Eye movement data processing method and system for autism spectrum disorder detection

Abstract

The present invention discloses an eye movement data processing method and system for autism spectrum disorder detection, which displays multiple detection icons in a detection task with different movement patterns. The moving detection icons guide a subject to view a display module, and then collects an eye movement image sequence of the subject's eyes viewing the detection icons, extracts eye movement data from the sequence and groups the eye movement data, calculates a sight point displacement data set corresponding to each group of eye movement data, imports a motion function corresponding to each detection icon into a test coordinate system, and imports each sight point displacement data set into the test coordinate system respectively, and determines which motion function each sight point displacement data set conforms to, thereby dynamically associating the subject's sight line position with the detection icon, and realizing the capture of the regularity of the subject's sight line following the detection icon; the detection method of the present invention does not require the use of high-precision, high-cost hardware, improves versatility, and can meet the screening scenarios of large-scale, rapid detection.

Description

Technical Field

[0001] The present invention belongs to the technical field of image data processing, and in particular, relates to an eye movement data processing method and system for autism spectrum disorder detection. Background Art

[0002] Currently, there are two main types of detection methods for autism spectrum disorder: the first type detects the three core characteristics of autism spectrum disorder and the behavioral patterns unique to autism spectrum disorder based on these core characteristics; the second type detects physiological indicators that are different between autistic patients and normal people (including but not limited to eye movement parameters, brain structure and connectivity-related parameters, etc.).

[0003] Existing questionnaires and scales for screening and detecting autism spectrum disorders (such as the Child Heart Scale-II and CARS) are based on the first approach, using scenario-based questionnaires designed for testing, coupled with on-site interaction and hands-on manipulation to achieve the purpose of assessing the condition. Furthermore, some existing devices replicate the required testing scenarios through visual images and videos, optimizing and simplifying manual operations through intelligent methods. These devices, combined with eye trackers, capture the corresponding gaze position and provide the test results to the doctor to assist in diagnosis. However, these traditional scale-based tests take a very long time to complete, and require doctors to maintain professional interaction and observation with the patient and their family members throughout the process, resulting in high workload. This hinders large-scale, rapid screening and results in relatively low diagnostic efficiency. For auxiliary diagnostic devices used with eye trackers, each patient undergoes a 15-minute eye calibration process before the test can begin. This also places high demands on the accuracy of the eye tracker, as the exact gaze position must be known to determine what the patient is actually looking at. These two reasons make the first approach unsuitable for large-scale, rapid screening. Furthermore, the initial calibration process requires a high level of patient cooperation, increasing the complexity of the doctor's operation and making the test more difficult to complete. Young children struggle to cooperate with the calibration process, potentially depriving them of the opportunity for early intervention.

[0004] When individuals with autism spectrum disorder view specific objects, scenes, or actions, their eye movement parameters (such as saccade amplitude, saccade latency / response time, and peak velocity), eye movement parameters (such as mean, standard deviation / standard error, and effect size), and pupil size differ from those of normal individuals. In addition to the auxiliary diagnostic devices used with eye trackers described above, a more precise eye tracker is used to acquire and analyze relevant physiological information and generate statistical data. This, combined with the patient's response to the test scenario, improves the accuracy and reliability of the test results. This second approach has the same drawbacks as the first. Furthermore, higher precision comes with a higher cost, further exacerbating these drawbacks. Summary of the Invention

[0005] The purpose of the present invention is to provide a more efficient eye movement data processing method and system for autism spectrum disorder detection. The detection task is designed based on the three core characteristics of autism spectrum disorder (social impairment, communication impairment, narrow interests and stereotyped behavior) and unique behavioral patterns (joint attention paradigm, name-calling response paradigm, non-social sound stimulation behavior paradigm, etc.). A display device is used to display each detection icon in the detection task with different movement patterns. A sequence of eye movement images of the test subject's eyes viewing the detection icons is collected, and the eye movement image sequence is analyzed and compared with the movement pattern of the detection icons to determine the test subject's eye movement following the detection icons, and the test results are obtained to assist doctors in diagnosis.

