Visual field detection method and device and visual field detection equipment

By acquiring multi-frame detection data and calculating focus information using the target field of view detection model, the problem of manual feedback in the prior art affecting the reliability of the result is solved, and the accuracy and reliability of field of view detection are improved.

CN119033326AActive Publication Date: 2024-11-29SHANGHAI UNITED IMAGING METAHEALTHCARE CO LTD
View PDF 10 Cites 0 Cited by

Patent Information

Application Number
CN202411164626.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-22
Publication Date
2024-11-29
Estimated Expiration
2044-08-22

AI Technical Summary

Technical Problem

In the existing visual field detection methods, patients need to manually feedback the stimulus points, which are susceptible to inattention or inability to correctly detect the stimulus points, resulting in low reliability of the results.

Method used

By acquiring multi-frame detection data, using the preset target field of view detection model, the focus information of the detection object, including the concentration results and observation results of the stimulus points, generate field of view detection results, avoid manual feedback, and reduce subjectivity errors.

Benefits of technology

It improves the accuracy of visual field detection results, reduces the complexity of interaction, and enhances the reliability of detection results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119033326A_ABST
    Figure CN119033326A_ABST
Patent Text Reader

Abstract

The invention relates to a visual field detection method, a visual field detection device and visual field detection equipment. Obtaining multi-frame detection data, obtaining focusing information of the detection object according to the multi-frame detection data and a preset target visual field detection model, and obtaining a visual field detection result of the detection object according to the focusing information; the detection data comprises visual physiological data of the detection object in the process that the visual field detection equipment displays the stimulation point, and the focusing information comprises an attention concentration result of the detection object and an observation result of the detection object on the stimulation point. In the embodiment of the invention, the focusing information is obtained based on the visual physiological data of the detection object in the process of displaying the stimulation point by the visual field detection equipment, and the visual field detection result is generated based on the focusing information, that is, the detection object does not need to press a button to carry out manual feedback when watching the stimulation point, and the visual field detection result is generated according to the feedback result; the complexity of interaction is reduced, subjective errors caused by manual feedback are avoided, and the accuracy of a visual field detection result is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a visual field detection method, device and visual field detection equipment. Background Art

[0002] Visual field testing is a non-invasive examination method that helps detect diseases early and monitor disease progression. If the visual field test results show visual field loss, the doctor may conduct further examinations to determine the cause of the visual field loss and select appropriate treatment options such as medication, surgery, etc. based on the type and stage of the disease.

[0003] In the current visual field detection method, the patient needs to press the trigger of the visual field detection device to provide feedback when seeing the stimulation point displayed on the visual field detection device. The patient may become inattentive or unable to correctly perceive the stimulation point, resulting in the feedback result being greatly affected by subjectivity, thereby making the reliability of the visual field detection result low. Summary of the invention

[0004] Based on this, it is necessary to provide a visual field detection method, device and visual field detection equipment that can improve the accuracy of visual field detection results in response to the above technical problems.

[0005] In a first aspect, the present application provides a visual field detection method, comprising:

[0006] Acquire multiple frames of detection data; the detection data includes visual physiological data of the detection object during the process of the visual field detection device displaying the stimulation point;

[0007] Obtaining focus information of the detection object according to the multiple frames of detection data and a preset target visual field detection model; the focus information includes the attention concentration result of the detection object and the observation result of the detection object on the stimulation point;

[0008] A visual field detection result of the detection object is obtained according to the focusing information.

[0009] In one embodiment, obtaining the focus information of the detection object according to the multiple frames of detection data and a preset target field of view detection model includes:

[0010] Normalizing each of the detection data according to the data type to obtain a plurality of normalized detection data;

[0011] The focusing information is obtained according to the plurality of normalized detection data and the target field of view detection model.

[0012] In one embodiment, the normalized detection data includes normalized optical axis vectors of the eyes of the detection object and a normalized fixation point of the visual field detection device; and obtaining the focusing information according to the normalized detection data and the target visual field detection model includes:

[0013] For each frame of the normalized optical axis vectors of the eyes, based on the attribute parameters of the visual field detection device and the normalized optical axis vectors of the eyes, determining the normalized visual line intersection point of the detection object in the visual field detection device;

[0014] Determining a normalized fixation point offset according to a difference between the normalized sight line intersection point and the normalized fixation point;

[0015] Determining a normalized optical axis vector difference between the eyes of the detection object based on a difference in normalized optical axis vectors between the eyes of the detection object;

[0016] Each of the normalized detection data, each of the normalized fixation point offsets and each of the normalized optical axis vector differences are input into the target visual field detection model to obtain the focusing information.

[0017] In one embodiment, the step of inputting each of the normalized detection data, each of the normalized fixation point offsets, and each of the normalized optical axis vector differences into the target visual field detection model to obtain the focus information includes:

[0018] For each frame of the normalized detection data, the normalized detection data, the normalized fixation point offset and the normalized optical axis vector are spliced ​​to obtain sequence data;

[0019] Encoding the order relationship of the plurality of sequence data using the position encoding module in the target visual field detection model to obtain a plurality of initial feature vectors;

[0020] Using a feature encoding module in the target visual field detection model to perform feature extraction on the multiple initial feature vectors to obtain multiple target feature vectors;

[0021] Linear mapping is performed on the plurality of target feature vectors to obtain the focusing information.

