Adjustment amplitude automatic evaluation method without subjective feedback

Abstract

The invention discloses an automatic adjustment amplitude evaluation method without subjective feedback, and belongs to the technical field of computer vision, and the method comprises the steps: extracting an eyeball movement track based on binocular image data; performing trajectory feature calculation based on the eyeball movement trajectory, and obtaining a trajectory length, a trajectory average speed and a trajectory curvature; based on the trajectory length, the trajectory average speed, the trajectory curvature and a preset state threshold, performing binocular trajectory collaboration analysis to obtain a real-time adjustment state; when it is judged that the real-time adjustment state is an interference abnormal state, triggering an abnormal processing mechanism, obtaining new current binocular image data, and obtaining a current adjustment state based on the current binocular image data; when it is judged that the current adjusting state is a fuzzy state, critical data are obtained; obtaining the target adjustment amplitude based on the critical data, and achieving the automatic evaluation of the adjustment amplitude. According to the adjustment amplitude automatic evaluation method without subjective feedback disclosed by the invention, the accuracy of an eye adjustment amplitude automatic evaluation result is effectively improved.

Description

Technical Field

[0001] This invention relates to the field of computer vision technology, and in particular to an automatic evaluation method for adjustment amplitude without subjective feedback. Background Technology

[0002] Accommodative amplitude refers to the maximum ability of the human eye to adjust from the far point to the near point, and is an important indicator for assessing the eye's accommodative function. Traditional methods for testing accommodative amplitude mainly rely on subjective patient feedback, i.e., moving a target close to the eye and recording the position when the patient feels the target begins to blur. However, this method has the following problems: it depends on the patient's subjective feelings and is easily affected by attention, reaction delays, or comprehension biases; it cannot distinguish between true and false accommodative insufficiency; and it lacks objective physiological indicators for verification, resulting in low reliability of the test results.

[0003] In existing technologies, some studies have attempted to detect accommodative state using eye-tracking techniques, but most rely on changes in pupil diameter or corneal reflective points. These methods have the following limitations: pupil diameter changes are influenced by various factors, such as light intensity and emotional state, and their correlation with accommodative amplitude is weak; corneal reflective point changes are affected by factors such as eye position and corneal curvature, resulting in limited measurement accuracy; and most existing technologies use artificial intelligence algorithms, which are computationally complex and difficult to implement in clinical settings. Therefore, developing an objective, accurate, and simple method for examining accommodative amplitude is of great significance for improving the accuracy and clinical applicability of ophthalmic examinations. Summary of the Invention

[0004] This invention provides an automatic assessment method for accommodation amplitude without subjective feedback, which can solve the technical problems of existing technologies such as complex calculations, difficulty in popularization in clinical settings, and susceptibility to external factors leading to insufficient accuracy in detecting eye accommodation amplitude, and effectively improve the accuracy of automatic assessment of eye accommodation amplitude.

[0005] This invention provides an automatic evaluation method for adjustment range without subjective feedback, comprising: Real-time acquisition of binocular image data, and extraction of eye movement trajectories based on the binocular image data; Based on the eye movement trajectory, trajectory features are calculated to obtain trajectory length, average trajectory velocity, and trajectory curvature; Based on the trajectory length, average trajectory speed, trajectory curvature, and preset state threshold, binocular trajectory coordination analysis is performed to obtain the real-time adjustment state. When the real-time adjustment state is determined to be an abnormal interference state, the abnormality handling mechanism is triggered to obtain new current binocular image data and obtain the current adjustment state based on the current binocular image data. When the current adjustment state is determined to be an ambiguous state, critical data is obtained; The target adjustment range is obtained based on the critical data, enabling automatic evaluation of the adjustment range.

[0006] This invention provides an automatic assessment method for accommodation amplitude without subjective feedback. By automatically extracting real-time binocular image data and eye trajectory, it eliminates the need for subjective feedback from the subject, thus avoiding errors caused by subjective feedback. Next, feature analysis is performed on the trajectory, combining three trajectory features for synergistic analysis to comprehensively reflect the motion state corresponding to eye accommodation and thereby determine the eye's accommodation state, effectively improving the accuracy of accommodation state judgment. Furthermore, in the event of interference, anomaly handling is triggered and data is reacquired, ensuring the continuity and effectiveness of the assessment process. Finally, the accommodation amplitude is automatically calculated based on critical data, achieving automatic accommodation amplitude assessment without subjective intervention, significantly improving the objectivity and efficiency of automatic accommodation amplitude assessment.

[0007] Further, the step of calculating trajectory features based on the eye movement trajectory to obtain trajectory length, average trajectory velocity, and trajectory curvature includes: The eye movement trajectory is segmented in real time based on a preset sliding time window to obtain the current trajectory window; The trajectory features of the current trajectory window are calculated to obtain the trajectory length, average trajectory velocity, and trajectory curvature of the current trajectory window. Specifically: The current trajectory window includes a sequence of pupil center coordinates; The trajectory length is obtained by calculating the trajectory features based on the pupil center coordinate sequence and the pre-acquired real-time image frame number; The average velocity of the trajectory is obtained based on the trajectory length and the pre-acquired real-time time data; The trajectory curvature is obtained based on the trajectory length, real-time image frame count, and pupil center coordinate sequence.

