Electronic myopia glasses with eye condition tracking image acquisition feedback
By combining an eye-tracking sensor and a main control unit, the image acquisition mode and diopter are intelligently adjusted, solving the problem of blind image acquisition by cameras in existing technologies and achieving efficient, low-latency image acquisition and optimized visual experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- ANHUI AVATAR THREE WORLDS TECH CO LTD
- Filing Date
- 2025-12-01
- Publication Date
- 2026-07-21
AI Technical Summary
The cameras in existing electronic myopia glasses cannot sense the user's visual intent, resulting in blind image acquisition, high power consumption, poor image quality, system latency, and a disconnect between system performance and user experience, failing to achieve deep closed-loop linkage.
An eye-tracking sensor is used to identify the gaze direction. The main control unit generates control commands to adjust the working mode of the image acquisition unit. Combined with the refractive correction module and predictive control, intelligent and precise image acquisition optimization is achieved.
This allows image acquisition resources to be concentrated on the area of user focus, significantly improving image quality, reducing power consumption, eliminating gaze switching delay, and enhancing visual comfort and system performance.
Smart Images
Figure CN224536281U_ABST
Abstract
Description
Technical Field
[0001] This utility model relates to the field of smart wearable device technology, specifically to an electronic myopia glasses with eye-tracking image acquisition and feedback. Background Technology
[0002] With the development of augmented reality (AR) technology, smart glasses have become an important direction for revolutionizing traditional vision correction methods. Existing technologies have attempted to combine cameras with near-eye display systems to provide users with electronic visual assistance. However, such solutions generally suffer from significant drawbacks:
[0003] First, there is a disconnect between perception and execution. Most existing glasses cameras operate in a fixed mode (such as continuous autofocus or fixed focus), which cannot perceive the user's visual intent (whether they are looking at something far away or near). Their image acquisition strategy is blind and cannot optimize resources for the user's current focus, resulting in high power consumption and poor image quality in key areas.
[0004] Second, there is a lack of intelligent collaboration. Eye-tracking technology is mostly used for interactive control (such as menu selection), but it has not formed a deep closed-loop linkage with the core image acquisition function of the glasses. Its potential has not been fully explored, and it has failed to achieve the leap from "passive acquisition" to "active optimization".
[0005] Third, system latency and user experience are disconnected. When the user's gaze shifts, there is a delay in camera focusing or mode switching, causing the displayed image to not match the user's expectations, which can easily cause visual fatigue and dizziness.
[0006] Therefore, there is an urgent need in this field for electronic myopia glasses that can understand the user's visual intent in real time and optimize the front-end image acquisition strategy intelligently, accurately and quickly to improve visual comfort, image quality and system energy efficiency.
[0007] Based on this, this invention designs an electronic myopia glasses with eye-tracking image acquisition and feedback to solve the above problems. Utility Model Content
[0008] The purpose of this invention is to provide an electronic myopia glasses with eye-tracking image acquisition and feedback, in order to solve the problems mentioned in the background art.
[0009] To achieve the above objectives, this utility model provides the following technical solution:
[0010] An electronic myopia glasses system with eye-tracking image acquisition and feedback includes:
[0011] Eyeglass frames;
[0012] An image acquisition unit is mounted on the eyeglasses frame and is used to acquire images of the external scene.
[0013] The main control unit is located inside the eyeglass frame and is electrically connected to the image acquisition unit;
[0014] A catadioptric optical display module is mounted on the eyeglass frame and electrically connected to the main control unit, used to display the image processed by the main control unit;
[0015] An eye-tracking sensor, mounted on the eyeglasses frame, is used to collect the user's eye movement data;
[0016] The main control unit is communicatively connected to the eye-tracking sensor and is configured as follows:
[0017] The user's gaze direction is identified based on the eye movement data;
[0018] Based on the identified gaze direction, control commands are generated to adjust the operating mode of the image acquisition unit, thereby outputting an optimized image signal that matches the gaze direction.
[0019] As a further embodiment of this utility model, it also includes: a diopter correction module, integrated in the optical path of the catadioptric optical display module, used to adjust the diopter of the output beam;
[0020] The main control unit is further configured to generate control commands based on the identified gaze direction to synchronously adjust the refractive power parameters of the refractive power correction module.
