine the matching level K of the real-time distance D, wherein the matching level K is the distance tolerance range of the real-time distance D.

[0030] S400: Based on the matching gear K and the preset viewing angle α, calculate the physical width w of the current target. The calculation formula is as follows: w = 2D tan(α / 2); Control the screen to render the E-shaped icon corresponding to the physical width w of the current icon.

[0031] Specifically, in steps S300-S400, the use of ArUco technology for automatic distance measurement enables adaptive monitoring of vision without manual distance measurement and allows a single person to complete the test.

[0032] During testing, either a traditional E-shaped target or a Qualcomm E-shaped target can be used. The Qualcomm E-shaped target is shown below. Figure 3 As shown, a square "E" shaped logo is used with three strokes of equal length, each stroke or gap being 1 / 5 of the side length of the square. Its boundary ratio is 1:2:1, and the average brightness of the letter "E" (black core and white border) matches the brightness of the gray background.

[0033] The types of tests may include: 100% contrast ratio of traditional E-shaped target, 100% contrast ratio of Qualcomm E-shaped target, 50% contrast ratio of Qualcomm E-shaped target, and 10% contrast ratio of Qualcomm E-shaped target.

[0034] This embodiment divides the 1m to 2m distance into four distance gradients: 1m, 1.25m, 1.6m, and 2m, based on the principle that the visual difference for the same target size at different distance gradients is 0.1 logMAR. These are the multi-level distance gradients, with permissible distance ranges of 0.9~1.1m, 1.1~1.4m, 1.4~1.6m, and 1.8~2.2m, respectively. Then, the distance gradient of the real-time distance D is determined, which is the matching level K. During rendering, each page displays five targets of equal size, with the spacing between each target equal to the width of one target on the page. The number of targets facing each direction is equal, their order of appearance is randomly distributed, and adjacent targets have different directions.

[0035] The size of the optotype for the same line of visual acuity across four distance ranges is calculated based on the distance measured by the monitor's camera, ensuring that the optotype size for the same line of visual acuity has the same angular size at different fixation distances. When the angular angle α is fixed, the optotype size can be derived from the distance D using the following formula: w = 2D tan(α / 2); The angular relationship during calculation is as follows: Figure 4 As shown S500: Receive user input regarding the orientation of the E-shaped target and obtain orientation judgment data; Specifically, the user determines the direction of the "E" icon on the mobile device screen and inputs the direction data on the keyboard. Then, the system receives the user's input of the orientation of the "E" icon and obtains the direction determination data.

[0036] The procedure for a vision test can be as follows: 1) Preparation ① Sit or stand so that your line of sight is level with the screen.

[0037] ② Randomly select any inspection distance within 1-2m.

[0038] ③ Select the test type, including the test eye, optotype type, and contrast, and put a QR code eye mask on the test eye.

[0039] 2) Formal Testing ① Five visual targets corresponding to the test type appear in the center of the screen, arranged in a row.

[0040] ② Use the arrow keys on the keyboard to answer questions based on the direction of the E-shaped target indicated by the dot.

[0041] ③ If you cannot see the direction of the target, press any arrow key on the keyboard until the results display page appears.

[0042] 3) Results Display and Explanation ① Format: Visual acuity results (5-point recording method / decimal recording method) + table.

[0043] ② User information.

[0044] ③ Test type information.

[0045] ④ Time consumption information.

[0046] S600: When a change in the real-time distance D is detected, and the change exceeds the distance tolerance range of the matching gear K corresponding to the real-time distance D, the screen of the mobile device is switched to the shooting interface of the camera, and the user is reminded in text to return to the initial position until the real-time distance D is within the distance tolerance range of the matching gear K corresponding to the real-time distance D. When a different user is detected, the matching level K and the physical width w of the current target are recalculated, and the screen is re-controlled to render the E-shaped target corresponding to the physical width w of the current target. Specifically, when the user remains stationary, the user's movement causes a change in the implementation distance D. When the change exceeds the distance tolerance range of the matching level K corresponding to the real-time distance D, the screen of the mobile device switches to the camera's shooting interface and reminds the user to return to the initial position with text until the real-time distance D is within the distance tolerance range of the corresponding matching level K, so as to remind the user to stand in a reasonable range to complete the vision test and ensure that the collected direction judgment data is accurate.

[0047] By using existing technologies such as facial recognition, or by obtaining the user's login information, or by determining whether the QR code marker is the same, it can be determined whether the user has switched. If a different user is detected, steps S300 to S500 are repeated, the E-shaped visual target is re-rendered according to a preset fixed viewpoint, the gear position is re-matched, and the direction judgment data is re-collected.