[0008] In the above scheme, the continuous eye movement trajectory is divided into appropriate local segments by the segmented processing of the sliding time window, avoiding the deviation of the feature calculation of the whole trajectory and making the feature results more accurate. Based on specific data such as pupil coordinate sequence, the three features are quantitatively calculated, making the acquisition of trajectory length, average speed and curvature more objective and accurate, and providing reliable feature data support for subsequent accommodation state analysis.

[0009] Further, obtaining the trajectory curvature based on the trajectory length, real-time image frame count, and pupil center coordinate sequence includes: Construct a first vector and a second vector based on any three consecutive pupil center coordinates in the pupil center coordinate sequence; The cross product of unit vectors is calculated based on the first vector and the second vector to obtain the cross product of unit vectors. The curvature at the differential point is obtained based on the cross product of the unit vectors. Obtain the curvature of all differential points on the pupil center coordinate sequence, and perform summation and normalization calculation based on the curvature of all differential points to obtain the trajectory curvature.

[0010] In the above scheme, the curvature is calculated by starting from the local differential features of the trajectory. The curvature of each local point is obtained first and then normalized to accurately reflect the curvature of the eye movement trajectory. This avoids the error of the overall rough calculation of curvature, so that the trajectory curvature can more accurately reflect the directional changes in the eye's accommodation process and improve the reliability of the feature.

[0011] Furthermore, the step of performing binocular trajectory coordination analysis based on the trajectory length, average trajectory velocity, trajectory curvature, and preset state threshold to obtain the real-time adjustment state includes: The preset state thresholds include a trajectory length threshold, a trajectory average velocity threshold, and a trajectory curvature threshold; Based on the comparison between the trajectory length and the trajectory length threshold, the trajectory length judgment result is obtained; The trajectory average speed is compared with the trajectory average speed threshold to obtain the trajectory average speed judgment result; Based on the comparison between the trajectory curvature and the trajectory curvature threshold, the trajectory curvature judgment result is obtained; Based on the trajectory length judgment result, trajectory average speed judgment result, and trajectory curvature judgment result, a binocular trajectory coordination analysis is performed to obtain the real-time adjustment status.

[0012] In the above scheme, by presetting the corresponding thresholds for each feature and comparing them separately, it is determined whether each feature is within the normal range. By combining the judgment results of multiple features for collaborative analysis, the judgment of the adjustment state is more comprehensive and accurate, reducing the possibility of misjudgment based on a single feature.

[0013] Furthermore, the step of performing binocular trajectory coordination analysis based on the trajectory length judgment result, trajectory average velocity judgment result, and trajectory curvature judgment result to obtain real-time adjustment status includes: The trajectory length determination result includes the left eye trajectory length determination result and the right eye trajectory length determination result; The trajectory average velocity judgment result includes the left eye trajectory average velocity judgment result and the right eye trajectory average velocity judgment result; The trajectory curvature judgment results include the left eye trajectory curvature judgment results and the right eye trajectory curvature judgment results; Based on the judgment results of the left eye trajectory length, right eye trajectory length, left eye trajectory average speed, right eye trajectory average speed, left eye trajectory curvature, and right eye trajectory curvature, a binocular trajectory coordination analysis is performed: When all conditions are met, the real-time adjustment status is set to clear. When none of the judgments meet the preset threshold conditions, the real-time adjustment status is obtained as an ambiguous state; When the preset abnormal characteristic conditions are met, the real-time adjustment status is obtained as an interference abnormal status.

[0014] In the above scheme, a clear state is determined when all features of both eyes meet the threshold, and a blurred state is determined when none of them meet the threshold. This is consistent with the physiological characteristics of eye movement when accommodation is good and insufficient. Identifying abnormal states of interference can eliminate the influence of non-accommodative factors, further improving the accuracy and specificity of accommodation state judgment.

[0015] Furthermore, after the step of performing binocular trajectory coordination analysis based on the trajectory length, average trajectory velocity, trajectory curvature, and preset state threshold to obtain the real-time adjustment state, the method further includes: When the real-time adjustment state is determined to be in an ambiguous state, the critical data is directly obtained; When the real-time adjustment state is determined to be clear, the process returns to the step of acquiring new binocular image data in real time and extracting new eye movement trajectories based on the binocular image data.

[0016] In the above scheme, critical data is acquired in a timely manner when the state is identified as blurry, and the critical moment of accommodation failure is accurately captured; when the state is identified as clear, data is continuously collected, which ensures continuous monitoring of the accommodation state during the movement of the target, and ensures that the critical data corresponding to accommodation failure can be acquired, thereby improving the accuracy of accommodation amplitude calculation.