[0022] In one embodiment, the feature encoding module in the target field of view detection model is used to extract features from the plurality of initial feature vectors to obtain each target feature vector, including:

[0023] Inputting the multiple initial feature vectors into the self-attention submodule in the feature encoding module for correlation processing to obtain multiple embedded feature vectors;

[0024] The multiple embedded feature vectors are input into the feedforward network submodule in the feature encoder module for nonlinear transformation processing to obtain the multiple target feature vectors.

[0025] In one embodiment, the method further comprises:

[0026] Acquiring training data; the training data includes visual physiological data of the test subject during the process of the visual field detection device displaying the stimulation point;

[0027] The initial visual field detection model is trained according to the training data and the standard focusing information corresponding to the training data to obtain the target visual field detection model; the standard focusing information includes the standard attention concentration result of the test subject and the standard observation result of the test subject on the stimulation point; the standard observation result is determined according to the stimulation intensity of the stimulation point and a preset stimulation intensity threshold; the standard attention concentration result is determined according to the loss of the fixation point, the feedback result of the test subject on the stimulation point and the standard observation result.

[0028] In a second aspect, the present application also provides a visual field detection device, comprising:

[0029] An acquisition module, used for acquiring multiple frames of detection data; the detection data includes visual physiological data of the detection object during the process of the visual field detection device displaying the stimulation point;

[0030] A first determination module is used to obtain focus information of the detection object according to the multiple frames of detection data and a preset target field of view detection model; the focus information includes the attention concentration result of the detection object and the observation result of the detection object on the stimulation point;

[0031] The second determination module is used to obtain the field of view detection result of the detection object according to the focusing information.

[0032] In a third aspect, the present application further provides a visual field detection device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0033] Acquire multiple frames of detection data; the detection data includes visual physiological data of the detection object during the process of the visual field detection device displaying the stimulation point;

[0034] Obtaining focus information of the detection object according to the multiple frames of detection data and a preset target visual field detection model; the focus information includes the attention concentration result of the detection object and the observation result of the detection object on the stimulation point;

[0035] A visual field detection result of the detection object is obtained according to the focusing information.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0037] Acquire multiple frames of detection data; the detection data includes visual physiological data of the detection object during the process of the visual field detection device displaying the stimulation point;

[0038] Obtaining focus information of the detection object according to the multiple frames of detection data and a preset target visual field detection model; the focus information includes the attention concentration result of the detection object and the observation result of the detection object on the stimulation point;

[0039] A visual field detection result of the detection object is obtained according to the focusing information.

[0040] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0041] Acquire multiple frames of detection data; the detection data includes visual physiological data of the detection object during the process of the visual field detection device displaying the stimulation point;

[0042] Obtaining focus information of the detection object according to the multiple frames of detection data and a preset target visual field detection model; the focus information includes the attention concentration result of the detection object and the observation result of the detection object on the stimulation point;

[0043] A visual field detection result of the detection object is obtained according to the focusing information.

[0044] The above-mentioned visual field detection method, device and visual field detection equipment obtain multiple frames of detection data, obtain the focusing information of the detection object according to the multiple frames of detection data and the preset target visual field detection model, and obtain the visual field detection result of the detection object according to the focusing information; the detection data includes the visual physiological data of the detection object during the process of the visual field detection device displaying the stimulation point, and the focusing information includes the attention concentration result of the detection object and the observation result of the detection object on the stimulation point. In the embodiment of the present application, the attention concentration result and the observation result are obtained based on the visual physiological data of the detection object during the process of the visual field detection device displaying the stimulation point and the target visual field detection model, and the visual field detection result is generated based on the attention concentration result and the observation result, that is, there is no need for the detection object to press a button for manual feedback when viewing the stimulation point, and the visual field detection result is generated according to the feedback result, which greatly reduces the complexity of the interaction, avoids the subjective error caused by manual feedback, and improves the accuracy of the visual field detection result. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 A diagram showing an application environment of a visual field detection method in an embodiment;

[0047] Figure 2 is a schematic flow chart of a visual field detection method in one embodiment;

[0048] Figure 3 is a flow chart of a visual field detection method in another embodiment;

[0049] Figure 4 is a flow chart of a method for determining focus information in one embodiment;

[0050] Figure 5 is a flow chart of a method for determining focus information in another embodiment;

[0051] Figure 6 is a flow chart of a method for determining focusing information in another embodiment;

[0052] Figure 7 is a schematic diagram of a target visual field detection model in one embodiment;

[0053] Figure 8 Schematic diagram of a flow chart of a method for determining a target feature vector in one embodiment;

[0054] Fig. 9 A schematic diagram of a flow chart of a method for determining a target visual field detection model in one embodiment;