[0048] S700: After receiving the user's instruction to stop the vision test, the vision test result is output based on the direction judgment data, the preset angle α, the matching gear K, and the real-time distance D.

[0049] Specifically, the vision test results are output based on preset rules and the above data.

[0050] In practice, steps S100 to S500 are executed sequentially to obtain the final response. Step S600 simultaneously performs data collection during the execution of each step from S100 to S500 to obtain audit trail data.

[0051] In this embodiment, this application utilizes the camera of a mobile tablet device and computer vision technology to achieve adaptive testing of visual function. Specifically, it acquires real-time distance data between the user and the device using ArUco QR code recognition technology, and combines this with the pinhole imaging principle and distortion correction algorithm to accurately deduce the three-dimensional spatial position. During the vision test, this application dynamically calculates the physical size of the visual target to ensure that the viewing angle of the target is completely consistent at different distances.

[0052] Specifically, at a fixed viewing angle, the greater the distance, the larger the physical size of the visual target needs to be. In traditional testing, if the user does not strictly maintain a fixed distance, the physical size of the visual target on the screen remains unchanged, but the actual viewing angle will shrink or enlarge, leading to errors in visual acuity calculation. This application eliminates measurement deviations caused by distance differences by binding distance to a preset viewing angle and automatically rendering a sequence of visual targets of the corresponding size. This ensures that the perceived size of the visual targets remains constant when the user looks at the text displayed on the screen at different distances. In other words, the physical size of the visual targets is dynamically calculated based on real-time distance, ensuring that the viewing angle of the visual targets in the same line is the same at different distances.

[0053] This application allows users to complete the test within a free distance range without the need for external auxiliary tools, significantly improving the convenience of self-testing. Ultimately, the test results are converted into standardized visual acuity values ​​through real-time distance conversion, enabling relatively accurate visual acuity testing by a single operator.

[0054] In some embodiments, it also includes: When controlling the screen to render the E-shaped icon corresponding to the physical width w of the current icon, multiple E-shaped icons are generated by rendering the screen line by line according to a preset ratio.

[0055] In practice, the E-shaped visual targets are presented row by row, with 5 visual targets per row, and the visual target increment rate per row is... (0.1logMAR), which means the ratio of the sizes of two adjacent rows of cursors is approximately 1.2589.

[0056] In some embodiments, the E-mark is a Qualcomm E-mark.

[0057] In specific implementation, such as Figure 4 As shown, the E-shaped logo uses a square "E" shape with three equally long strokes, each stroke or gap being 1 / 5 of the side length of the square. Its boundary ratio is 1:2:1, and the average brightness of the E-letter (black core and white border) matches the brightness of the gray background.

[0058] In this embodiment, the high-pass visual target is a black and white visual target presented on a uniform grayscale background, which effectively simulates the sensitivity of the human eye at different spatial frequencies. In normal individuals, its detection threshold and resolution threshold are consistent. Visual stimulation programs designed based on this visual target have been shown to have better repeatability consistency and are of particular significance in neurological visual impairment.

[0059] In some embodiments, after outputting the vision test results, the method further includes: Determine whether the user has initiated a field of view test request; if so, obtain the real-time distance D. Determine whether the real-time distance D is within the preset fixed distance range for field of view testing; if not, generate a reminder. Receive user's visual field test input data and output visual field test results.

[0060] In practice, the specific process of the visual field test can be as follows: 1) Preparation ① Take a seated position (57cm away from the designated distance), adjust your position, and put on the blindfold.

[0061] ② Physiological blind spot detection and monitoring.

[0062] ③ Conduct simulation tests using the demonstration program until the test subjects are familiar with the flow test process.

[0063] 2) Formal Testing ① A gaze target “·” appears in the center of the screen, informing the subject to gaze at this target throughout the test.

[0064] ② Physiological blind spot monitoring: Calculation of false positive rate.

[0065] ③ Instruct the participants to respond using the keyboard arrow keys.

[0066] ④ The visual targets appear randomly and sequentially within a predetermined area on the screen, and the display duration is 1 second.

[0067] ⑤ After 1 second, the circle will turn white and wait for a response. There is no time limit for the response.

[0068] ⑥ When you answer correctly, the small dot in the center of the target will turn green; when you answer incorrectly, the small dot will turn purple.