[0017] Furthermore, it also includes: When the number of consecutive occurrences of the aforementioned abnormal interference states exceeds a preset abnormality threshold, a severe abnormality mechanism is triggered, ending the current automatic evaluation process of the adjustment range.

[0018] In the above scheme, when the number of consecutive abnormal interference states exceeds a preset threshold, a severe anomaly mechanism is triggered to end the current evaluation, avoiding continuous interference that would render a large amount of evaluation data invalid, saving unnecessary evaluation time, and reducing invalid operations.

[0019] Furthermore, after the step of triggering an anomaly handling mechanism, acquiring new current binocular image data, and obtaining the current accommodation state based on the current binocular image data when the real-time accommodation state is determined to be an interference anomaly state, the method further includes: Several current adjustment states are continuously acquired based on a preset sliding time window; When the number of consecutive occurrences of the ambiguous state exceeds a preset adjustment threshold, it is determined that the preset adjustment insufficiency condition is met, and the critical data of the first occurrence of the ambiguous state when the preset adjustment insufficiency condition is met is obtained.

[0020] In the above scheme, the adjustment state is continuously acquired through a preset sliding time window. When the number of consecutive occurrences of the fuzzy state exceeds a preset threshold, it is determined that the preset adjustment insufficiency condition is met, thus avoiding random errors caused by a single fuzzy state and ensuring that the determination is a true adjustment insufficiency. Then, the critical data of the first fuzzy state is acquired to accurately locate the critical distance of adjustment failure.

[0021] Furthermore, the real-time acquisition of binocular image data and the extraction of eye movement trajectories based on the binocular image data include: The visual target is moved toward the subject's eyes at a preset standard distance and a preset constant speed, and binocular image data is collected simultaneously in real time. Eye movement trajectories are extracted based on the binocular image data.

[0022] In the above scheme, the standard distance is preset to ensure the standardization of the examination, the target is moved at a constant speed to make the eye's accommodation process smooth and gradual, and the synchronous acquisition of images can make the eye movement trajectory data correspond accurately with the target distance, providing standardized and synchronous basic data for the subsequent acquisition of critical data and the calculation of accommodation amplitude.

[0023] Furthermore, it also includes: Repeat the automatic adjustment range evaluation method to obtain several target adjustment ranges; The final adjustment range is obtained by averaging the target adjustment ranges mentioned above, thus achieving automatic evaluation of the adjustment range.

[0024] In the above scheme, repeated evaluations are used to avoid random errors from a single evaluation, thereby further improving the reliability and stability of the final adjustment range and making the evaluation results more credible.

[0025] This invention provides an automatic assessment method for accommodation amplitude without subjective feedback. By acquiring binocular images in real time and extracting eye movement trajectories, combined with segmented processing using a sliding time window and quantified feature calculation, it accurately obtains the trajectory length, average trajectory velocity, and trajectory curvature, reflecting the eye's accommodation state. Furthermore, by collaboratively analyzing the judgment results of different features from both eyes, it accurately distinguishes between clear, blurred, and interfering abnormal states, achieving the identification and judgment of accommodation amplitude. Simultaneously, it addresses interference and occasional blurred states, maintaining the rationality and effectiveness of the assessment process and further ensuring the accuracy of accommodation state judgment. Moreover, through standardized target movement methods, precise capture of accommodation failure threshold data, and averaging of multiple assessments, it ultimately achieves automatic accommodation amplitude assessment without subjective feedback from the subject. This improves the objectivity, accuracy, and efficiency of the assessment, while avoiding the influence of subjective errors and accidental factors, making the assessment results of accommodation amplitude more reliable. Attached Figure Description

[0026] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0027] Figure 1 This is a schematic diagram of an automatic adjustment range evaluation method that does not require subjective feedback, provided in this embodiment. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, 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.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0030] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0031] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0032] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0033] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0034] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0035] This embodiment provides an automatic evaluation method for adjustment range without requiring subjective feedback, such as... Figure 1 As shown, it includes: S1. Real-time acquisition of binocular image data, and extraction of eye movement trajectory based on the binocular image data; S2. Calculate trajectory features based on the eye movement trajectory to obtain trajectory length, average trajectory velocity, and trajectory curvature; S3. Perform binocular trajectory coordination analysis based on the trajectory length, average trajectory speed, trajectory curvature and preset state threshold to obtain real-time adjustment status; S4. When the real-time adjustment state is determined to be an abnormal interference state, the abnormal handling mechanism is triggered to obtain new current binocular image data and obtain the current adjustment state based on the current binocular image data. S5. When the current adjustment state is determined to be an ambiguous state, obtain the critical data; S6. Obtain the target adjustment range based on the critical data to achieve automatic evaluation of the adjustment range.