[0055] Fig.10 is a flow chart of a visual field detection method in another embodiment;

[0056] Fig.11 FIG. 4 is a structural block diagram of a visual field detection device in one embodiment. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] The visual field detection method provided in the embodiment of the present application can be applied to Figure 1The application environment includes a visual field detection device, the internal structure of which can be shown as follows. Figure 1 As shown. The visual field detection device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the visual field detection device is used to provide computing and control capabilities. The memory of the visual field detection device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the visual field detection device is used to exchange information between the processor and the external device. The communication interface of the visual field detection device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network or other technologies. When the computer program is executed by the processor, a visual field detection method is implemented. The display unit of the visual field detection device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen, and the input device of the visual field detection device can be an external touchable display screen, or a button, trackball or touchpad set on the shell of the visual field detection device, or an external keyboard, touchpad or mouse, etc.

[0059] Optionally, the visual field detection device may be a wearable visual field detection device, for example, the visual field detection is integrated into a head mounted device, and the head mounted device may be a virtual reality (VR) device, an augmented reality (AR) device, a mixed reality (MR) device, smart glasses, etc. The visual field detection device may also be a non-wearable visual field detection device, such as a desktop detection device.

[0060] Those skilled in the art will understand that Figure 1 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the field of view detection device to which the scheme of the present application is applied. The specific field of view detection device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0061] In an exemplary embodiment, Figure 2 As shown, a visual field detection method is provided, which is applied to Figure 1 The visual field detection device in the example is used to illustrate, including the following S201 to S203. Among them:

[0062] S201, acquiring multiple frames of detection data; the detection data includes visual physiological data of the detection object during the process of the visual field detection device displaying the stimulation point.

[0063] Among them, the detection data includes the visual physiological data of the detection object during the process of the visual field detection device displaying the stimulus point. The visual physiological data can reflect the cognitive state and attention level of the detection object, and is not limited to visual stimulation. For example, pupil size is related to the level of psychological workload and the intensity of light stimulation; blinking can block visual input to reduce interference, and internal creative thinking usually leads to higher blinking frequency and longer blinking duration; eye convergence refers to the angle between the gaze lines of the right eye and the left eye. Eye convergence can be used to determine the change in the focus depth of the detection object on the visual input. Therefore, the visual physiological data of the detection object before and after the display of the nth stimulus point can be obtained, which can be the pupil diameter r t , the optical axis vector of the object's eyes , , blink frequencyb t and palpebral fissure height t Etc. t is the time corresponding to the detection data, that is, the number of frames corresponding to the detection data.

[0064] Optionally, the detection data may also include basic data of the detection object. For example, the detection object's age a, the detection object's pupil distance information p d etc.; the detection data may also include data related to the visual field detection device, such as the fixation point coordinates of the visual field detection device , the time when the nth stimulus point appears t n , the relative position of the nth stimulus point , the stimulation intensity L of the nth stimulation point n .

[0065] Optionally, the detection data may also include electroencephalogram (EEG) data of the detection subject during the process of the visual field detection device displaying the stimulation point.

[0066] In this embodiment, the detection data can be sent to the visual field detection device by other detection devices, or can be obtained from the corresponding system of the hospital, or can be collected by the visual field detection device, or can be input by the user. For example, the basic data of the detection object can be input by the user, or can be imported from the hospital system; the visual physiological data can be directly collected by the wearable visual field detection device from the detection object.

[0067] Combination Figure 3As shown, taking the visual field detection device as a head-mounted visual field detection device as an example, the head-mounted visual field detection device is started to ensure that each system of the head-mounted visual field detection device moves normally. Personalized parameter adjustment is performed based on the age information and pupil distance information of the detection object. The post-processing platform of the head-mounted visual field detection device determines the fixation point of the head-mounted visual field detection device based on the pupil distance information, and determines the stimulation point based on the age information, and outputs the fixation point and the stimulation point on the display screen. At the same time, the head-mounted visual field detection device is used to collect the visual physiological data of the detection object.

[0068] S202, obtaining focus information of the detection object according to the multi-frame detection data and a preset target field of view detection model; the focus information includes the attention concentration result of the detection object and the observation result of the detection object on the stimulation point.

[0069] Optionally, the target vision detection model can be an autoencoder, a long short-term memory network, or a convolutional neural network, etc.

[0070] In this embodiment, continue to combine the above Figure 3 As shown, multiple frames of detection data can be directly input into the target visual field detection model to obtain the attention concentration result of the detection object and the observation result of the detection object on the stimulation point. The attention concentration result is the degree of attention concentration of the detection object, and the observation result is the probability that the detection object sees the stimulation point.

[0071] In a possible implementation, the multi-frame detection data may be preprocessed and the preprocessed data may be input into the target field of view detection model to obtain focus information. For example, the detection data may be normalized, or abnormal data in the detection data may be removed, or the detection data may be deduplicated.

[0072] In one possible implementation, since the stimulation points include stimulation points that appear at multiple different times, the relative position and stimulation intensity of the stimulation points at the next moment can be adjusted in real time based on the focusing information, and the focusing information is subsequently determined based on the last adjusted stimulation points and other detection data.

