Visual function detection system for amblyopic children based on virtual reality technology

Abstract

The present invention discloses a system for detecting visual function of children with amblyopia based on virtual reality technology, comprising an eye detection module, an external detection module, a processing module, and a display module. The eye detection module is used to collect eye images; the external detection module is used to collect action instructions and action information; the processing module is used to adjust the detection process according to the action instructions, generate a detection image based on the detection process, analyze the eye image and action information, and calculate the analysis results based on the detection process to generate a visual function detection result; and the display module is used to display the detection image using virtual reality technology. This system can detect the visual function of children with amblyopia in real time and intelligently.

Description

Technical Field

[0001] The present invention relates to the field of intelligent detection technology, and in particular to a visual function detection system for children with amblyopia based on virtual reality technology. Background Art

[0002] Amblyopia is a common eye disease in children in ophthalmology clinic. It is a state of visual impairment caused by the inability to receive appropriate visual stimulation during infancy due to various reasons such as perception, movement, conduction and visual center, which affects visual development. It is mainly manifested as low vision and binocular single vision dysfunction. The hazards of amblyopia are often discussed, involving many aspects, usually the following aspects. The most common hazard is low vision. Amblyopic patients have poor monocular fixation ability and cannot form normal stereoscopic vision. The third point is that in addition to the physical damage to the patient's vision, amblyopic patients also have a certain psychological impact. However, the current detection of amblyopia requires going to the hospital for a special test by a doctor. During the doctor's test, the symptoms need to be manually diagnosed. There are no relevant instruments and equipment for the detection of the visual function of children with amblyopia in the existing technology, resulting in the lack of real-time and intelligent detection of the visual function of children with amblyopia. Summary of the Invention

[0003] In order to solve the problem that the visual function detection of amblyopic children in the above-mentioned existing technology is not real-time and intelligent enough, the present invention provides a visual function detection system for amblyopic children based on virtual reality technology, which can detect the visual function of amblyopic children in real time and intelligently.

[0004] In order to achieve the above technical objectives, the present invention provides a system for detecting visual function of amblyopic children based on virtual reality technology, comprising

[0005] Eye detection module, in vitro detection module, processing module, display module;

[0006] The processing module is connected to the eye detection module, the in-vitro detection module, and the display module respectively;

[0007] The eye detection module is used to collect eye images;

[0008] The in vitro detection module is used to collect action instructions and action information;

[0009] The processing module is used to adjust the detection process according to the action instruction, generate a detection picture based on the detection process, analyze the eye image and action information, and calculate the analysis result based on the detection process to generate a visual function test result;

[0010] The display module is used to display the detection image through virtual reality technology.

[0011] Optionally, the eye detection module includes a video acquisition unit and an extraction unit

[0012] The video acquisition unit is used to acquire eyeball videos; the extraction unit is used to extract key frames from the eyeball videos to obtain eyeball images.

[0013] Optionally, the in vitro detection module includes a motion instruction detection unit and a motion information detection unit;

[0014] The motion instruction detection unit is used to detect motion instructions, wherein the motion instructions are a variety of different gestures; the motion information detection unit is used to detect motion information.

[0015] Optionally, the processing module includes a process unit, a detection picture unit, and an amblyopia detection unit;

[0016] The process unit is used to set the detection process and adjust the detection process based on the action instruction, wherein the detection process includes light perception detection, color perception detection, shape perception detection, contrast perception detection, and stereo perception detection;

[0017] The detection image unit is used to generate a detection image according to the detection process;

[0018] The amblyopia detection unit is used to calculate the aggregation situation of the eye image and identify the eye position, and to perform action recognition on the action information. Based on the detection process, the calculation results, eye position recognition results and action recognition results are statistically analyzed, and visual function detection results are generated according to the statistical results, wherein the visual function detection results include scores under different detection processes.

[0019] Optionally, the display model includes a wearable device and left and right eye display units;

[0020] The wearable device is used to fix the left and right eye display units; the left and right eye display units are used to display detection pictures through virtual reality technology, wherein the detection pictures include left eye detection pictures and right eye detection pictures.

[0021] Optionally, the system further includes a voice module; the voice module is connected to the processing module;

[0022] The voice module is used to generate voice instructions; the processing module is also used to receive voice instructions, replace the action instructions with voice instructions, and adjust the detection process according to the voice instructions.

[0023] Optionally, the detection image unit is connected to a cloud database.

[0024] The cloud database is used to store detection images under different detection processes;

[0025] The detection picture unit is further configured to store the generated detection pictures in a cloud database and extract the detection pictures in the cloud database based on the detection process.