[0069] 3) Instructions for Physiological Blind Spot Detection ① Physiological blind spot monitoring target size: 0.43° ② Contrast Ratio: 100% ③ Determining the location of the physiological blind spot: When testing the right eye, the fixation point is located slightly to the left of the screen. There is a fixation point in the center of the white screen, with a diameter of 0.5 cm. The subject is instructed to fixate on this point. At this time, a solid black dot with a diameter of 0.5 cm appears from the right side of the screen. The black dot gradually moves outward from the fixation point. When the subject notices that the black dot disappears from the visual field, they click a button to confirm. This step is repeated 3 times, and the average position is taken to determine the location of the physiological blind spot. When testing the physiological blind spot of the left eye, the fixation point is located slightly to the right of the screen, and the black dot enters from the left side of the screen. The rest is the same as the right eye (a 10° visual field measurement range is reserved).

[0070] ④ Determine the position in both directions and record the results separately; however, the displayed position is the midpoint between the two values.

[0071] ⑤ The physiological blind spot monitoring target appears 8-10 times throughout the process.

[0072] 4) Simulation Test Instructions Several visual targets appear randomly and sequentially within a predetermined area on the screen, each display lasting 2 seconds, until the patient is familiar with the procedure. The visual targets do not appear in the same position during two presentations. The subject is instructed to respond using the keyboard directional buttons. The blue dot represents the fixation point, appearing simultaneously with the visual target for 2 seconds; subsequently, the yellow dot is replaced by a hollow white circle, indicating a wait for a response; when the response is correct, the central fixation target turns green for 1 second; when the response is incorrect, it turns purple for 1 second. After three consecutive correct responses, the patient proceeds to the next procedure.

[0073] 5) Test Parameter Description At a test distance of 57cm Test range: 5° Eye-tracking monitoring: monitoring the location of the physiological blind spot Visual stimulus distribution location: 16 test points are evenly distributed within a square area with a side length of 10cm.

[0074] Contrast ratio: defined by Michelson Contrast, the formula is as follows Corresponding letter sizes: 0.6cm for the inner circle of the square; 1.0cm for the outer circle of the square.

[0075] The test points are spaced approximately 3.3 cm apart horizontally and vertically. Test range: a circle with a diameter of 0.3cm around the fixation point.

[0076] 6) Threshold Strategy Description The program starts from the possible threshold range and then continuously advances towards the true threshold.

[0077] The program proposes two "stacks": an upper limit stack and a lower limit stack.

[0078] The set visual stimulus contrast range is 1% to 100%.

[0079] Detailed process description: The upper limit is 1%, and the lower limit is 100%. First, the midpoint between the set upper and lower limits is presented. If the user answers correctly, this value is added to the lower limit stack. Then, the midpoint of the contrast range is presented until the user answers incorrectly, at which point the incorrect value is added to the upper limit stack.

[0080] Endpoint: Until two reversals occur (i.e., from "user answered correctly" to "user answered incorrectly" and vice versa), and the contrast between the upper and lower limits is ≤10%. The final output threshold is defined as the midpoint between the upper and lower limits when the above two conditions are met.

[0081] There are two other possible responses: If two consecutive visual stimuli receive correct responses, the contrast of the next visual target is set to the upper limit. If an incorrect response is received, the program continues. If a correct response is still received, the value is popped from the upper limit stack and replaced with the previously stored upper limit value. The contrast of the next visual stimulus is then determined by the midpoint between the corrected upper and lower limit stack values. Similarly, if two consecutive visual stimuli receive incorrect responses, the contrast of the next visual target is set to the lower limit. If a correct response is received, the program continues. If an incorrect response is still received, the value is popped from the lower limit stack and replaced with the previously stored lower limit value. The contrast of the next visual stimulus is then determined by the midpoint between the upper and lower limit stack values.

[0082] If "Correct Answer" and "Incorrect Answer" are presented twice consecutively after the initial threshold upper and lower limits (i.e., 100% and 1%) are displayed, the threshold range will be output directly and the test will terminate.

[0083] 7) Instructions for Physiological Blind Spot Detection Physiological blind spot monitoring target size: 0.43° Contrast Ratio: 100% Determining the location of the physiological blind spot: When testing the right eye, the fixation point is located slightly to the left of the screen. There is a fixation point in the center of the white screen, 0.5cm in diameter. The subject is instructed to fixate on this point. At this time, a solid black dot, 0.5cm in diameter, appears from the right side of the screen. The black dot gradually moves outward from the fixation point. When the subject notices the black dot disappear from the visual field, they click a button to confirm. This step is repeated 3 times, and the average position is used to determine the location of the physiological blind spot. When testing the physiological blind spot of the left eye, the fixation point is located slightly to the right of the screen, and the black dot enters from the left side of the screen. The rest is the same as the right eye (with a 10° visual field measurement range reserved).