[0006] In order to solve the above technical problems, this application adopts the following technical solutions:

[0007] A method for processing eye movement data for autism spectrum disorder detection is proposed, including:

[0008] S1, displaying a motion detection icon group on a display module; wherein the detection icon group includes at least two detection icons, and each detection icon moves according to a different motion function;

[0009] S2, collecting eye movement image sequences of the test subject when viewing the display module, analyzing the eye movement position data, and constructing an eye movement data scatter plot with time as the horizontal axis and eye movement position as the vertical axis;

[0010] S3, grouping the eye movement data based on the eye movement data scatter plot;

[0011] S4, calculating the sight point displacement data set of each data group and constructing a scatter plot of the sight point displacement data;

[0012] S5, constructing a test coordinate system and importing the motion function corresponding to the detection icon into the test coordinate system;

[0013] S6. Import the line-of-sight landing point displacement data sets of each group into the test coordinate system in sequence and compare them with the motion function graphs to find the motion functions that each line-of-sight landing point displacement data set conforms to;

[0014] S7. Classify the line-of-sight landing point displacement data sets of each group and output the statistical results.

[0015] In some embodiments of the present invention, step S3 specifically includes:

[0016] Set a constant k. Starting from the origin of the scatter plot coordinate system of the eye movement data, take two adjacent data in the horizontal axis direction in sequence; the constant k is: the critical value between the eye movement amplitude and the saccade amplitude during tracking and fixation, which is the displacement amount shown in the collected eye movement images;

[0017] Obtain the vertical coordinate values of the two data and calculate the absolute value Δk of the difference between them;

[0018] Compare Δk with the constant k. If Δk < k, classify the two data into the same group of data. If Δk > k, use a as the splitting point of the data set, classify a into the previous group of data, and classify b into a new group of data.

[0019] In some embodiments of the present invention, calculating the line-of-sight landing point displacement data set of each data group in step S4 specifically includes:

[0020] Multiply the position coordinates of the eye movement data by the constant to obtain the line-of-sight landing point displacement data set; where , is the displacement amount of a single detection icon, is the iris displacement amount corresponding to the eye movement image sequence.

[0021] In some embodiments of the present invention, importing the motion function corresponding to the detection icon into the test coordinate system in step S5 specifically includes:

[0022] Taking the center of the detection icon as the origin of the test coordinate system and the motion function as the motion trajectory of the origin, setting the distances between the left edge image of the detection icon and the origin and between the right edge image of the detection icon and the origin as a, and obtaining the motion function of the left edge of the detection icon and the motion function of the right edge image;

[0023] Import the motion function of the left edge and the motion function of the right edge into the test coordinate system, and the range enclosed by the two motion functions constitutes the actual motion area of the entire image of the detection icon.

[0024] In some embodiments of the present invention, step S6 specifically includes:

[0025] Import each set of sight point displacement data sets into the test coordinate system in sequence;

[0026] Compare each set of sight point displacement datasets with the motion area corresponding to each detection icon, and find the number of data points in each motion area for each set of sight point displacement datasets. ;

[0027] Will The motion function corresponding to the maximum value is determined to be the running function that the sight point displacement data set conforms to.

[0028] An eye movement data processing system for autism spectrum disorder detection is proposed, comprising:

[0029] A display module, configured to display a motion detection icon group; wherein the detection icon group includes at least two detection icons, each detection icon moving according to a different motion function;

[0030] An acquisition module, used for acquiring an eye movement image sequence of a test subject when viewing a display module;

[0031] The calculation module is used to process eye movement data according to the following steps:

[0032] Analyze the eye movement position data and construct a scatter plot of the eye movement data with time as the horizontal axis and eye movement position as the vertical axis;

[0033] Group the eye movement data based on the eye movement data scatter plot;

[0034] Calculate the sight point displacement data set of each data group and construct a scatter plot of the sight point displacement data;

[0035] Construct a test coordinate system and import the motion function corresponding to the detection icon into the test coordinate system;

[0036] Import each set of sight point displacement data sets into the test coordinate system in turn and compare them with the motion function graphs to find the motion function that each sight point displacement data set conforms to;

[0037] Classify each group of sight point displacement data sets and output statistical results.