[0026] Optionally, the system further includes the communication module,

[0027] The communication module is connected to the processing module;

[0028] The communication module is used to establish communication with a mobile terminal, and after the communication is established, transmit the child's amblyopia visual function detection result to the mobile terminal, wherein the mobile terminal includes a mobile phone, a tablet computer and a laptop computer.

[0029] The present invention has the following technical effects:

[0030] The present invention adjusts the detection process through the processing module, and uses virtual reality technology through the display module to display the detection pictures corresponding to the detection process. During the display process, the patient's eye information is collected through the eye detection module, and the patient's movement information is collected through the movement detection module. The above patient information data is processed and analyzed to generate the child's visual function detection results. The system provided by the present invention can detect the child's visual function in real time. At the same time, there is no need for human control and analysis during the detection process, realizing automated and intelligent visual function detection of amblyopic children, which is very practical. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0032] Figure 1 A schematic diagram of a system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0034] In order to solve the problems in the prior art of visual function detection for amblyopic children that are not real-time and intelligent enough, the present invention provides the following solutions:

[0035] like Figure 1The present invention provides a system for detecting visual function of amblyopic children based on virtual reality technology, comprising:

[0036] An eye detection module, an in vitro detection module, a display module, and a processing module, wherein the processing module is connected to the eye detection module, the in vitro detection module, and the display module respectively;

[0037] The eye detection module is used to collect eye images; the eye detection module includes a video acquisition unit and an extraction unit

[0038] The video acquisition unit is used to capture eyeball video; the extraction unit is used to extract key frames from the eyeball video to obtain an eyeball image. The video acquisition unit uses a miniature camera installed on a wearable device. When the user uses the wearable device for testing, the video acquisition unit captures the patient's eyeball video in real time. The extraction unit sets a certain acquisition and extraction cycle, extracts the key frame images of the video acquisition unit, and transmits the extracted images to the processing module via Bluetooth technology. After extraction, the extraction module performs pre-processing operations such as image enhancement and image normalization on the image to enhance the recognition of the image content.

[0039] The in vitro detection module is used to collect motion instructions and motion information; the in vitro detection module includes a motion instruction detection unit and a motion information detection unit; the motion instruction detection unit is used to detect motion instructions, wherein the motion instructions are a variety of different gestures; the motion information detection unit is used to detect motion information. The in vitro detection module uses a Kinect somatosensory sensor to capture the patient's movements in real time and recognize the patient's movements. In the setting of motion instructions, simple and easy-to-recognize gestures are used for setting, and the user can input different gestures and enter corresponding motion instructions for setting. The collection of motion information can also be achieved through the Kinect somatosensory sensor, which performs real-time detection in the detection process and converts the motion information into related image data containing key joints of the human body and transmits it to the processing module.

[0040] The processing module is used to adjust the detection process according to the action instruction, generate a detection picture based on the detection process, analyze the eye image and action information, and calculate the analysis result based on the detection process to generate a visual function detection result; the processing module includes a process unit, a detection picture unit, and an amblyopia detection unit;

[0041] The process unit is used to set the detection process and adjust the detection process based on the action instruction, wherein the detection process includes multiple detection schemes, including red-green separation detection, stereoscopic vision detection, anisotropia detection, near vision detection, horizontal and vertical heterophoria detection, collective near point detection, and adjustment flexibility detection.

[0042] The process unit first sets up the test process. During the setup process, the duration of the test process, the intervals between different tests within the test process, and the test sequence for different test schemes are set. These parameters have initial defaults and can be used normally without setting them. After the test process is set up, the start, pause, and end of the test process are adjusted through action commands.

[0043] The detection image unit is used to generate a detection image according to the detection process;

[0044] During different detection processes, corresponding detection images are generated. For example, when detecting in a red-green separation manner, the detection image unit generates a left-eye image with two different symbols, a symbol with the same shape and position as the left-eye image, and a right-eye image with two symbols whose positions and shapes are different from the other symbol in the left-eye image. At the same time, red and green filters are added to the left-eye image and the right-eye image respectively. The user makes a first action to indicate what they see. During stereoscopic vision detection, the left eye and the right eye generate different stereoscopic sight mark images respectively, and the user makes a second action to indicate what they see. During unequal image detection, the left eye and the right eye generate unequal image sight mark images respectively. For near vision detection, the left eye and the right eye generate a series of images with symbols from large to small at different times. For horizontal and vertical heterophoria detection, the left eye generates a symbol in the middle of the image, and the right eye generates a series of images with symbols moving from the right side to the left side of the image. For collective near point detection, a series of images from small to large are generated. For adjustment flexibility detection, a series of images with different blur but some of them are clear are generated.