[0084] The position is determined bidirectionally, and the results are recorded separately; however, the position displayed is the midpoint between the two values.

[0085] The physiological blind spot monitoring target appears 8-10 times throughout the process.

[0086] In this embodiment, a central field of vision can be achieved with the assistance of QR code ranging, thereby enabling earlier and more timely detection of eye damage and monitoring of eye health.

[0087] In some embodiments, after outputting the vision test results, the method further includes: Determine whether the user has initiated an adjustment range test request. If so, obtain the real-time distance D and receive the user's adjustment range test input data. Based on the adjustment range test input data and the real-time distance D, the adjustment range test result is output.

[0088] In practice, the commonly used methods for measuring accommodative amplitude in clinical settings include the near-far method and the negative lens method. This procedure measures accommodative amplitude based on the near-far method, which involves gradually moving the indicator closer to the light source to create light divergence, thereby stimulating the eye to adjust its accommodation. A detailed explanation follows: (1) Test parameter description Test distance: 15cm-67cm. The ArUco technology is used for automatic distance measurement to enable a single person to complete the adjustment range test.

[0089] Test range: 1.49D-6.67D Adjustment range: The formula is 1 / distance to the nearest adjustment point (m). (2) Test Procedure Description 1) Preparation ① Take a seat (at a predetermined distance of 57cm) and adjust your position.

[0090] ② Select the eye to be tested and put on the QR code eye mask for the eye to be tested.

[0091] 2) Formal Testing ① Focus on and be able to clearly see the E-shaped target on the screen.

[0092] ② While focusing on the target, move your head toward the screen at a speed of about 1 cm / s until the target becomes blurry or you are 15 cm away from the screen.

[0093] ③ Press the space bar to complete one test, repeat the operation three times and take the average value.

[0094] In this embodiment, the adjustment range can be tested with the assistance of QR code ranging, thereby enabling earlier and more timely detection of eye damage and monitoring of eye health.

[0095] This application also provides a visual function assessment device based on adaptive distance correction; please refer to [link to relevant documentation]. Figure 5 As shown, the device includes: The data acquisition module 100 is used to call the camera of the mobile device to capture the video stream of the QR code tag worn by the user; The distance calculation module 200 is used to obtain the image feature parameters of the QR code marker in the video stream based on ArUco technology, and calculate the real-time distance D between the user and the camera by combining the pinhole imaging model and distortion correction algorithm. The matching module 300 is used to map the real-time distance D to a preset multi-level distance gradient and determine the matching level K of the real-time distance D, wherein the matching level K is the distance tolerance range of the real-time distance D. The unified viewing angle module 400 is used to calculate the physical width w of the current target based on the matching level K and the preset viewing angle α. The calculation formula is as follows: w = 2D tan(α / 2); Control the screen to render the E-shaped icon corresponding to the physical width w of the current icon; The interaction module 500 is used to receive user input regarding the orientation of the E-shaped visual target and obtain orientation judgment data; when a change in the real-time distance D is detected, and the change exceeds the distance tolerance range of the matching level K corresponding to the real-time distance D, the screen of the mobile device is switched to the camera's shooting interface, and the user is reminded to return to the initial position with text until the real-time distance D is within the distance tolerance range of the matching level K corresponding to it; when a different user is detected, the matching level K and the physical width w of the current visual target are recalculated, and the screen is re-controlled to render the E-shaped visual target corresponding to the physical width w of the current visual target; The output module 600 is used to output the vision test result based on the direction judgment data, the preset angle α, the matching gear K, and the real-time distance D after receiving the user's instruction to stop the vision test.

[0096] The functional implementation of each module in the above-mentioned visual function evaluation device based on adaptive distance correction corresponds to the steps in the above-mentioned visual function evaluation method embodiment based on adaptive distance correction. Their functions and implementation processes will not be described in detail here.

[0097] This application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the visual function evaluation method based on adaptive distance correction as described in any of the above embodiments.

[0098] This application also provides a computer-readable storage medium storing a program. The computer-readable storage medium refers to a data storage medium, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The working process, details, and technical effects of the computer-readable storage medium provided in this embodiment can be found in the above embodiment regarding a visual function evaluation method based on adaptive distance correction, and will not be repeated here.

[0099] The application also provides a computer program product, including computer instructions that, when executed by a processor, implement the steps of the visual function evaluation method based on adaptive distance correction as described in any of the above embodiments.