[0073] S203, obtaining a visual field detection result of the detection object according to the focusing information.

[0074] In this embodiment, when the focusing information meets the preset requirements, the visual field detection result of the detection object is generated based on the relative position and stimulation intensity of the stimulation point. For example, the focusing information includes the detection object's concentration result and the detection object's observation result of the stimulation point. The preset requirements can be that the attention threshold is 60%, and the probability threshold of the detection object seeing the stimulation point is 70%. For one of the stimulation points, if the detection object's concentration result is greater than 60% and the observation result is greater than 70%, the relative position and stimulation intensity of the stimulation point are saved. Based on the stimulation intensity and relative position of the saved stimulation point, the visual field detection result of the detection object is generated.

[0075] In the above-mentioned visual field detection method, multiple frames of detection data are obtained, and the focus information of the detection object is obtained based on the multiple frames of detection data and a preset target visual field detection model, and the visual field detection result of the detection object is obtained based on the focus information; the detection data includes the visual physiological data of the detection object during the process of the visual field detection device displaying the stimulation point, and the focus information includes the attention concentration result of the detection object and the observation result of the detection object on the stimulation point. In the embodiment of the present application, the attention concentration result and the observation result are obtained based on the visual physiological data of the detection object during the process of the visual field detection device displaying the stimulation point and the target visual field detection model, and the visual field detection result is generated based on the attention concentration result and the observation result, that is, there is no need for the detection object to press a button for manual feedback when viewing the stimulation point, and the visual field detection result is generated based on the feedback result, which greatly reduces the complexity of the interaction, avoids the subjective error caused by manual feedback, and improves the accuracy of the visual field detection result.

[0076] Figure 4 FIG. 1 is a flow chart of a method for determining focus information in an embodiment. Figure 4 As shown, the embodiment of the present application relates to a possible implementation method of how to obtain focus information of a detection object based on multiple frames of detection data and a preset target field of view detection model, including the following steps:

[0077] S401, normalizing each detection data according to the data type to obtain a plurality of normalized detection data.

[0078] In this embodiment, each test data is normalized according to the data type to obtain multiple normalized test data. For example, if the test data is age, the age can be normalized by dividing it by 150 to obtain the normalized age; if the test data is pupil diameter, the pupil diameter of the test object is normalized based on the maximum value of the pupil diameter of each test object when the visual field detection device displays the stimulation point to obtain the normalized pupil diameter, that is, ; The test data is the blink frequency. The blink frequency of the test object is normalized based on the maximum value of the blink frequency of each test object when the visual field detection device displays the stimulation point, and the normalized blink frequency is obtained, that is, .

[0079] S402, obtaining focusing information according to a plurality of normalized detection data and a target field of view detection model.

[0080] In this embodiment, multiple normalized detection data can be input into the target field of view detection model to obtain focus information, or new data can be generated based on multiple normalized detection data, and the new data and the normalized detection data can be input into the target field of view detection model to obtain focus information. For example, the normalized detection data includes the normalized optical axis vectors of both eyes of the detection object, and the normalized optical axis vector difference can be obtained based on the normalized optical axis vectors of both eyes, and the normalized detection data and the normalized optical axis vector difference are input into the target field of view detection model to obtain focus information.

[0081] In an embodiment of the present application, each detection data is normalized according to the data type to obtain a plurality of normalized detection data, and focusing information is obtained based on the plurality of normalized detection data and a target field of view detection model, which can improve the efficiency and accuracy of determining the focusing information.

[0082] Figure 5 FIG. 1 is a flow chart of a method for determining focus information in another embodiment. Figure 5 As shown, the embodiment of the present application relates to a possible implementation method of how to obtain focusing information based on normalized detection data and a target field of view detection model, including the following steps:

[0083] S501 , for each frame of the normalized optical axis vectors of both eyes, determine the normalized sight line intersection point of the detection object on the visual field detection device based on the attribute parameters of the visual field detection device and the normalized optical axis vectors of both eyes.

[0084] In this embodiment, the attribute parameters of the visual field detection device include the simulated lens parameters and display screen parameters of the visual field detection device. For example, the normalized optical axis vector at time t is , Combined with the simulated lens parameters of the visual field detection device, the intersection points of the visual lines of the detected object on the visual field detection device are calculated respectively. and .

[0085] The sight line intersection point is normalized according to the display screen parameters of the visual field detection device, and the normalized sight line intersection point is , , w, h are the number of pixels of width and height of the display screen of the visual field detection device.

[0086] S502: Determine a normalized fixation point offset according to a difference between the normalized sight line intersection point and the normalized fixation point.

[0087] In this embodiment, the normalized fixation point offset can be obtained by taking the difference between the normalized sight intersection point and the normalized fixation point, that is, , .

[0088] S503 : determining a normalized optical axis vector difference between the two eyes of the detection object based on the difference in the normalized optical axis vectors between the two eyes of the detection object.