[0038] In some embodiments of the present invention, when the computing module groups the eye movement data based on the eye movement data scatter plot, the computing module includes:

[0039] A constant k is set, starting from the origin of the eye movement data scatter plot coordinate system, and sequentially taking two adjacent data points in the horizontal axis direction; the constant k is: the critical value between the eye movement amplitude during gaze tracking and the saccade amplitude, which is expressed as the displacement in the collected eye movement image;

[0040] Obtain the vertical coordinate values of two data, and calculate the absolute value Δk of the difference between the two;

[0041] Compare Δk with the constant k. If Δk < k, classify the two data into the same group of data. If Δk > k, use a as the splitting point of the data set, classify a into the previous group of data, and classify b into a new group of data.

[0042] In some embodiments of the present invention, when the operation module calculates the line-of-sight landing point displacement data set of each data group, it specifically includes:

[0043] Multiply the position coordinates of the eye movement data by the constant to obtain the line-of-sight landing point displacement data set; where , is the displacement amount of a single detection icon, is the iris displacement amount corresponding to the eye movement image sequence.

[0044] In some embodiments of the present invention, when the operation module imports the motion function corresponding to the detection icon into the test coordinate system, it specifically includes:

[0045] Take the center of the detection icon as the origin of the test coordinate system, and the motion function as the motion trajectory of the origin. Set the distance between the left edge picture of the detection icon and the origin and the distance between the right edge picture and the origin as a, and obtain the motion function of the left edge of the detection icon and the motion function of the right edge picture,

[0046] Import the motion function of the left edge and the motion function of the right edge into the test coordinate system, and the range enclosed between the two motion functions constitutes the actual motion area of the entire picture of the detection icon.

[0047] In some embodiments of the present invention, when the operation module finds the motion function that each line-of-sight landing point displacement data set conforms to, it specifically includes:

[0048] Import each line-of-sight landing point displacement data set into the test coordinate system in sequence;

[0049] Compare each line-of-sight landing point displacement data set with the motion area corresponding to each detection icon respectively, and find the number of data points ;

[0050] Judge the motion function corresponding to the maximum value as the operating function that the line-of-sight landing point displacement data set conforms to.

[0051] Compared with the existing technology, the advantages and positive effects of this application are: in the eye movement data processing method and system for autism spectrum disorder detection proposed in this application, based on the core characteristics and unique behavioral patterns of autism spectrum disorder, a test task is designed to mine the eye movement patterns of the test subject based on observing detection icons, so that the tester can be assisted in judging whether the test subject has autism spectrum disorder based on the mined eye movement patterns. During the test, a display module is used to display multiple detection icons in the detection task with different motion patterns. The motion-based detection icons are used to guide the testee to look at the display module, and then an eye movement image sequence of the testee's eyes looking at the detection icons is collected. Eye movement data is extracted from the eye movement image sequence and grouped. The gaze landing point displacement data set corresponding to each group of eye movement data is calculated, and the motion function corresponding to each detection icon is imported into the test coordinate system. Each gaze landing point displacement data set is imported into the test coordinate system respectively, and it is determined which motion function each gaze landing point displacement data set conforms to. The testee's line of sight position is dynamically associated with the detection icon, and the regular capture of the testee's line of sight following the detection icon is achieved. Compared with the existing detection method used with an eye tracker, the method of the present invention can instantly determine the testee's line of sight position, omit the instrument calibration process, and achieve the effect of not requiring the testee to adjust and cooperate throughout the process, which can effectively improve detection efficiency and reduce the difficulty of detection operation. At the same time, the detection method of the present invention does not require the use of high-precision and high-cost hardware, improves versatility, and can meet the screening scenarios of large-scale and rapid detection.

[0052] After reading the detailed description of the embodiments of the present application in conjunction with the accompanying drawings, other features and advantages of the present application will become more apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a schematic diagram of the steps of the eye movement data processing method for autism spectrum disorder detection proposed by the present invention;

[0054] Figure 2 A diagram showing a detection icon group displayed with different motion functions in the present invention;

[0055] Figure 3 This is an example of the eye movement data scatter plot constructed in the present invention;

[0056] Figure 4 For the present invention Figure 3 An example of an eye movement data scatter plot after being grouped is shown;

[0057] Figure 5 It is a diagram showing the relationship between the movement of the iris of the human eye and the displacement of the detection icon that the eye is looking at;

[0058] Figure 6 For the present invention Figure 4An example of a scatter plot of gaze point displacement data for the eye movement data scatter plot shown;