[0036] In the specific implementation process, this embodiment presents visual targets through a digital display screen when collecting binocular image data in real time, controls the distance between the subject's eyes and the visual targets, and then collects binocular image data of the subject, and then extracts the eye movement trajectory to analyze the characteristics of the eye movement trajectory, judge the accommodation state, and determine the accommodation amplitude.

[0037] In the specific implementation process, this embodiment adopts a conventional ellipse fitting algorithm in this field (input: continuous infrared image sequence, single frame resolution 640x480 pixels, grayscale image; output: pupil center coordinate sequence). The specific processing flow is as follows: Image preprocessing: The input binocular image data is converted to grayscale, Gaussian filtered (using standard deviation, σ=1.5 for image noise reduction), and Otsu's adaptive threshold segmentation is applied to output a binary image. Gaussian filtering removes random noise while preserving important contour information. The Otsu algorithm is a "smart color separation" technique used to find the optimal threshold value, converting the grayscale image into a clear black-and-white binary image. These are all mature techniques in the field of computer vision.

[0038] Pupil detection: Based on the binary image obtained from image preprocessing, extract the pupil edge point set E = {(x_i, y_i)} (i = 1, 2, ..., M, where M is the number of edge points), and fit the ellipse equation using the least squares method, as shown in the following formula: ; The center of the ellipse is calculated to obtain the position of the pupil center. , The specific formula is as follows: ; ; Where: a, b, c, d, e, and f represent ellipse parameters, which are calculated from edge point E using the least squares method. a, b, and c represent the coefficients of the ellipse equation, used to characterize the geometric shape of the pupil contour (ellipse when b²-4ac<0), d and e represent the coefficients of the linear term of the ellipse equation, which are related to the pupil position offset and determine the center coordinate position; b²-4ac is the ellipse discriminant, used to ensure that the fitting result is an ellipse (corresponding to the pupil contour of the human eye).

[0039] Coordinate transformation: The pupil center position in each frame of the image is... Pupil center coordinates converted to screen coordinates Where i = 1, 2, ..., N, and N is the number of image frames. The pupil center coordinates are concatenated in chronological order to output the eye movement trajectory T = { ,…, In eye-tracking systems, pupil coordinates and screen coordinates need to be calibrated by the human eye before automatic evaluation. During the calibration process, a mapping relationship is established to facilitate coordinate transformation.

[0040] Optionally, step S2 includes: The eye movement trajectory is segmented in real time based on a preset sliding time window to obtain the current trajectory window; The trajectory features of the current trajectory window are calculated to obtain the trajectory length, average trajectory velocity, and trajectory curvature of the current trajectory window. Specifically: The current trajectory window includes a sequence of pupil center coordinates; The trajectory length is obtained by calculating the trajectory features based on the pupil center coordinate sequence and the pre-acquired real-time image frame number; The average velocity of the trajectory is obtained based on the trajectory length and the pre-acquired real-time time data; The trajectory curvature is obtained based on the trajectory length, real-time image frame count, and pupil center coordinate sequence.

[0041] In the specific implementation process, this embodiment uses a preset sliding time window (such as a 2-second window) to segment the eye movement trajectory. By calculating the trajectory length, average trajectory speed, and trajectory curvature of the trajectory data within each window, it is possible to determine in real time whether there is insufficient accommodation, i.e., a blurred state, at the instantaneous target distance corresponding to the current window.

[0042] In the specific implementation process, trajectory features are calculated based on the pupil center coordinate sequence and the number of pre-acquired real-time image frames. The specific calculation process for obtaining the trajectory length is shown in the following formula: ; Where: L is the trajectory length, in pixels; , ) represents the coordinates of the pupil center in the i-th frame image, and N is the number of real-time image frames being analyzed.

[0043] The specific calculation process for obtaining the average velocity of the trajectory based on the trajectory length and pre-acquired real-time time data is as follows: ; in: Δt represents the average velocity of the trajectory, in pixels per second; Δt represents the total real-time data analyzed, in seconds.

[0044] In practice, the trajectory length represents the total distance the eye moves during observation: when accommodation is good, the eye movement distance is small; when accommodation is insufficient, the eye moves frequently to find a clear target, increasing the trajectory length. The average trajectory speed represents the average speed of eye movement: when accommodation is insufficient, the eye needs to move frequently to find a clear target, increasing the average speed. The trajectory curvature represents the degree of curvature of the eye movement trajectory: when accommodation is insufficient, the eye frequently changes its gaze direction, increasing the trajectory curvature; when accommodation is good, the eye maintains a stable gaze, resulting in a smaller trajectory curvature.

[0045] Optionally, obtaining the trajectory curvature based on the trajectory length, real-time image frame count, and pupil center coordinate sequence includes: Construct a first vector and a second vector based on any three consecutive pupil center coordinates in the pupil center coordinate sequence; The cross product of unit vectors is calculated based on the first vector and the second vector to obtain the cross product of unit vectors. The curvature at the differential point is obtained based on the cross product of the unit vectors. Obtain the curvature of all differential points on the pupil center coordinate sequence, and perform summation and normalization calculation based on the curvature of all differential points to obtain the trajectory curvature.