[0089] In this embodiment, the normalized optical axis vectors of the eyes of the detection object are , The difference is taken as the normalized optical axis vector difference between the two eyes of the detection object. .

[0090] S504, input each normalized detection data, each normalized fixation point offset and each normalized optical axis vector difference into a target visual field detection model to obtain focusing information.

[0091] In this embodiment, the normalized detection data, normalized fixation point offset and normalized optical axis vector difference corresponding to each frame are spliced ​​to obtain sequence data, and a plurality of sequence data are input into the target visual field detection model to obtain focusing information.

[0092] In an embodiment of the present application, for each frame of the normalized optical axis vector of both eyes, based on the attribute parameters of the visual field detection device and the normalized optical axis vector of both eyes, the normalized line of sight intersection of the detection object on the visual field detection device is determined, and the normalized fixation point offset is determined according to the difference between the normalized line of sight intersection and the normalized fixation point, and the normalized optical axis vector difference of both eyes of the detection object is determined based on the difference between the normalized optical axis vectors of both eyes of the detection object, and each normalized detection data, each normalized fixation point offset and each normalized optical axis vector difference are input into the target visual field detection model to obtain focusing information. The embodiment of the present application generates the normalized optical axis vector difference and the normalized fixation point offset based on the normalized fixation point and the normalized optical axis vector, expands the normalized detection data, enriches the data set, and thus improves the accuracy of focusing information determination.

[0093] Figure 6 FIG. 1 is a flow chart of a method for determining focus information in another embodiment. Figure 6 As shown, the embodiment of the present application relates to a possible implementation method of how to input each normalized detection data, each normalized fixation point offset and each normalized optical axis vector difference into a target visual field detection model to obtain focusing information, including the following steps:

[0094] S601, for each frame of normalized detection data, the normalized detection data, the normalized fixation point offset and the normalized optical axis vector difference are spliced ​​to obtain sequence data.

[0095] In this embodiment, the normalized detection data, the normalized fixation point offset and the normalized optical axis vector difference are spliced ​​to obtain sequence data. For example, the normalized data includes normalized age, normalized pupil distance information, normalized pupil diameter, normalized blink frequency, normalized palpebral fissure height, normalized optical axis vector of both eyes, normalized fixation point, normalized relative position of the stimulation point, normalized stimulation intensity of the stimulation point and the appearance time of the stimulation point. The normalized detection data, the normalized fixation point offset and the normalized optical axis vector difference are spliced ​​to obtain sequence data with a dimension of 16.

[0096] S602, using a position encoding module in a target visual field detection model to encode the order relationship of a plurality of sequence data to obtain a plurality of initial feature vectors.

[0097] In this embodiment, Figure 7 is a schematic diagram of a target vision detection model in an embodiment, such as Figure 7 As shown, since the time sequence information of the sequence data is more important, the position encoding module is used to encode the order relationship of multiple sequence data, that is, the multiple sequence data are numbered and the numbered sequence data are used as the initial feature vector.

[0098] S603, using a feature encoding module in the target field of view detection model to perform feature extraction on multiple initial feature vectors to obtain multiple target feature vectors.

[0099] In this embodiment, the feature encoding module may include a self-attention submodule and a feedforward network submodule, and the self-attention submodule and the feedforward network submodule are used to perform feature extraction on multiple initial feature vectors to obtain multiple target feature vectors.

[0100] In a possible implementation, the feature encoding module may further include a convolution layer and a pooling layer, etc., and the convolution layer and the pooling layer are used to extract features from multiple initial feature vectors to obtain a target feature vector.

[0101] Optionally, the feature encoding module may include multiple ones.

[0102] S604, linear mapping is performed on the target feature vector to obtain focusing information.

[0103] In the embodiment of the present application, since the focusing information includes the attention concentration result and the observation result, the target feature vector can be linearly mapped to a two-dimensional vector with a real value range by a linear mapping layer, and then the two-dimensional vector is mapped to [0, 1) by a sigmoid layer, and the output of the sigmoid layer is That is, the probability of the subject's attention being focused and the probability of seeing the stimulus point.

[0104] In an embodiment of the present application, for each frame of normalized detection data, the normalized detection data, the normalized fixation point offset and the normalized optical axis vector difference are spliced ​​to obtain sequence data, and the order relationship of multiple sequence data is encoded using the position encoding module in the target field of view detection model to obtain multiple initial feature vectors, and the feature encoding module in the target field of view detection model is used to extract features from multiple initial feature vectors to obtain target feature vectors, and the target feature vectors are linearly mapped to obtain focusing information. The embodiment of the present application uses a position encoding module to encode the sequence relationship of multiple sequence data, fully considers the timing information of multiple sequence data, improves the accuracy of determining the focusing information, and uses a feature encoding module to obtain a feature vector, which fully considers the practicality of the target field of view detection model.