[0059] Figure 7 This is a schematic diagram of a motion function corresponding to a detection icon in the present invention after being imported into a test coordinate system;

[0060] Figure 8 This is an example of a detection icon in the present invention;

[0061] Figure 9 For the present invention Figure 8 An example of the motion area of the detection icon in the test coordinate system;

[0062] Figure 10 This is a schematic diagram of importing a sight point displacement dataset into a test coordinate system in the present invention;

[0063] Figure 11 for Figure 10 Schematic diagram of the comparison between the gaze point displacement dataset and the motion area of a detection image;

[0064] Figure 12 for Figure 10 Schematic diagram of the comparison between the gaze point displacement dataset and the motion area of another detection image. DETAILED DESCRIPTION

[0065] The specific implementation of this application is further described in detail below with reference to the accompanying drawings.

[0066] The present invention aims to propose an eye movement data processing method for auxiliary diagnosis of autism spectrum disorder detection. The entire system includes a display module, an acquisition module, an operation module, a calculation module and an output module; the display module is used to display the detection icon, and the displayed content is controlled by the calculation module; the acquisition module is used to collect the eye movement image sequence of the test subject when viewing the detection icon; the operation module is used to control the start, stop, pause and other operations of the detection; the calculation module is used to drive each module, run the algorithm, and obtain the data processing results; the output module outputs the data processing results in electronic or paper form.

[0067] Combine Figure 1 As shown, the eye movement data processing method for autism spectrum disorder detection proposed by the present invention includes the following steps:

[0068] S1: Displaying a moving detection icon group on a display module; the detection icon group includes at least two detection icons, and each detection icon moves according to a different motion function.

[0069] For example, multiple detection icons of a detection icon group are displayed horizontally back and forth on the display module using different motion functions, for example Figure 2For the two detection icons shown, the detection icon of the human head image moves back and forth from left to right at a first set rate, and the detection icon of the train head image moves back and forth from right to left at a second set rate.

[0070] Among these, multiple detection diagrams are marked as Detection Icon 1, Detection Icon 2,..., Detection Icon n; the corresponding motion functions are denoted as , , ……, .

[0071] S2: Collect the eye movement image sequence of the test subject when viewing the display module, parse to obtain the eye movement position data, use time as the horizontal axis and eye movement position as the vertical axis to construct an eye movement data scatter plot.

[0072] The acquisition module collects the eye movement image sequence of the test subject during the viewing of the detection icon on the display module, parses the eye movement image sequence to obtain the eye movement position data (horizontal and / or vertical), establishes an eye movement data scatter plot coordinate system with time as the horizontal axis and position data as the vertical axis, and imports the eye movement position data into the coordinate system according to the acquisition time of the image sequence to obtain the scatter plot of the eye movement data. As Figure 3 shown is the scatter plot of the eye movement data obtained by importing the horizontal position data of the eye movement into the coordinate system according to the acquisition time. <00>

[0073] S3: Group the eye movement data based on the eye movement data scatter plot.

[0074] Set a constant k. Starting from the origin of the eye movement data scatter plot coordinate system, successively take two adjacent data a and b in the horizontal axis direction (that is, the eye movement data corresponding to two adjacent time points), obtain the vertical coordinate values of the two data, calculate the absolute value Δk of the difference between the two, compare Δk with the constant k. If Δk < k, then classify the two data into the same group of data; if Δk > k, then take a as the segmentation point of the data set, classify a into the previous group of data, and classify b into a new group of data.

[0075] The purpose of this step is to optimize the fitting degree of the fitting curve in subsequent operations and reduce interference.

[0076] The actual meaning of the constant k is: the critical value between the eye movement amplitude and the saccade amplitude during tracking gaze, manifested as the displacement amount in the collected eye movement image.

[0077] The scatter plot after grouping is as Figure 4 shown. Assume that finally N groups of eye movement data are separated.

[0078] S4: Calculate the line of sight landing point displacement data set for each data group and construct a line of sight landing point displacement data scatter plot.