[0046] In the specific implementation process, when obtaining the trajectory curvature based on the trajectory length, real-time image frame count, and pupil center coordinate sequence, the first step is to obtain the pupil center coordinates of any three consecutive pupils on the eye movement trajectory. , and Construct two vectors: the first vector Second vector Next, we calculate the cross product of these two vectors (in two-dimensional space, the size of the cross product is the area of ​​the parallelogram formed by these two vectors), as shown in the following formula: ; Since calculating the trajectory curvature only requires considering the cross product of unit vectors, the unit vector is then calculated. and The specific calculation process for obtaining the cross product of unit vectors by performing the cross product of unit vectors is shown in the following formula: ; Furthermore, in calculus, the definition of curvature k is as follows: ; in: It is the rate of change of the tangent vector with respect to time. It is the velocity vector (differentiated from the position vector).

[0047] Therefore, for discrete points, this embodiment approximately uses the cross product of the aforementioned unit vectors to estimate the curvature k, as shown in the following equation: ; Where Δs is a tiny change in arc length.

[0048] Applying the above idea to each point in the eye movement trajectory yields the curvature at the differential point. : ; The curvature of the trajectory is obtained by summing and normalizing the curvatures at all differential points, as shown in the following formula: ; Where: C is the trajectory curvature, which is dimensionless.

[0049] Optionally, step S3 includes: The preset state thresholds include a trajectory length threshold, a trajectory average velocity threshold, and a trajectory curvature threshold; Based on the comparison between the trajectory length and the trajectory length threshold, the trajectory length judgment result is obtained; The trajectory average speed is compared with the trajectory average speed threshold to obtain the trajectory average speed judgment result; Based on the comparison between the trajectory curvature and the trajectory curvature threshold, the trajectory curvature judgment result is obtained; Based on the trajectory length judgment result, trajectory average speed judgment result, and trajectory curvature judgment result, a binocular trajectory coordination analysis is performed to obtain the real-time adjustment status.

[0050] In its implementation, this embodiment proposes a method for judging accommodation state based on eye movement trajectory characteristics. The thresholds for trajectory length, average trajectory velocity, and trajectory curvature can be initially set based on theoretical models or pre-experimental data of typical human eye accommodation behavior. In practical applications, these thresholds can be individually adjusted through calibration or machine learning. In this embodiment, the following threshold range is initially set as the judgment criterion: Trajectory length threshold: =50 pixels (clinical validation required), average velocity threshold for trajectory: =5 pixels / second (clinical validation required), trajectory curvature threshold: =0.2 (clinical validation required). These thresholds are all set based on typical characteristics of eye movement trajectories. When the trajectory characteristics (including the trajectory length, average trajectory speed, and trajectory curvature) exceed the threshold, it indicates that the eye is in a blurred state, that is, in a state of insufficient accommodation.

[0051] Optionally, the step of performing binocular trajectory coordination analysis based on the trajectory length judgment result, trajectory average velocity judgment result, and trajectory curvature judgment result to obtain real-time adjustment status includes: The trajectory length determination result includes the left eye trajectory length determination result and the right eye trajectory length determination result; The trajectory average velocity judgment result includes the left eye trajectory average velocity judgment result and the right eye trajectory average velocity judgment result; The trajectory curvature judgment results include the left eye trajectory curvature judgment results and the right eye trajectory curvature judgment results; Based on the judgment results of the left eye trajectory length, right eye trajectory length, left eye trajectory average speed, right eye trajectory average speed, left eye trajectory curvature, and right eye trajectory curvature, a binocular trajectory coordination analysis is performed: When all conditions are met, the real-time adjustment status is set to clear. When none of the judgments meet the preset threshold conditions, the real-time adjustment status is obtained as an ambiguous state; When the preset abnormal characteristic conditions are met, the real-time adjustment status is obtained as an interference abnormal status.