[0105] Figure 8 FIG. 1 is a flow chart of a method for determining a target feature vector in an embodiment. Figure 8 As shown, the embodiment of the present application relates to a possible implementation method of how to use the feature encoding module in the target field of view detection model to extract features from multiple initial feature vectors to obtain multiple target feature vectors, including the following steps:

[0106] S801, input multiple initial feature vectors into the self-attention submodule in the feature encoding module for correlation processing to obtain multiple embedded feature vectors.

[0107] In this embodiment, since there is correlation between data of different dimensions in the same sequence data, there is also correlation between data of the same dimension in different sequence data. For example, the pupil size of the detected object is strongly correlated with the position and intensity of the stimulation point.

[0108] The self-attention mechanism of the self-attention submodule is used to find the correlation between different initial feature vectors and the correlation of the same initial feature vector itself, and multiple embedded feature vectors are obtained.

[0109] S802, inputting the multiple embedded feature vectors into the feedforward network submodule in the feature encoder module for nonlinear transformation processing to obtain multiple target feature vectors.

[0110] In this embodiment, a plurality of embedded feature vectors are input into a feedforward network submodule, and the feedforward network submodule performs a nonlinear transformation on the plurality of embedded feature vectors, further extracts features of the embedded feature vectors, and obtains a plurality of target feature vectors.

[0111] If there are multiple feature encoding modules, after performing nonlinear transformation on multiple embedded feature vectors to extract features, they are continuously input into the next feature encoding module, and the feature vector output by the last feature encoding module is used as the target feature vector.

[0112] In an embodiment of the present application, multiple initial feature vectors are input into the self-attention submodule in the feature encoding module for correlation processing to obtain multiple embedded feature vectors, and the multiple embedded feature vectors are input into the feedforward network submodule in the feature encoder module for nonlinear transformation processing to obtain multiple target feature vectors. This fully considers the correlation between the sequence data, improves the accuracy of obtaining the target feature vector, and thus improves the accuracy of the focusing information obtained based on the target feature vector.

[0113] In one embodiment, a method for determining a target visual field detection model is also provided, comprising: acquiring training data; the training data comprising visual physiological data of a test subject during a process in which a visual field detection device displays a stimulation point; training an initial visual field detection model according to the training data and standard focusing information corresponding to the training data to obtain a target visual field detection model; the standard focusing information comprising a standard attention concentration result of the test subject and a standard observation result of the test subject on the stimulation point; the standard observation result is determined according to the stimulation intensity of the stimulation point and a preset stimulation intensity threshold; the standard attention concentration result is determined according to the loss of the fixation point, the feedback result of the test subject on the stimulation point and the standard observation result.

[0114] The standard focusing information includes the standard attention concentration results of the test subject and the standard observation results of the test subject on the stimulation point. The standard observation results are based on the stimulation intensity of the stimulation point. and preset stimulation intensity threshold Determination, that is, whether the test subject sees the stimulation point is determined according to the stimulation intensity of the stimulation point and the preset stimulation intensity threshold, that is The preset stimulation intensity threshold is determined according to the stimulation intensity of the corresponding position in each frame of training data of the test object.

[0115] like Fig. 9 As shown, the standard attention results are based on the loss of fixation point. , Test subjects' feedback on stimulation points and standard observations s, That is, if the test subject sees the stimulus point and the test subject feedbacks that he saw the stimulus point, and the fixation point is not lost, the standard attention result is 1; or, if the test subject does not see the stimulus point and the test subject does not feedback that he saw the stimulus point, and the fixation point is not lost, the standard attention result is 1; if the test subject sees the stimulus point but the test subject does not feedback that he saw the stimulus point, the standard attention concentration result is 0; if the test subject does not see the stimulus point but the test subject feedbacks that he saw the stimulus point, the standard attention concentration result is 0; if the fixation point is lost, the standard attention concentration result is 0.

[0116] In this embodiment, continue as Fig. 9 As shown, the training data includes the basic data of the test object, visual physiological data, fixation point data and stimulation point data, as well as the optical axis vector difference and fixation point offset obtained based on the fixation point and binocular optical axis vectors in the visual physiological data. The training data can be normalized or not. The training data is input into the initial visual field detection model to obtain the predicted focusing information, and the initial visual field detection model is trained according to the loss value of the predicted focusing information and the standard focusing information, and the target visual field detection model is obtained by minimizing the loss value.

[0117] Optionally, a binary cross entropy loss function may be used to calculate the loss value L of the predicted focus information and the standard focus information. , where q is the number of training data in one iteration of training, y is the standard attention concentration result or standard observation result in the training data, and p y To predict attentional outcomes or to predict observed outcomes.

[0118] In an embodiment of the present application, training data is obtained, and an initial field of view detection model is trained based on the training data and standard focusing information corresponding to the training data to obtain a target field of view detection model, thereby laying a foundation for subsequently obtaining focusing information of the detection object based on the target field of view detection model.