[0079] As Figure 5As shown in the figure, there is a positive proportional relationship between the iris movement L1 of the human eye and the displacement L2 of the detection icon that the eye is looking at per unit time. In the figure, o is the eye axis position, L3 is the distance between the iris and the eye axis, and L4 is the distance between the iris and the display module. Similarly, the iris displacement L0 in the eye movement image sequence is also directly proportional to the iris displacement L1 of the human eye. Therefore, the detection icon displacement L2, the iris displacement L0 in the eye movement image sequence, and the iris displacement L1 of the human eye are directly proportional. By measuring the displacement L2 of a single detection icon and the corresponding iris displacement L0 in the eye movement image sequence, the ratio between the two can be obtained. .

[0080] According to the above principles, the eye movement dataset By multiplying the position coordinate value of with the constant J, we can get the sight point displacement data set or ; Reconstruct the scatter plot based on the new data set to obtain the sight point displacement data scatter plot, such as Figure 6 shown.

[0081] S5: Construct a test coordinate system, and import the motion function corresponding to the detection icon into the test coordinate system.

[0082] Construct a test coordinate system and transform the motion function of each detection icon (1, 2, ..., n) 、 、……、 Import the constructed test coordinate system, such as Figure 7 An embodiment shown.

[0083] S6: Importing each set of sight point displacement data sets into the test coordinate system in turn and comparing them with each motion function graph to find the motion function that each sight point displacement data set conforms to.

[0084] Take the eye movement data divided into four groups in step S3 as an example, 、 、 、 Indicates that first Import the data of the data group into the test coordinate system and determine which range of the motion function graph each data point falls within. Assume The data set contains 10 data points. Then determine which range of the motion function graph these 10 data points fall into, and count the number of data points that fall within the same range of the motion function graph. Set a threshold m. When the number of data points that fall within the same range of the motion function graph exceeds the threshold m, determine The data points of the data set conform to the motion function, which corresponds to the test subject's sight following the detection icon moving with the motion function. The data of the data group is imported into the test coordinate system and the above method is repeated to determine which motion function it conforms to; then Data Group, The data set is imported into the test coordinate system and the above method is repeated to determine which motion function is met.

[0085] S7: Classify each group of sight point displacement data sets and output statistical results.

[0086] That is, the eye movement data of viewing the same detection icon are counted into a set and the result is output.

[0087] From step S6, it has been determined which motion function each sight point displacement data set conforms to, for example The data of the data set conforms to the motion function , The data of the data set conforms to the motion function , The data of the data set conforms to the motion function , The data of the data set conforms to the motion function , then Data Groups and Motion Functions Divide into one category and output the binding relationship, 、 and Data Groups and Motion Functions Classify into one category and output the binding relationship.

[0088] The above-mentioned present invention is based on the core characteristics and unique behavioral patterns of autism spectrum disorder, and designs a test task based on observing detection icons to explore the eye movement patterns of the test subject, so as to assist the tester in judging whether the test subject has autism spectrum disorder based on the mined eye movement patterns. During the test, a display module is used to display multiple detection icons in the detection task with different motion patterns. The test subject is guided to view the display module based on the motion of the detection icons (to test the test subject's interest in and ability to follow each detection icon). Then, a sequence of eye movement images of the test subject viewing the detection icons is collected. Eye movement data is extracted from the eye movement image sequence and grouped. A gaze point displacement dataset corresponding to each set of eye movement data is calculated. The motion function corresponding to each detection icon is imported into a test coordinate system, and each gaze point displacement dataset is imported into the test coordinate system. It is determined which motion function each gaze point displacement dataset conforms to. This dynamically associates the test subject's gaze position with the detection icon, and captures the regularity of the test subject's gaze following the detection icon. Compared to existing detection methods used with eye trackers, the method of the present invention can instantly determine the test subject's gaze position, eliminating the need for instrument calibration, and achieving the effect of eliminating the need for test subject adjustment and cooperation throughout the entire process. This can effectively improve detection efficiency and reduce the difficulty of detection operations. At the same time, the detection method of the present invention does not require the use of high-precision, high-cost hardware, improving versatility and meeting the needs of large-scale, rapid screening scenarios.

[0089] The following describes in detail steps S5 and S6 of the eye movement data processing method proposed by the present invention using a specific embodiment.