[0021] As a further embodiment of this invention: the eye-tracking sensor is disposed on both sides of the bridge of the nose and / or the inside of the eyeglass frame.
[0022] As a further embodiment of this utility model: the image acquisition unit is a focusing camera module, used for automatic focusing within a preset focal length range.
[0023] As a further aspect of this utility model: the main control unit is configured as follows:
[0024] When the gaze direction is detected to be a distant scene, the focusing camera module is controlled to focus on the telephoto mode and the resolution of the central area of the image is improved.
[0025] When the gaze direction is detected to be close-up, the focusing camera module is controlled to focus to close-up mode and the image field of view is expanded.
[0026] As a further embodiment of this utility model: the image acquisition unit is a fixed-focus camera module assembly, including a close-up fixed-focus camera for acquiring close-up images and a distant fixed-focus camera for acquiring distant images.
[0027] As a further aspect of this utility model: the main control unit is configured as follows:
[0028] When the gaze direction is detected to be a distant scene, the distant fixed-focus camera is activated as the main image source and the data from the close-up fixed-focus camera is suppressed.
[0029] When the gaze direction is detected to be close-up, the close-up fixed-focus camera is activated as the main image source and the data from the distant fixed-focus camera is suppressed.
[0030] As a further embodiment of this utility model: the main control unit is configured to: predict eye movement trends based on the trajectory and speed of eye movements, and based on the prediction results, initiate an adjustment command for the working mode of the image acquisition unit in advance before the user's gaze switches to a new target.
[0031] As a further embodiment of this invention: the eye-tracking sensor is configured in a half-eye image acquisition mode, capturing only a local area of the eyeball; the main control unit is configured to reconstruct the complete eye movement trajectory based on the local eyeball image data through a dynamic context memory library.
[0032] As a further aspect of this invention: the dynamic context memory stores historical eye-tracking feature vectors, and the main control unit fuses the current frame data with the historical feature vectors based on a three-dimensional attention mechanism to predict the gaze point shift trend.
[0033] As a further embodiment of this utility model, it also includes an external display screen, which is located outside the eyeball position on the outside of the eyeglass frame; the main control unit is further configured to send the currently identified gaze direction or the working status information of the image acquisition unit to the external display screen for real-time display.
[0034] As a further embodiment of this utility model, it also includes a supplementary lighting unit; the main control unit is configured to dynamically adjust the brightness and supplementary lighting mode of the supplementary lighting unit based on the image exposure acquired by the eye-tracking sensor, so as to ensure tracking accuracy in low-light environments.
[0035] Compared with the prior art, the beneficial effects of this utility model are:
[0036] 1. Intelligent image acquisition: It realizes a leap from "blind acquisition" to "intent-driven" acquisition, which concentrates image acquisition resources on the user's current area of interest and significantly improves subjective image quality.
[0037] 2. High efficiency and low power consumption: By making decisions based on the gaze direction, irrelevant acquisition units (such as suppressing cameras in non-gaze directions in a dual-camera scheme) can be turned off or their working status optimized, significantly reducing system power consumption.
[0038] 3. Low latency and high smoothness: The introduction of an eye-tracking trend prediction algorithm can trigger the switching of the acquisition mode in advance, effectively eliminating the perceptible delay caused by the switching of gaze, and ensuring a smooth and comfortable visual experience.
[0039] 4. Ingenious structure and versatility: The application of technologies such as half-eye image acquisition reduces the requirements for sensor hardware, making it easy to integrate into various eyeglass frames and broadening the productization path. Attached Figure Description
[0040] Figure 1 This is a schematic diagram of the overall structure of the present invention (Embodiment 1);
[0041] Figure 2 for Figure 1 A schematic diagram of a partial explosion (Example 1);
[0042] Figure 3 This is a schematic diagram of the overall structure of the present invention (Embodiment 2);
[0043] Figure 4 for Figure 1 A schematic diagram of a partial explosion (Example 2);
[0044] The attached diagram lists the components represented by each number as follows:
[0045] 1-Eyeglasses frame, 2-Image acquisition unit, 21-Focusing camera module, 22-Close-up fixed-focus camera, 23-Long-range fixed-focus camera, 3-Main control unit, 4-Eye tracking sensor, 5-Folding optical display module, 6-External display screen. Detailed Implementation
[0046] Please see Figure 1-2 This utility model provides a technical solution:
[0047] Example 1: Intelligent Focusing System Based on Focusing Camera Module
[0048] See Figure 1 and Figure 2 This embodiment demonstrates the core closed-loop control process of this invention. An eye-tracking sensor 4 (preferably mounted on both sides of the bridge of the nose) continuously collects images of the user's eyes. After receiving the data, the main control unit 3 first identifies the pupil center coordinates using an image algorithm and calculates the gaze vector, thereby determining whether the user's current gaze direction is a distant scene (such as looking out a window) or a near scene (such as reading a book).