[0052] In the specific implementation process, this embodiment uses a binocular coordination judgment mechanism to distinguish between inspection interference and the true accommodation state. Judgment is made by real-time monitoring of the trajectory characteristics of the left and right eyes (including trajectory length L, average trajectory velocity V, and trajectory curvature C). Since insufficient accommodation causes frequent eye movements (high average velocity) and changes in gaze direction (high curvature), while good accommodation results in less eye movement and a stable direction (low average velocity and curvature), the specific judgment principles set in this embodiment include: firstly, real-time monitoring of the trajectory characteristics of the left and right eyes, including trajectory length L, average trajectory velocity V, and trajectory curvature C. Then, based on the three trajectory characteristics and their corresponding thresholds, a state judgment is made. Insufficient accommodation state: when the trajectory length L, average trajectory velocity V, and trajectory curvature C of both eyes simultaneously exceed the threshold and the fluctuation is stable (without obvious jumps), it is judged as an insufficient accommodation state (the target begins to blur). If none of these judgments meet the preset threshold conditions, the real-time accommodation state is obtained as a blurred state. Good accommodation state: When the trajectory length L, average trajectory velocity V, and trajectory curvature C of both eyes are all within the threshold range, and the trajectory is smooth and stable, it is judged as a good accommodation state. At this time, if all the judgments meet the preset threshold conditions, the real-time accommodation state is obtained as a clear state. Checking for interference anomalies: If neither of the above two conditions is met, it is judged as an interference anomaly. At this time, if the judgment meets the preset abnormal feature conditions, the real-time accommodation state is obtained as an interference anomaly state. Specific manifestations include: the trajectory feature of one or both eyes exceeding the threshold, and the trajectory feature value showing obvious jumps, indicating unstable fluctuations, such as head micro-movements causing jump features, blinking, or brief distraction. Among them, when performing abnormal feature recognition, anomalies typically include: jump features are manifested as a trajectory suddenly shifting significantly and then quickly returning to its original position, or feature values ​​fluctuating violently up and down in a short period of time; a typical blinking pattern is the trajectory completely disappearing within 50-100 milliseconds and then reappearing; a typical distraction pattern is the trajectory suddenly jumping to the edge and then returning to the target within a few seconds.

[0053] Optionally, after step S3, the following steps are also included: When the real-time adjustment state is determined to be in an ambiguous state, the critical data is directly obtained; When the real-time adjustment state is determined to be clear, the process returns to the step of acquiring new binocular image data in real time and extracting new eye movement trajectories based on the binocular image data.

[0054] In the specific implementation process, in step S4, when the real-time accommodation state is determined to be an abnormal interference state, the abnormality handling mechanism is triggered. Specifically, this includes: when an abnormal interference is detected (such as monocular sacral movement): display "Measurement interference detected, please keep your gaze fixed", and pause for 3 seconds before automatically continuing to check for abnormalities; after the condition returns to normal, acquire new binocular image data and repeat the trajectory feature acquisition and determination process. When an insufficient accommodation state is detected (the trajectory features of both eyes simultaneously exceed the threshold, i.e., the real-time accommodation state is determined to be blurred): record the critical data (including the critical distance) and complete the measurement. For example, if the target can only be moved to a position 7cm away from the eye, then the recorded data is 7cm.

[0055] Optional, also includes: When the number of consecutive occurrences of the aforementioned abnormal interference states exceeds a preset abnormality threshold, a severe abnormality mechanism is triggered, ending the current automatic evaluation process of the adjustment range.

[0056] In the specific implementation process, the serious abnormality mechanism is as follows: when the number of abnormal examinations exceeds the preset abnormality threshold (in this embodiment, the preset abnormality threshold is set to 3 times) during the same examination process, the system will prompt "Frequent measurement interference, it is recommended to rest and try again or consult an ophthalmologist", end the current automatic adjustment range assessment process, and allow the operator to decide whether to continue.

[0057] Optionally, after step S4, the following steps are also included: Several current adjustment states are continuously acquired based on a preset sliding time window; When the number of consecutive occurrences of the ambiguous state exceeds a preset adjustment threshold, it is determined that the preset adjustment insufficiency condition is met, and the critical data of the first occurrence of the ambiguous state when the preset adjustment insufficiency condition is met is obtained.

[0058] Optionally, step S1 includes: The visual target is moved toward the subject's eyes at a preset standard distance and a preset constant speed, and binocular image data is collected simultaneously in real time. Eye movement trajectories are extracted based on the binocular image data.

[0059] Optional, also includes: Repeat the automatic adjustment range evaluation method to obtain several target adjustment ranges; The final adjustment range is obtained by averaging the target adjustment ranges mentioned above, thus achieving automatic evaluation of the adjustment range.

[0060] In the specific implementation process, the preset standard distance includes the standard inspection distance (set to 40cm in this embodiment) and the preset closest distance (e.g., set to 10cm). When using the automatic adjustment amplitude evaluation method without subjective feedback provided in this embodiment for inspection, the specific steps include: initialization, the examinee sits in front of the inspection equipment and looks at the target on the digital display screen at the standard inspection distance; continuous movement is started, the display screen moves at a preset constant speed (e.g., 1... The infrared camera moves at a low speed (cm / s) from the standard examination distance towards the subject's eyes until the preset closest distance is reached or the system determines that accommodation has failed (insufficient accommodation). Simultaneous image acquisition: Throughout the entire movement of the target, the infrared camera continuously acquires images of both eyes at 30 frames per second, recording the eye movement trajectory in real time. Trajectory analysis: The system uses a preset sliding time window (e.g., a 2-second window) to segment the eye movement trajectory and calculates the trajectory length, average speed, and curvature for the trajectory data within each window, thereby determining in real time whether insufficient accommodation occurs at the instantaneous target distance corresponding to the current window. Accommodation state judgment: To ensure the accuracy of the judgment results and avoid accidental factors, this embodiment further sets the following accommodation state judgment principle: If the characteristics of the eye trajectory within a certain sliding window continuously exceed a preset accommodation number threshold (e.g., exceeding the threshold for two consecutive windows), it is determined that the eye can no longer maintain clear accommodation at that distance. Accommodation amplitude calculation: Taking the critical clear distance d before accommodation failure (unit: meters), the accommodation amplitude A = 1 / d is calculated, with the unit being diopter (D). For example, if insufficient accommodation is determined at 25cm, then the accommodation amplitude A ≈ 1 / 0.25. = 4D; Repeated verification: To ensure accuracy, the check can be repeated 2-3 times, and the average value is taken as the final result.