[0090] As Figure 8 Taking the detection icon shown as an example, the center of the detection icon is set as the origin of the test coordinate system. is the motion trajectory of the origin, and the distance between the left edge of the detection icon and the origin is set to a, and the distance between the right edge and the origin is also a. Then the motion function of the left edge of the detection icon is , the motion function of the right edge of the picture is , import these two functions into the test coordinate system, the range enclosed by the two functions is the actual motion area of the entire screen of the detection icon, such as Figure 9 shown.

[0091] Import each segment of the sight point displacement data set into the test coordinate system in sequence and compare it with the motion area corresponding to each detection icon. Figure 10 As shown, the first segment of the sight point displacement data set is imported into the test coordinate system and compared with the motion area of the detection icon 1. In each segment of the data set, the multiple tables of data points are , keep the horizontal axis (time axis) value unchanged, and add a constant value to the vertical axis data of all data points ,get , so as to achieve the overall translation of the data points in the data set along the vertical coordinate direction in the test coordinate system; The value satisfies the following condition: as many data points as possible in the current data set are included in the motion area of the current detection icon.

[0092] After the above conditions are met, the total number of data points in the statistical data set is recorded as , is the number of the sight point displacement dataset; then the number of data points contained in the jth motion area is counted and recorded as .

[0093] like Figure 11 In the embodiment shown, the total number of data points in the first segment of the data set is 11. After all points in the data set are uniformly translated vertically, at most 9 data points can be included in the motion area of the detection icon 1. , Similarly, if Figure 12 As shown, by comparing the first segment of the data set with the motion area of the detection icon 2, we can get , .

[0094] Repeat the above steps, and after each data set comparison is completed, multiple Value and a value.

[0095] Pick The maximum value among the values ,like , then this segment of the data set and the detection icon The overlap of the motion area is the highest, and it is judged that the test subject's gaze is following the detection icon. It is not followed by other detection icons.

[0096] In some embodiments of the present invention, a constant is set Used for Make a judgment, if , it is determined that the time period of the current data set is where the test subject's sight is following the detection icon ,like , it is determined that during the time period of the current data set, the test subject's gaze did not follow any detection icon.

[0097] In some embodiments of the present invention, the statistical data output in step S7 may be visualized in the form of a chart or the like, so that the tester can intuitively know the classification results.

[0098] Based on the above-mentioned eye movement data processing method for autism spectrum disorder detection, the present invention also proposes an eye movement data processing system for autism spectrum disorder detection, including:

[0099] A display module for displaying a detection icon group in motion; wherein, the detection icon group includes at least two detection icons, and each detection icon moves according to a different motion function.

[0100] An acquisition module for acquiring an eye movement image sequence when the tested person views the display module.

[0101] An operation module for processing eye movement data according to the following steps: parsing to obtain eye movement position data, constructing an eye movement data scatter plot with time as the horizontal axis and eye movement position as the vertical axis; grouping the eye movement data based on the eye movement data scatter plot; calculating a line-of-sight landing point displacement data set for each data group, and constructing a line-of-sight landing point displacement data scatter plot; constructing a test coordinate system, and importing the motion function corresponding to the detection icon into the test coordinate system; sequentially importing each group of line-of-sight landing point displacement data sets into the test coordinate system for comparison with the graphs of each motion function, and finding the motion function that each line-of-sight landing point displacement data set conforms to; classifying each group of line-of-sight landing point displacement data sets and outputting a statistical result.

[0102] When the operation module groups the eye movement data based on the eye movement data scatter plot, it includes: setting a constant k, starting from the origin of the eye movement data scatter plot coordinate system, and sequentially taking two adjacent data in the horizontal axis direction; the constant k is: the critical value between the eye movement amplitude and the saccade amplitude during tracking gaze, manifested as the displacement amount in the acquired eye movement image; obtaining the vertical coordinate values of the two data, and calculating the absolute value Δk of the difference between the two; comparing Δk with the constant k, if Δk < k, then classify the two data into the same data group, if Δk > k, then use a as the segmentation point of the data set, classify a into the previous data group, and classify b into a new data group.

[0103] When the operation module calculates the line-of-sight landing point displacement data set for each data group, it specifically includes: multiplying the position coordinates of the eye movement data by the constant to obtain the line-of-sight landing point displacement data set; wherein, is the displacement amount of a single detection icon, is the iris displacement amount corresponding to the eye movement image sequence.