[0049] Workflow: If a distant view is detected, the main control unit 3 immediately sends a set of instructions to the focusing camera module 21: ① Drive the motor to move the lens group to the "telephoto" focal length position; ② Activate the center region super-resolution algorithm in the image signal processor (ISP) to sharpen and enhance details in the central 1 / 3 area of the image. If a close-up view is detected, the instructions are: ① Drive the lens group to move to the "close-up" focal length; ② Switch to wide-angle mode to expand the field of view (FOV) to cover a wider near field of view. This scheme achieves precise matching between the acquisition strategy and the visual intent.
[0050] Example 2: High-efficiency switching system based on fixed-focus camera combination
[0051] See Figure 2 and Figure 4 In this embodiment, another technical approach is adopted. The image acquisition unit 2 consists of a close-up fixed-focus camera 22 with a large field of view and a short focal length (e.g., an equivalent focal length of 28mm) and a long-range fixed-focus camera 23 with a small field of view and a long focal length (e.g., an equivalent focal length of 85mm).
[0052] Workflow: The main control unit 3 intelligently selects the data source based on the eye-tracking results. When the user is looking at a distant object, the main control unit 3 uses the image captured by the distant fixed-focus camera 23 as the main signal source for output, while completely ignoring the data stream from the close-up fixed-focus camera 22, or reducing its weight to a very low level for auxiliary calculations. This can save nearly 50% of image processing power consumption. When the user is looking at a close object, the close-up camera 22 is activated, and the distant camera 23 is suppressed. This solution achieves mode switching through hardware switching rather than mechanical movement, resulting in faster speed and higher reliability.
[0053] In addition, it should be noted that the fixed-focus camera module used in image acquisition unit 2 is not limited to the fixed-focus combination of near-focus and far-focus mentioned above. It may also be a single fixed-focus camera. Full-resolution cameras, which are increasingly widely used now, can achieve direct acquisition of full-resolution images within a certain focal length range. For example, extended depth-of-field (EDoF) cameras achieve clear image acquisition within a certain object distance range through special optical design and image processing algorithms. These will not be listed one by one here.
[0054] Example 3: Half-eye image acquisition and high-precision reconstruction
[0055] See Figure 2 and Figure 4 To address the issue of limited internal space in eyeglasses, the eye-tracking sensor 4 in this embodiment employs a half-eye image acquisition mode. Because it is mounted at an angle to the side of the nose, its field of view only covers the lower half of the eyeball (including part of the pupil and iris).
[0056] Workflow: The main control unit 3 does not require a complete eye image. Its built-in dedicated processor extracts key features (such as pupil edge curvature and iris texture) from local images. The processor then accesses a dynamic context memory library, which stores eye movement feature vectors from the most recent seconds in a temporal sequence. Using a 3D attention mechanism algorithm, the system correlates and fuses the local features of the current frame with the historical sequence to accurately calculate the complete eye orientation and gaze coordinates. This method achieves high-precision tracking with low-cost hardware.
[0057] Example 4: Predictive Control to Eliminate Delay
[0058] To create a seamless experience, a time-series prediction network (such as LSTM) is integrated into the main control unit 3.
[0059] Workflow: The network continuously analyzes the trajectory, speed, and acceleration of eye movements. When it detects that the eye is moving to the right at a high speed, the network predicts that the user's gaze will fall on the right-hand area approximately 50ms later. Based on this prediction, the main control unit 3 can send an instruction to the image acquisition unit 2 in advance to begin adjusting the exposure and focus parameters of the right-hand area. By the time the user's gaze actually reaches the target, the system has already completed the adjustment, achieving a "zero" latency visual experience.
[0060] Example 5: System Expansion and Functional Synergy
[0061] This embodiment adds more functional modules to the basic system, demonstrating the scalability of this invention.