[0045] The amblyopia detection unit is used to calculate the aggregation situation of the eye image and identify the eye position, and to perform action recognition on the action information. Based on the detection process, the calculation results, eye position recognition results and action recognition results are statistically analyzed, and visual function detection results are generated according to the statistical results, wherein the visual function detection results include scores under different detection processes.

[0046] During the above-mentioned detection, the eye image and motion information are received in real time, the time under different process schemes is recorded, and the time domain information is used to correspond to the eye image and motion information. Under the red-green separation detection method, the motion information is identified, the number and color of the symbols seen are identified, and the data is recorded. If there are 4 different colors, it is normal, 2 or 3 red or green symbols are recorded as 1, and 5 symbols are recorded as 2. During stereoscopic vision, the motion information is identified. If there are two lines and one point, it is normal. Three lines and one point are recorded as 1, and four lines and one point are recorded as 2. During unequal image detection, the motion information is identified to determine whether the size is the same. If the size is the same, it is normal. A difference of half a frame is recorded as 1, and a frame is recorded as 2. For near vision detection, the left and right eyes are tested separately, and finally the left and right eyes are tested together. A series of symbols are played in sequence from large to small. When an unclear image appears, the image is recorded. The size of the symbol on the image is used to read the degree of myopia or hyperopia corresponding to the size of the symbol. When detecting horizontal and vertical heterophoria, the eye image is collected, the aggregation in the eye image is identified, and the size and position of the eye are identified. The action information is identified. The degree of strabismus of the eye when it is clear is calculated through the size and position of the eye, and different degrees of strabismus are scored. The near point detection is integrated, the action information is identified, the time when the blur just occurred is determined, the position and aggregation in the eye image are identified, and then the clearest time before is returned. The eye image is identified, and the aggregation and position are calculated. The distance represented by the calculated image is the inverse of the reading of the near point adjustment. When detecting the flexibility of adjustment, the number of times the action display can see a clear image is identified and the number is recorded. The action information in the above content can be pre-set before use, and a number is set to represent the action and the action is determined. The test results of the above different detection schemes are integrated, and different test results are counted to generate the visual function test results of amblyopic children.

[0047] The display module is used to display the detection images. The display module includes a wearable device and left and right eye display units. The wearable device is used to secure the left and right eye display units. The left and right eye display units are used to display the detection images, which include left and right eye detection images. The wearable device serves as the carrier for the VR glasses, and its display is a left-eye display. By placing the left and right eye detection images into the left and right eye displays, respectively, the images are displayed, recording the child's movements and performing calculations on the eye image.

[0048] The system also includes a voice module connected to the processing module; the voice module is configured to generate voice instructions; the processing module is further configured to receive voice instructions, replace action instructions with voice instructions, and adjust the detection process based on the voice instructions. The voice module inputs voice instructions through voice, and replaces the voice instructions with action instructions in the processing module. The voice module can also input voice data, which is transmitted to the processing module, and different voice data is used to replace the action information to execute different operations in the action information.

[0049] The detection picture unit is connected to a cloud database, which is used to store detection pictures under different detection processes; the detection picture unit is also used to store the generated detection pictures in the cloud database, and extract the detection pictures in the cloud database based on the detection process.

[0050] The system further includes a communication module connected to the processing module; the communication module is configured to establish communication with a mobile terminal and, after communication is established, transmit the child's amblyopia visual function test results to the mobile terminal, wherein the mobile terminal includes a mobile phone, a tablet computer, and a laptop computer. The visual function test results can be effectively identified anytime and anywhere through the mobile terminal.

[0051] This system also includes a remote communication module, which is connected to the processing module and the display acquisition module through the remote communication module, and transmits the data collected by the eye acquisition module and the motion acquisition module, as well as the data generated in the detection process of the processing module to the hospital server. The hospital server is connected to the processing module, and the hospital staff performs relevant score evaluation and judgment to generate the final detection results.