[0104] When the operation module imports the motion function corresponding to the detection icon into the test coordinate system, it specifically includes: taking the center of the detection icon as the origin of the test coordinate system, and the motion function as the motion trajectory of the origin, setting the distance between the left edge picture of the detection icon and the origin and the distance between the right edge picture of the detection icon and the origin as a, and obtaining the motion function of the left edge of the detection icon and the motion function of the right edge of the picture , is the number of the motion function; the motion function of the left edge and the motion function of the right edge are imported into the test coordinate system, and the range enclosed by the two motion functions constitutes the actual motion area of the entire screen of the detection icon.

[0105] The calculation module finds the motion function that each sight point displacement data set conforms to, specifically including: importing each set of sight point displacement data sets into the test coordinate system in turn; comparing each set of sight point displacement data sets with the motion area corresponding to each detection icon, and finding the number of data points of each set of sight point displacement data sets falling into each motion area ;Will The motion function corresponding to the maximum value is determined to be the running function that the sight point displacement data set conforms to.

[0106] The present invention also proposes an autism spectrum disorder detection device, which is equipped with the eye movement data processing system given above, runs the eye movement data processing method given above, and outputs the eye movement regularity data of the test subject. The tester can combine the core characteristics and behavioral patterns of autism spectrum disorder and use the eye movement regularity data of the test subject to assist in determining whether the test subject has autism spectrum disorder.

[0107] It should be noted that, in the specific implementation process, the above-mentioned control part can be implemented by a hardware processor executing computer execution instructions in software form stored in the memory, which will not be elaborated here. The programs corresponding to the actions performed by the above-mentioned control circuit can be stored in the system's computer-readable storage medium in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0108] The computer-readable storage medium mentioned above may include volatile memory, such as random access memory; may also include non-volatile memory, such as read-only memory, flash memory, hard disk or solid-state drive; may also include a combination of the above types of memory.

[0109] The processor mentioned above can also be a collective term for multiple processing elements. For example, the processor can be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices (PLDs), discrete gate or transistor logic devices (LDDs), discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor, etc., and can also be a special-purpose processor.

[0110] It should be pointed out that the above description is not a limitation of the present invention, and the present invention is not limited to the above examples. Changes, modifications, additions or substitutions made by ordinary technicians in this technical field within the essential scope of the present invention should also fall within the scope of protection of the present invention.

Claims

1. A method for processing eye movement data for detecting autism spectrum disorder, characterized in that: Including: S1, displaying a group of moving detection icons on a display module; wherein, the group of detection icons includes at least two detection icons, and each detection icon moves according to a different motion function; S2, collecting an eye movement image sequence of a subject when watching the display module, parsing to obtain eye movement position data, and constructing an eye movement data scatter plot with time as the horizontal axis and eye movement position as the vertical axis; S3, grouping the eye movement data based on the eye movement data scatter plot; S4, calculating a line-of-sight landing point displacement data set for each data group, and constructing a line-of-sight landing point displacement data scatter plot; S5, constructing a test coordinate system and importing the motion function corresponding to the detection icon into the test coordinate system; S6, sequentially importing each group of line-of-sight landing point displacement data sets into the test coordinate system for comparison with the graphs of each motion function, and finding the motion function that each line-of-sight landing point displacement data set conforms to; S7, classifying each group of line-of-sight landing point displacement data sets and outputting a statistical result; In step S4, calculating the line-of-sight landing point displacement data set for each data group specifically includes: Combine the position coordinates of the eye movement data with the constant Multiply them to get the sight point displacement dataset; where, , is the displacement of a single detection icon, is the iris displacement corresponding to the eye movement image sequence; In step S5, importing the motion function corresponding to the detection icon into the test coordinate system specifically includes: The center of the detection icon is the origin of the test coordinate system, the motion function is the motion trajectory of the origin, and the distance between the left edge of the detection icon and the origin and the distance between the right edge of the detection icon and the origin are set to a, and the motion function of the left edge of the detection icon is obtained. and the motion function of the right edge of the picture , is the number of the motion function; Importing the motion function of the left edge and the motion function of the right edge into the test coordinate system, and the range enclosed between the two motion functions constitutes the actual motion area of the entire picture of the detection icon.