[0062] Synchronous adjustment of refractive power: While issuing image acquisition commands, the main control unit 3 can also issue commands to the refractive power correction module to adjust its refractive power to a preset value that matches the current viewing distance, thereby achieving dual optimization of vision and refractive power.
[0063] External status display: The main control unit 3 can send the current working mode (such as "far-distance mode" or "reading mode") to the external display screen 6 in the form of icons for display. The external display screen 6 is integrated and set at the eye position on the external mirror surface to enhance human-computer interaction.
[0064] Adaptive lighting: In low-light environments, the main control unit 3 dynamically adjusts the brightness of the lighting unit (infrared LED) based on the exposure value of the image from the eye sensor 4, and even switches between "bright pupil" and "non-bright pupil" modes to always ensure tracking accuracy.
[0065] Based on the above embodiments, the following examples from real-world scenarios will be used to illustrate the points:
[0066] Scenario 1: Outdoor navigation and information browsing (based on a dual-core fixed-focus camera solution)
[0067] User behavior: When a user is walking on the street wearing glasses, they need to see the road signs and buildings in the distance at times, and check the information on the smartwatch on their wrist at other times.
[0068] Power consumption analysis of traditional solutions:
[0069] Two fixed-focus cameras, one for distant views and one for close-up views, need to work continuously and simultaneously to capture two high-definition video streams.
[0070] The main control unit needs to continuously perform complex image stitching or fusion calculations on the two video streams to provide a complete picture. This process places extremely high demands on the processor's computing power and consumes a huge amount of power.
[0071] Result: The device gets noticeably hot in a short time, and its battery life is significantly shortened.
[0072] Power consumption optimization demonstration of this utility model:
[0073] Intent perception: The eye-tracking sensor monitors in real time that the user's eyes are raised and their gaze is focused on a distant road sign. The main control unit immediately recognizes "distant gaze".
[0074] Precise resource allocation:
[0075] Activate key unit: Immediately activate the long-range fixed-focus camera.
[0076] Non-critical units are shut down: Simultaneously, a sleep or power-off command is sent to the close-up fixed-focus camera, causing it to completely cease operation. This directly saves power consumption for the close-up camera itself.
[0077] Reduced processing load: The main control unit only needs to process the video stream from a single distant camera, eliminating the need for complex dual-channel data fusion calculations. The image processor's load can be reduced by more than 50%, significantly lowering the power consumption of the core computing unit.
[0078] Performance Improvement: Due to resource concentration, the system can use all its computing power to optimize the clarity and detail of distant images, making road sign text exceptionally clear and improving the performance of core tasks.
[0079] Dynamic switching: When the user's gaze shifts down to their wrist, the system completes the switching within milliseconds: the distant camera goes into sleep mode, and the close-up camera starts up and optimizes processing. The entire process is efficient and seamless.
[0080] Conclusion: In this scenario, this invention achieves significant power saving and precise performance delivery through the strategies of "selective hardware activation" and "dynamic load adjustment".
[0081] Scenario 2: Indoor long-term reading and document processing (based on a focus-adjustable camera solution)
[0082] User behavior: Users sit at their desks and spend long periods of time reading documents or paper files on their computer screens, with their eyes primarily focused on the immediate surroundings.
[0083] Power consumption analysis of traditional solutions:
[0084] To cope with possible changes in field of view, a focusing camera needs to continuously perform small-range "search-style" autofocus or maintain a compromise focal length, but this will result in less than ideal close-up details.
[0085] Continuous focus motor driving and image analysis also result in unnecessary power consumption.
[0086] Power consumption optimization demonstration of this utility model:
[0087] Intent perception and locking: The system recognizes that the user has entered a continuous "close-range gaze" state and the line of sight moves smoothly on the near plane.
[0088] Stable working status:
[0089] Fixed optical parameters: After the main control unit controls the focusing camera module to focus to the optimal close distance in one go, the frequent fine-tuning drive of the focusing motor can be greatly reduced or stopped, saving the power consumption of mechanical drive.
[0090] Optimization strategy: The system switches to "close-up mode" and disables or reduces image algorithms optimized for distant scenes (such as long-distance super-resolution), instead running algorithms more suitable for close-up scenes (such as widening the field of view and text sharpening). This algorithm-level "burden reduction" also reduces power consumption.