[0061] This embodiment provides an automatic assessment method for accommodative amplitude without subjective feedback. It objectively and accurately measures the accommodative amplitude of the human eye, objectively measuring the accommodative state through eye movement trajectory characteristics, reducing reliance on subjective patient feedback and effectively improving the reliability of examination results. Eye movement trajectory characteristics are highly correlated with accommodative state; by calculating multiple trajectory characteristics and setting reasonable thresholds, the accommodative state can be accurately determined. Furthermore, the algorithm is based on simple geometric calculations during the analysis and calculation process, without relying on complex artificial intelligence models, making it easy to implement in clinical settings and simple to perform. It is applicable to accommodative amplitude examinations for various populations. The method provided in this embodiment relates to the field of ophthalmic examination technology and can be applied to: professional ophthalmology hospitals for routine ophthalmic examinations, assessing patients' accommodative function and providing objective evidence for the diagnosis and treatment of ophthalmic diseases; optometry centers for detailed examinations before optometry and spectacle fitting, providing accurate evidence for spectacle fitting, especially for patients with accommodative dysfunction, avoiding discomfort caused by accommodative problems; school vision screening for large-scale student vision screening, rapidly assessing students' accommodative function, early detection of accommodative dysfunction, and timely intervention; and ophthalmic research for clinical research on accommodative function, providing objective data for the diagnosis of ophthalmic diseases and promoting the development of ophthalmic research.

[0062] In its implementation, this embodiment also provides an accommodation amplitude testing device, including a digital display screen, an image acquisition module, an image processing module, and a display module. The image processing module includes an eye movement trajectory analysis algorithm. Specifically, the image acquisition module acquires real-time image data of the subject's eyes, including data from an infrared camera; the image processing module extracts the eye movement trajectory and determines the accommodation state; finally, the display module displays the accommodation amplitude test results and operation prompts.

[0063] In practice, the size and position of the target can be adjusted on the digital display screen.

[0064] Optionally, the adjustment amplitude testing device performs human eye calibration on the subject before use. By recording the pupil center coordinates when the subject gazes at a known point on the screen, a mapping relationship between pupil coordinates and screen coordinates is established to ensure the accuracy of eye movement tracking. This human eye calibration technology is a mature existing technology in the field of eye tracking and will not be described in detail in this embodiment.

[0065] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can realize that any of the above-described method embodiments of the present invention provides an automatic evaluation method for adjustment range without subjective feedback.

[0066] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0067] Based on the above-described method embodiments, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements an automatic adjustment range evaluation method without subjective feedback according to any embodiment of the present invention.

[0068] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0069] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0070] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0071] Based on the above-described method embodiments, another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute an automatic adjustment amplitude evaluation method without subjective feedback as described in any of the above-described method embodiments of the present invention.

[0072] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0073] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for automatically evaluating adjustment range without subjective feedback, characterized in that, include: Real-time acquisition of binocular image data, and extraction of eye movement trajectories based on the binocular image data; Based on the eye movement trajectory, trajectory features are calculated to obtain trajectory length, average trajectory velocity, and trajectory curvature; Based on the trajectory length, average trajectory speed, trajectory curvature, and preset state threshold, binocular trajectory coordination analysis is performed to obtain the real-time adjustment state. When the real-time adjustment state is determined to be an abnormal interference state, the abnormality handling mechanism is triggered to obtain new current binocular image data and obtain the current adjustment state based on the current binocular image data. When the current adjustment state is determined to be an ambiguous state, critical data is obtained; The target adjustment range is obtained based on the critical data, enabling automatic evaluation of the adjustment range.

2. The automatic adjustment range evaluation method without subjective feedback as described in claim 1, characterized in that, The calculation of trajectory features based on the eye movement trajectory to obtain trajectory length, average trajectory velocity, and trajectory curvature includes: The eye movement trajectory is segmented in real time based on a preset sliding time window to obtain the current trajectory window; The trajectory features of the current trajectory window are calculated to obtain the trajectory length, average trajectory velocity, and trajectory curvature of the current trajectory window. Specifically: The current trajectory window includes a sequence of pupil center coordinates; The trajectory length is obtained by calculating the trajectory features based on the pupil center coordinate sequence and the pre-acquired real-time image frame number; The average velocity of the trajectory is obtained based on the trajectory length and the pre-acquired real-time time data; The trajectory curvature is obtained based on the trajectory length, real-time image frame count, and pupil center coordinate sequence.