2. The eye movement data processing method for autism spectrum disorder detection according to claim 1, characterized in that: Step S3 specifically includes: Setting a constant k, starting from the origin of the eye movement data scatter plot coordinate system, sequentially taking two adjacent data in the horizontal axis direction; the constant k is: the critical value between the eye movement amplitude and the saccade amplitude during tracking and fixation, manifested as the displacement amount in the collected eye movement images; Obtaining the vertical coordinate values of the two data, and calculating the absolute value Δk of the difference between the two; Comparing Δk with the constant k, if Δk < k, then classifying the two data into the same data group, if Δk > k, then taking a as the splitting point of the data set, classifying a into the previous data group, and classifying b into a new data group.

3. The eye movement data processing method for autism spectrum disorder detection according to claim 1, characterized in that: Step S6 specifically includes: Sequentially importing each group of line-of-sight landing point displacement data sets into the test coordinate system; Compare each set of sight point displacement datasets with the motion area corresponding to each detection icon, and find the number of data points in each motion area for each set of sight point displacement datasets. ; Will The motion function corresponding to the maximum value is determined to be the running function that the sight point displacement data set conforms to.

4. An eye movement data processing system for autism spectrum disorder detection, characterized in that: Including: A display module for displaying a group of moving detection icons; wherein, the group of detection icons includes at least two detection icons, and each detection icon moves according to a different motion function; An acquisition module for collecting an eye movement image sequence of a subject when watching the display module; An operation module for processing eye movement data according to the following steps: Parsing to obtain eye movement position data, and constructing an eye movement data scatter plot with time as the horizontal axis and eye movement position as the vertical axis; Grouping the eye movement data based on the eye movement data scatter plot; Calculating a line-of-sight landing point displacement data set for each data group, and constructing a line-of-sight landing point displacement data scatter plot; Constructing a test coordinate system and importing the motion function corresponding to the detection icon into the test coordinate system; Sequentially importing each group of line-of-sight landing point displacement data sets into the test coordinate system for comparison with the graphs of each motion function, and finding the motion function that each line-of-sight landing point displacement data set conforms to; Classifying each group of line-of-sight landing point displacement data sets and outputting a statistical result; When calculating the line-of-sight landing point displacement data set for each data group, the operation module specifically includes: Combine the position coordinates of the eye movement data with the constant Multiply them to get the sight point displacement dataset; where, , is the displacement of a single detection icon, is the iris displacement corresponding to the eye movement image sequence; The operation module imports the motion function corresponding to the detection icon into the test coordinate system, specifically including: The center of the detection icon is the origin of the test coordinate system, the motion function is the motion trajectory of the origin, and the distance between the left edge of the detection icon and the origin and the distance between the right edge of the detection icon and the origin are set to a, and the motion function of the left edge of the detection icon is obtained. and the motion function of the right edge of the picture , is the number of the motion function; Import the motion functions of the left edge and the right edge into the test coordinate system, and the range enclosed by the two motion functions constitutes the actual motion area of the entire picture of the detection icon.

5. The eye movement data processing system for autism spectrum disorder detection according to claim 4, characterized in that: When the operation module groups the eye movement data based on the eye movement data scatter plot, it includes: Set a constant k, starting from the origin of the eye movement data scatter plot coordinate system, and sequentially take two adjacent data in the horizontal axis direction; the constant k is: the critical value between the eye movement amplitude and the saccade amplitude during tracking gaze, which is manifested as the displacement amount in the collected eye movement image; Obtain the longitudinal coordinate values of the two data, and calculate the absolute value Δk of the difference between the two; Compare Δk with the constant k. If Δk < k, the two data are grouped into the same group of data. If Δk > k, a is used as the splitting point of the data set, a is grouped into the previous group of data, and b is grouped into a new group of data.

6. The eye movement data processing system for autism spectrum disorder detection according to claim 4, characterized in that: When the operation module finds the motion function that each set of line-of-sight landing point displacement data conforms to, it specifically includes: Import each set of line-of-sight landing point displacement data into the test coordinate system in sequence; Compare each set of sight point displacement datasets with the motion area corresponding to each detection icon, and find the number of data points in each motion area for each set of sight point displacement datasets. ; Will The motion function corresponding to the maximum value is determined to be the running function that the sight point displacement data set conforms to.

Images