[0091] Predictive Sleep Mode: Combining the predictive control from Example 4, if the system detects that the user has entered a prolonged period of deep reading (reduced rapid eye saccades), it can further reduce the frame rate or resolution of image acquisition, entering a "low-power monitoring" state. Once it detects a significant shift in the gaze, it quickly restores full performance. This is similar to the automatic brightness adjustment and sleep mechanism of a mobile phone screen, further unlocking energy-saving potential.
[0092] Conclusion: In static or semi-static scenarios, this invention achieves long-term power consumption optimization by locking the working mode, reducing unnecessary mechanical movement and algorithm complexity, and greatly improves the device's battery life.
Claims
1. An electronic myopia glasses with eye-tracking image acquisition and feedback, characterized in that: include: Eyeglass frames; An image acquisition unit is mounted on the eyeglasses frame and is used to acquire images of the external scene. The main control unit is located inside the eyeglass frame and is electrically connected to the image acquisition unit; A catadioptric optical display module is mounted on the eyeglass frame and electrically connected to the main control unit, used to display the image processed by the main control unit; An eye-tracking sensor, mounted on the eyeglasses frame, is used to collect the user's eye movement data; The main control unit is communicatively connected to the eye-tracking sensor and is configured as follows: The user's gaze direction is identified based on the eye movement data; Based on the identified gaze direction, control commands are generated to adjust the operating mode of the image acquisition unit, thereby outputting an optimized image signal that matches the gaze direction.
2. The electronic myopia glasses with eye-tracking image acquisition and feedback according to claim 1, characterized in that: Also includes: A diopter correction module, integrated into the optical path of the catadioptric optical display module, is used to adjust the diopter of the output beam; The main control unit is further configured to generate control commands based on the identified gaze direction to synchronously adjust the refractive power parameters of the refractive power correction module.
3. An electronic myopia glasses with eye-tracking image acquisition and feedback according to claim 1 or 2, characterized in that: The eye-tracking sensors are located on both sides of the bridge of the nose and / or the inside of the eyeglass frame.
4. The electronic myopia glasses with eye-tracking image acquisition and feedback according to claim 1, characterized in that: The image acquisition unit is a focusing camera module, used for automatic focusing within a preset focal length range.
5. The electronic myopia glasses with eye-tracking image acquisition and feedback according to claim 4, characterized in that: The main control unit is configured as follows: When the gaze direction is detected to be a distant scene, the focusing camera module is controlled to focus on the telephoto mode and the resolution of the central area of the image is improved. When the gaze direction is detected to be close-up, the focusing camera module is controlled to focus to close-up mode and the image field of view is expanded.
6. The electronic myopia glasses with eye-tracking image acquisition and feedback according to claim 1, characterized in that: The image acquisition unit is a fixed-focus camera module assembly, including a close-up fixed-focus camera for acquiring close-up images and a distant fixed-focus camera for acquiring distant images.
7. The electronic myopia glasses with eye-tracking image acquisition and feedback according to claim 6, characterized in that: The main control unit is configured as follows: When the gaze direction is detected to be a distant scene, the distant fixed-focus camera is activated as the main image source and the data from the close-up fixed-focus camera is suppressed. When the gaze direction is detected to be close-up, the close-up fixed-focus camera is activated as the main image source and the data from the distant fixed-focus camera is suppressed.
8. The electronic myopia glasses with eye-tracking image acquisition and feedback according to claim 1, characterized in that: The main control unit is configured to: predict eye movement trends based on the trajectory and speed of eye movements, and based on the prediction results, initiate an adjustment command to the working mode of the image acquisition unit in advance before the user's gaze switches to a new target.
9. The electronic myopia glasses with eye-tracking image acquisition and feedback according to claim 1, characterized in that: The eye-tracking sensor is configured to acquire half-eye images, capturing only a local area of the eyeball; the main control unit is configured to reconstruct the complete eye movement trajectory based on the local eyeball image data using a dynamic context memory library.
10. An electronic myopia glasses with eye-tracking image acquisition and feedback according to claim 9, characterized in that: The dynamic context memory stores historical eye-tracking feature vectors, and the main control unit fuses the current frame data with the historical feature vectors based on a three-dimensional attention mechanism to predict the gaze point shift trend.