[0052] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A visual function detection system for amblyopic children based on virtual reality technology, characterized by: include: Eye detection module, in vitro detection module, processing module, display module; The processing module is connected to the eye detection module, the in-vitro detection module, and the display module respectively; The eye detection module is used to collect eye images; The in vitro detection module is used to collect action instructions and action information; The processing module is used to adjust the detection process according to the action instruction, generate a detection picture based on the detection process, analyze the eye image and action information, and calculate the analysis result based on the detection process to generate a visual function test result; The display module is used to display the detection image through virtual reality technology; The processing module includes a process unit, a detection picture unit, and a low vision detection unit; The process unit is used to set the detection process and adjust the detection process based on the action instruction, wherein the detection process includes light perception detection, color perception detection, shape perception detection, contrast perception detection, and stereo perception detection; The detection image unit is used to generate a detection image according to the detection process; The amblyopia detection unit is used to calculate the aggregation of the eye image and identify the eye position, and perform action recognition on the action information. Based on the detection process, the calculation results, the eye position recognition results, and the action recognition results are statistically analyzed, and a visual function test result is generated based on the statistical results, wherein the visual function test result includes scores under different detection processes; During the above-mentioned detection, the eye image and motion information are received in real time, the time under different process schemes is recorded, and the time domain information is used to correspond to the eye image and motion information. Under the red-green separation detection method, the motion information is identified, the number and color of the symbols seen are identified, and the data is recorded. If there are 4 different colors, it is normal, 2 or 3 red or green symbols are recorded as 1, and 5 symbols are recorded as 2. During stereoscopic vision, the motion information is identified. If there are two lines and one point, it is normal. Three lines and one point are recorded as 1, and four lines and one point are recorded as 2. During unequal image detection, the motion information is identified to determine whether the size is the same. If the size is the same, it is normal. A difference of half a frame is recorded as 1, and a frame is recorded as 2. For near vision detection, the left and right eyes are tested separately, and finally the left and right eyes are tested together. A series of symbols are played in sequence from large to small. When an unclear image appears, the size of the symbol on the image is recorded, and the myopia or hyperopia corresponding to the symbol size is read. Degree, horizontal and vertical heterophoria detection, collect eye images, identify the aggregation in the eye images, and identify the size and position of the eye, identify action information, calculate the degree of eye strabismus when clear through the size and position of the eye, and assign scores to different degrees of strabismus, collect near point detection, identify action information, determine the time when it just became blurred, identify the position and aggregation in the eye image, and then return to the clearest time before, identify the eye image, calculate the aggregation and position, and calculate the distance represented by the pictures, which is the inverse of the reading of the adjusted near point. When adjusting flexibility detection, identify the number of times the action display can see a clear image, and record the number. The action information in the above detection is pre-set before use, and a number is set to represent the action to determine the action; the test results of the above different detection schemes are integrated, and different test results are counted to generate visual function test results for amblyopic children.

2. The system for detecting visual function of amblyopic children based on virtual reality technology according to claim 1, characterized in that: The eye detection module includes a video acquisition unit and an extraction unit The video acquisition unit is used to acquire eyeball videos; the extraction unit is used to extract key frames from the eyeball videos to obtain eyeball images.

3. The system for detecting visual function of amblyopic children based on virtual reality technology according to claim 1, characterized in that: The in-vitro detection module includes a motion instruction detection unit and a motion information detection unit; The motion instruction detection unit is used to detect motion instructions, wherein the motion instructions are a variety of different gestures; the motion information detection unit is used to detect motion information.

4. The system for detecting visual function of amblyopic children based on virtual reality technology according to claim 1, characterized in that: The display module includes a wearable device and left and right eye display units; The wearable device is used to fix the left and right eye display units; the left and right eye display units are used to display detection pictures through virtual reality technology, wherein the detection pictures include left eye detection pictures and right eye detection pictures.

5. The visual function detection system for amblyopic children based on virtual reality technology according to claim 1, characterized in that: The system further includes a voice module; the voice module is connected to the processing module; The voice module is used to generate voice instructions; the processing module is also used to receive voice instructions, replace the action instructions with voice instructions, and adjust the detection process according to the voice instructions.

6. The system for detecting visual function of amblyopic children based on virtual reality technology according to claim 1, characterized in that: The detection image unit is connected to a cloud database, The cloud database is used to store detection images under different detection processes; The detection picture unit is further configured to store the generated detection pictures in a cloud database and extract the detection pictures in the cloud database based on the detection process.

7. The system for detecting visual function of amblyopic children based on virtual reality technology according to claim 1, characterized in that: The system further comprises a communication module, The communication module is connected to the processing module; The communication module is used to establish communication with a mobile terminal, and after the communication is established, transmit the visual function test result to the mobile terminal, wherein the mobile terminal includes a mobile phone, a tablet computer and a laptop computer.

Images