3. The automatic evaluation method for adjustment range without subjective feedback as described in claim 2, characterized in that, The process of obtaining the trajectory curvature based on the trajectory length, real-time image frame count, and pupil center coordinate sequence includes: Construct a first vector and a second vector based on any three consecutive pupil center coordinates in the pupil center coordinate sequence; The cross product of unit vectors is calculated based on the first vector and the second vector to obtain the cross product of unit vectors. The curvature at the differential point is obtained based on the cross product of the unit vectors. Obtain the curvature of all differential points on the pupil center coordinate sequence, and perform summation and normalization calculation based on the curvature of all differential points to obtain the trajectory curvature.

4. The automatic adjustment range evaluation method without subjective feedback as described in claim 1, characterized in that, The step of performing binocular trajectory coordination analysis based on the trajectory length, average trajectory velocity, trajectory curvature, and preset state threshold to obtain real-time adjustment status includes: The preset state thresholds include a trajectory length threshold, a trajectory average velocity threshold, and a trajectory curvature threshold; Based on the comparison between the trajectory length and the trajectory length threshold, the trajectory length judgment result is obtained; The trajectory average speed is compared with the trajectory average speed threshold to obtain the trajectory average speed judgment result; Based on the comparison between the trajectory curvature and the trajectory curvature threshold, the trajectory curvature judgment result is obtained; Based on the trajectory length judgment result, trajectory average speed judgment result, and trajectory curvature judgment result, a binocular trajectory coordination analysis is performed to obtain the real-time adjustment status.

5. The automatic evaluation method for adjustment range without subjective feedback as described in claim 4, characterized in that, The step of performing binocular trajectory coordination analysis based on the trajectory length judgment result, trajectory average velocity judgment result, and trajectory curvature judgment result to obtain real-time adjustment status includes: The trajectory length determination result includes the left eye trajectory length determination result and the right eye trajectory length determination result; The trajectory average velocity judgment result includes the left eye trajectory average velocity judgment result and the right eye trajectory average velocity judgment result; The trajectory curvature judgment results include the left eye trajectory curvature judgment results and the right eye trajectory curvature judgment results; Based on the judgment results of the left eye trajectory length, right eye trajectory length, left eye trajectory average speed, right eye trajectory average speed, left eye trajectory curvature, and right eye trajectory curvature, a binocular trajectory coordination analysis is performed: When all conditions are met, the real-time adjustment status is set to clear. When none of the judgments meet the preset threshold conditions, the real-time adjustment status is obtained as an ambiguous state; When the preset abnormal characteristic conditions are met, the real-time adjustment status is obtained as an interference abnormal status.

6. The automatic evaluation method for adjustment range without subjective feedback as described in claim 1, characterized in that, After the step of performing binocular trajectory coordination analysis based on the trajectory length, average trajectory velocity, trajectory curvature, and preset state threshold to obtain the real-time adjustment state, the method further includes: When the real-time adjustment state is determined to be in an ambiguous state, the critical data is directly obtained; When the real-time adjustment state is determined to be clear, the process returns to the step of acquiring new binocular image data in real time and extracting new eye movement trajectories based on the binocular image data.

7. The automatic adjustment range evaluation method without subjective feedback as described in claim 1, characterized in that, Also includes: When the number of consecutive occurrences of the aforementioned abnormal interference states exceeds a preset abnormality threshold, a severe abnormality mechanism is triggered, ending the current automatic evaluation process of the adjustment range.

8. The automatic evaluation method for adjustment range without subjective feedback as described in claim 1, characterized in that, After the step of triggering an anomaly handling mechanism, acquiring new current binocular image data, and obtaining the current accommodation state based on the current binocular image data when the real-time accommodation state is determined to be an interference anomaly state, the method further includes: Several current adjustment states are continuously acquired based on a preset sliding time window; When the number of consecutive occurrences of the ambiguous state exceeds a preset adjustment threshold, it is determined that the preset adjustment insufficiency condition is met, and the critical data of the first occurrence of the ambiguous state when the preset adjustment insufficiency condition is met is obtained.

9. The automatic evaluation method for adjustment range without subjective feedback as described in claim 1, characterized in that, The real-time acquisition of binocular image data, and the extraction of eye movement trajectories based on the binocular image data, includes: The visual target is moved toward the subject's eyes at a preset standard distance and a preset constant speed, and binocular image data is collected simultaneously in real time. Eye movement trajectories are extracted based on the binocular image data.

10. The automatic evaluation method for adjustment range without subjective feedback as described in claim 1, characterized in that, Also includes: Repeat the automatic adjustment range evaluation method to obtain several target adjustment ranges; The final adjustment range is obtained by averaging the target adjustment ranges mentioned above, thus achieving automatic evaluation of the adjustment range.

Images