[0100] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0101] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification. The above embodiments only illustrate several implementation methods of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that for those skilled in the art, several modifications and improvements can be made without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A visual function assessment method based on adaptive distance correction, characterized in that, include: Use the mobile device's camera to capture a video stream of the QR code tag worn by the user; Based on ArUco technology, the image feature parameters of the QR code marker in the video stream are obtained. Combined with the pinhole imaging model and distortion correction algorithm, the real-time distance D between the user and the camera is calculated. The real-time distance D is mapped to a preset multi-level distance gradient, and the matching level K of the real-time distance D is determined. The matching level K is the distance tolerance range of the real-time distance D. Based on the matching level K and the preset viewing angle α, the physical width w of the current target is calculated using the following formula: w = 2D tan(α / 2); Control the screen to render the E-shaped icon corresponding to the physical width w of the current icon; Receive user input regarding the orientation of the E-shaped visual target and obtain orientation judgment data; When a change in the real-time distance D is detected, and the change exceeds the distance tolerance range of the matching gear K corresponding to the real-time distance D, the screen of the mobile device is switched to the shooting interface of the camera, and the user is reminded to return to the initial position with text until the real-time distance D is within the distance tolerance range of the matching gear K corresponding to the real-time distance D. When a different user is detected, the matching level K and the physical width w of the current target are recalculated, and the screen is re-controlled to render the E-shaped target corresponding to the physical width w of the current target. After receiving a user's instruction to stop the vision test, the vision test result is output based on the direction judgment data, the preset angle α, the matching level K, and the real-time distance D.

2. The visual function assessment method based on adaptive distance correction according to claim 1, characterized in that, Also includes: When controlling the screen to render the E-shaped icon corresponding to the physical width w of the current icon, multiple E-shaped icons are generated by rendering the screen line by line according to a preset ratio.

3. The visual function assessment method based on adaptive distance correction according to claim 2, characterized in that, The E-shaped logo is the Qualcomm E-shaped logo.

4. The visual function assessment method based on adaptive distance correction according to claim 1, characterized in that, After outputting the vision test results, the following is also included: Determine whether the user has initiated a field of view test request; if so, obtain the real-time distance D. Determine whether the real-time distance D is within the preset fixed distance range for field of view testing; if not, generate a reminder. Receive user's visual field test input data and output visual field test results.

5. The visual function assessment method based on adaptive distance correction according to claim 1, characterized in that, After outputting the vision test results, the following is also included: Determine whether the user has initiated an adjustment range test request. If so, obtain the real-time distance D and receive the user's adjustment range test input data. Based on the adjustment range test input data and the real-time distance D, the adjustment range test result is output.

6. The visual function assessment method based on adaptive distance correction according to claim 1, characterized in that, The mobile device is a mobile phone, tablet, or laptop.

7. A visual function assessment device based on adaptive distance correction, characterized in that, include: The data acquisition module is used to access the camera of the mobile device and capture the video stream of the QR code tag worn by the user; The distance calculation module is used to obtain the image feature parameters of the QR code marker in the video stream based on ArUco technology, and calculate the real-time distance D between the user and the camera by combining the pinhole imaging model and distortion correction algorithm. The matching module is used to map the real-time distance D to a preset multi-level distance gradient and determine the matching level K of the real-time distance D, wherein the matching level K is the distance tolerance range of the real-time distance D. The unified viewing angle module is used to calculate the physical width w of the current target based on the matching level K and the preset viewing angle α. The calculation formula is as follows: w = 2D tan(α / 2); Control the screen to render the E-shaped icon corresponding to the physical width w of the current icon; The interaction module is used to receive user input regarding the orientation of the E-shaped visual target and obtain orientation judgment data; when a change in the real-time distance D is detected, and the change exceeds the distance tolerance range of the matching level K corresponding to the real-time distance D, the screen of the mobile device is switched to the camera's shooting interface, and the user is reminded with text to return to the initial position until the real-time distance D is within the distance tolerance range of the matching level K corresponding to it; when a different user is detected, the matching level K and the physical width w of the current visual target are recalculated, and the screen is re-controlled to render the E-shaped visual target corresponding to the physical width w of the current visual target; The output module is used to output the vision test result based on the direction judgment data, the preset angle α, the matching gear K, and the real-time distance D after receiving the user's instruction to stop the vision test.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the visual function evaluation method based on adaptive distance correction as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program, wherein when the program is executed by a processor, it implements the visual function evaluation method based on adaptive distance correction as described in any one of claims 1 to 6.

10. A computer program product comprising computer instructions, characterized in that, When executed by a processor, the computer instructions implement the steps of the visual function evaluation method based on adaptive distance correction as described in any one of claims 1 to 6.

Images