[0119] Fig.10 FIG. 1 is a flow chart of a visual field detection method in another embodiment. Fig.10 As shown, the following steps are included:

[0120] S1001, acquiring multiple frames of detection data; the detection data includes visual physiological data of the detection object during the process of the visual field detection device displaying the stimulation point;

[0121] S1002, normalizing each test data according to the data type to obtain a plurality of normalized test data; the normalized test data includes the normalized optical axis vectors of the eyes of the test subject and the normalized fixation point of the visual field detection device;

[0122] S1003, for each frame of the normalized optical axis vector of both eyes, based on the attribute parameters of the visual field detection device and the normalized optical axis vector of both eyes, determining the normalized visual line intersection point of the detection object on the visual field detection device;

[0123] S1004, determining a normalized fixation point offset according to a difference between the normalized sight line intersection point and the normalized fixation point;

[0124] S1005, determining a normalized optical axis vector difference between the eyes of the detection object based on a difference in the normalized optical axis vectors between the eyes of the detection object;

[0125] S1006, for each frame of normalized detection data, concatenate the normalized detection data, the normalized fixation point offset, and the normalized optical axis vector difference to obtain sequence data;

[0126] S1007, using a position encoding module in a target visual field detection model to encode the order relationship of the plurality of sequence data to obtain a plurality of initial feature vectors;

[0127] S1008, inputting the multiple initial feature vectors into the self-attention submodule in the feature encoding module for correlation processing to obtain multiple embedded feature vectors;

[0128] S1009, inputting the multiple embedded feature vectors into the feedforward network submodule in the feature encoder module for nonlinear transformation processing to obtain multiple target feature vectors;

[0129] S1010, linearly mapping multiple target feature vectors to obtain focusing information;

[0130] S1011, obtaining a visual field detection result of the detection object according to the focusing information.

[0131] In an embodiment of the present application, the attention concentration result and the observation result are obtained based on the visual physiological data of the detection subject when the visual field detection device displays the stimulation point, and the target visual field detection model, and the visual field detection result is generated based on the attention concentration result and the observation result. That is, the detection subject does not need to press a button for manual feedback when viewing the stimulation point, and the visual field detection result is generated according to the feedback result, which greatly reduces the complexity of the interaction, avoids the subjective error caused by manual feedback, and improves the accuracy of the visual field detection result.

[0132] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0133] Based on the same inventive concept, the embodiment of the present application also provides a visual field detection device for implementing the visual field detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more visual field detection device embodiments provided below can refer to the limitations on the visual field detection method above, and will not be repeated here.

[0134] In an exemplary embodiment, Fig.11 As shown, a visual field detection device is provided, comprising: an acquisition module 11, a first determination module 12 and a second determination module 13, wherein:

[0135] The acquisition module 11 is used to acquire multiple frames of detection data; the detection data includes visual physiological data of the detection object during the process of the visual field detection device displaying the stimulation point;

[0136] A first determination module 12 is used to obtain focus information of the detection object according to the multiple frames of detection data and a preset target visual field detection model; the focus information includes the attention concentration result of the detection object and the observation result of the detection object on the stimulation point;

[0137] The second determination module 13 is used to obtain the field of view detection result of the detection object according to the focusing information.

[0138] In one embodiment, the first determination module 12 is specifically used to normalize each detection data according to the data type to obtain a plurality of normalized detection data; and obtain focusing information according to the plurality of normalized detection data and the target field of view detection model.

[0139] In one embodiment, the first determination module 12 is specifically used to determine the normalized line of sight intersection of the detection object on the field of view detection device for each frame of the normalized optical axis vector of both eyes, based on the attribute parameters of the field of view detection device and the normalized optical axis vector of both eyes; determine the normalized fixation point offset according to the difference between the normalized line of sight intersection and the normalized fixation point; determine the normalized optical axis vector difference between the detection object's eyes based on the difference in the normalized optical axis vector of the detection object's eyes; input each normalized detection data, each normalized fixation point offset and each normalized optical axis vector difference into the target field of view detection model to obtain focusing information.

[0140] In one embodiment, the first determination module 12 is specifically used to splice the normalized detection data, the normalized fixation point offset and the normalized optical axis vector difference for each frame of normalized detection data to obtain sequence data; use the position encoding module in the target field of view detection model to encode the order relationship of multiple sequence data to obtain multiple initial feature vectors; use the feature encoding module in the target field of view detection model to extract features from multiple initial feature vectors to obtain target feature vectors; linearly map the target feature vector to obtain focusing information.

[0141] In one embodiment, the first determination module 12 is specifically used to input each initial feature vector into the self-attention submodule in the feature encoding module for correlation processing to obtain an embedded feature vector; and input the embedded feature vector into the feedforward network submodule in the feature encoder module for nonlinear transformation processing to obtain a target feature vector.

[0142] In one embodiment, the visual field detection device further includes:

[0143] A data acquisition module, used to acquire training data; the training data includes visual physiological data of the test subject during the process of the visual field detection device displaying the stimulation point;

[0144] The training module is used to train the initial visual field detection model according to the training data and the standard focusing information corresponding to the training data to obtain the target visual field detection model; the standard focusing information includes the standard attention concentration result of the test subject and the standard observation result of the test subject to the stimulation point; the standard observation result is determined according to the stimulation intensity of the stimulation point and the preset stimulation intensity threshold; the standard attention concentration result is determined according to the loss of the fixation point, the feedback result of the test subject to the stimulation point and the standard observation result.

[0145] Each module in the above-mentioned visual field detection device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the visual field detection device in the form of hardware, or can be stored in the memory in the visual field detection device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0146] In an exemplary embodiment, a visual field detection device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of any of the above method embodiments when executing the computer program.

[0147] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above method embodiments are implemented.

[0148] In one embodiment, a computer program product is provided, including a computer program, which implements the steps of any of the above method embodiments when executed by a processor.

[0149] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0150] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0151] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0152] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A visual field detection method, characterized in that: The method comprises: Acquire multiple frames of detection data; the detection data includes visual physiological data of the detection object during the process of the visual field detection device displaying the stimulation point; Obtaining focus information of the detection object according to the multiple frames of detection data and a preset target visual field detection model; the focus information includes the attention concentration result of the detection object and the observation result of the detection object on the stimulation point; A visual field detection result of the detection object is obtained according to the focusing information.

2. The method according to claim 1, characterized in that The step of obtaining the focus information of the detection object according to the multiple frames of detection data and a preset target field of view detection model includes: Normalizing each of the detection data according to the data type to obtain a plurality of normalized detection data; The focusing information is obtained according to the plurality of normalized detection data and the target field of view detection model.

3. The method according to claim 2, characterized in that The normalized detection data includes the normalized optical axis vectors of the eyes of the detection object and the normalized fixation point of the visual field detection device; The obtaining the focusing information according to the normalized detection data and the target field of view detection model includes: For each frame of the normalized optical axis vectors of the eyes, based on the attribute parameters of the visual field detection device and the normalized optical axis vectors of the eyes, determining the normalized visual line intersection point of the detection object on the visual field detection device; Determining a normalized fixation point offset according to a difference between the normalized sight line intersection point and the normalized fixation point; Determining a normalized optical axis vector difference between the eyes of the detection object based on a difference in normalized optical axis vectors between the eyes of the detection object; Each of the normalized detection data, each of the normalized fixation point offsets and each of the normalized optical axis vector differences are input into the target visual field detection model to obtain the focusing information.

4. The method according to claim 3, characterized in that The step of inputting each of the normalized detection data, each of the normalized fixation point offsets, and each of the normalized optical axis vector differences into the target visual field detection model to obtain the focusing information comprises: For each frame of the normalized detection data, the normalized detection data, the normalized fixation point offset and the normalized optical axis vector difference are spliced ​​to obtain sequence data; Encoding the order relationship of the plurality of sequence data using the position encoding module in the target visual field detection model to obtain a plurality of initial feature vectors; Using a feature encoding module in the target visual field detection model to perform feature extraction on the multiple initial feature vectors to obtain multiple target feature vectors; Linear mapping is performed on the plurality of target feature vectors to obtain the focusing information.

5. The method according to claim 4, characterized in that The step of extracting features from the plurality of initial feature vectors using the feature encoding module in the target field of view detection model to obtain each target feature vector includes: Inputting the multiple initial feature vectors into the self-attention submodule in the feature encoding module for correlation processing to obtain multiple embedded feature vectors; The multiple embedded feature vectors are input into the feedforward network submodule in the feature encoder module for nonlinear transformation processing to obtain the multiple target feature vectors.

6. The method according to claim 3, characterized in that: The method further comprises: Acquiring training data; the training data includes visual physiological data of the test subject during the process of the visual field detection device displaying the stimulation point; The initial visual field detection model is trained according to the training data and the standard focusing information corresponding to the training data to obtain the target visual field detection model; the standard focusing information includes the standard attention concentration result of the test subject and the standard observation result of the test subject on the stimulation point; the standard observation result is determined according to the stimulation intensity of the stimulation point and a preset stimulation intensity threshold; the standard attention concentration result is determined according to the loss of the fixation point, the feedback result of the test subject on the stimulation point and the standard observation result.

7. A visual field detection device, characterized in that: The device comprises: An acquisition module, used for acquiring multiple frames of detection data; the detection data includes visual physiological data of the detection object during the process of the visual field detection device displaying the stimulation point; A first determination module is used to obtain focus information of the detection object according to the multiple frames of detection data and a preset target field of view detection model; the focus information includes the attention concentration result of the detection object and the observation result of the detection object on the stimulation point; The second determination module is used to obtain the field of view detection result of the detection object according to the focusing information.

8. A visual field detection device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A wearable visual field detection device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. The device according to claim 9, characterized in that The device includes any one of a virtual reality device, an augmented reality device, a mixed reality device and smart glasses.

Citation Information

Patent Citations

  • Attention and visual ability training system and method based on eye tracking and intelligent evaluation technology

    CN107929007A

  • Visual field examination equipment and method

    CN109717828A

  • Systems and methods for visual field analysis

    CN111587086A

  • Display systems and methods for determining registration between a display and a user's eyes

    CN111771179A

  • Visual information identification method and system based on eye movement attention, medium and equipment

    CN115393946A