Online eye movement tracking behavior experiment method and system based on network camera

Abstract

The invention provides an online eye movement tracking behavior experiment method and system based on a network camera. The online eye movement tracking behavior experiment method comprises the following steps: S1, embedding an eye movement tracking experiment; s2, configuring an eye movement tracking experiment; s3, the eye movement tracking experiment answers; and S4, visualizing the eye movement data. According to the method, the learning cost of eye movement equipment and the cost of the equipment are reduced, a publisher can be effectively helped to eliminate interference data caused by resolution in advance, and the visual application can help a user to quickly check the data condition, so that the data finally collected by the user is the data of each corresponding experimental stimulus.

Description

Technical Field

[0001] The present invention belongs to the technical field of eye movement tracking, and particularly relates to an online eye movement tracking behavior experiment method and system based on a web camera. Background Art

[0002] Eye-tracking is a technology for measuring and recording eye movements. It analyzes an individual's visual attention and cognitive processes by capturing information such as the position of the eyes, the direction of gaze, and the size of the pupils. Eye-tracking has a wide range of applications in multiple fields, including psychological research, advertising effect evaluation, medical diagnosis, human-computer interaction, etc.

[0003] Currently, the common implementation method of eye-tracking relies on an eye tracker. An eye tracker is mainly based on infrared corneal reflection and realizes eye-tracking through infrared light and camera technology, that is, an infrared light source is used to irradiate the eyeball, and the reflected infrared light is captured by a camera. These reflected lights are received by the infrared light sensors in the eye tracker and converted into electrical signals, thereby determining the position and movement trajectory of the eyeball. This implementation method requires the subjects to be equipped with the hardware and software of the eye tracker, with relatively high costs, relatively complex wearing and interaction methods, and requires certain training and learning. These requirements limit the further widespread use of eye-tracking.

[0004] In recent years, the implementation scheme of online eye-tracking technology based on a web camera has developed rapidly. Its principle is to use artificial intelligence and deep neural networks to analyze the image data of the web camera. This technology realizes calibration by observing the interaction between the user and the web page (such as clicks and cursor movements), thereby training a mapping relationship between the click position of the user and the eye features. This technology implementation method runs completely in the user's browser, does not require sending video data to the server, and does not require special hardware support, only the camera permission of the user. In this way, it can be realized that the subjects do not need additional devices such as eye trackers and can complete the eye-tracking task remotely. However, in actual applications, this technology also needs to cooperate with multiple functions to play its actual role, including but not limited to: embedding and editing of eye-tracking experiments, saving of eye movement data, visualization of eye-tracking data, etc.

[0005] The existing implementation technologies of eye-tracking based on web cameras still have the following problems.

[0006] First, in the eye-tracking applications in various commercial and research fields, it is usually necessary to first design corresponding questionnaires and behavior experiments, and then configure the eye-tracking function for some parts of the experiments. That is to say, the eye-tracking technology itself needs to be equipped with a corresponding questionnaire and behavior experiment design system to truly play its role.

[0007] Second, during the process of conducting eye-tracking experiments remotely, it is necessary to consider the differences in the devices used by the subjects. One important condition is that the screen resolutions of the devices used by the subjects are different. In such a case, it is necessary to consider how to achieve a unified display method and a unified method for dividing eye movement fixation areas for the stimulus materials (such as pictures) under different screen resolutions, so as to ensure the uniformity of the response data of the subjects in different devices.

[0008] Third, it is necessary to record and save the eye-tracking data and visualize the eye movement data of the subjects. The original eye movement data is characterized by a large amount of data, which is not convenient for direct reading and interpretation. At the same time, when visualizing the eye movement data, it is necessary to combine the corresponding stimulus materials and the corresponding experimental content for intuitive display.

[0009] Fourth, in the traditional eye-tracking experiment mode, the eye movement data is independent data and needs to go through a certain data cleaning process to correspond with the questionnaire data and experimental data. This process also consumes a great deal of cost.

[0010] The above points are the important reasons why the current eye-tracking technology based on webcams has not been widely applied. Summary of the Invention

[0011] In view of the above problems, the present invention provides an online eye-tracking behavior experiment method and system based on a webcam.

[0012] The online eye-tracking behavior experiment method based on a webcam provided by the present invention includes the steps of:

[0013] S1. Embedding the eye-tracking experiment;

[0014] S2. Configuring the eye-tracking experiment;

[0015] S3. Answering the eye-tracking experiment;

[0016] S4. Visualizing the eye movement data.

[0017] Furthermore,

[0018] In the step S1, the eye-tracking experiment is designed as an independent section of an online questionnaire. At the same time, the eye-tracking experiment section and other questionnaire content sections are at the same level.

[0019] Furthermore,

[0020] The display order and display logic of each section, including the eye-tracking experiment section and other questionnaire content sections, are flexibly implemented through a process control function.

[0021] Furthermore,

[0022] The step S2 includes basic experiment style configuration, trial group configuration, trial stimulus configuration, trial response configuration, and trial feedback configuration.

[0023] Among them,

[0024] The basic experiment style configuration includes configuring the following: experiment name, instructions and conclusion, screen background color, experimental stimulus text color and font size, cross fixation point for switching between trials, trial presentation duration and switching method, full screen setting, progress bar display;

[0025] The trial group configuration includes configuring the following: trial group name, content and sequential movement within the group, presentation method of trials within the group;

[0026] The trial stimulus configuration includes configuring the following: trial description, stimulus type, display duration, inter-trial duration, and presented content, where the stimulus type is the content to be shown to the responder in the experiment;

[0027] The trial response configuration includes configuring the response method, and the response method includes at least one of continuing with any key, button, keyboard, and text input for response;

[0028] The trial feedback configuration includes configuring the following: whether there is feedback, feedback type, and feedback content, where the feedback type includes response duration and subject's answer, and the feedback content includes text, pictures, audio and video.

[0029] Furthermore,

[0030] The step S3 includes the steps:

[0031] S31. The user enters full screen;

[0032] S32. Pre-load the user's pictures and videos;

[0033] S33. Display the configured experimental instructions;

[0034] S34. Request the user's camera, and after obtaining the user's permission, start the camera, start collecting the user's facial information and help the user adjust their position. When the user's head position is in the center of the screen and the distance from the screen is the user's arm length, the detection passes and the user is allowed to continue the experiment;

[0035] S35. Calibrate the user's eyes. At nine positions in the upper left, upper middle, upper right, left middle, middle middle, right middle, lower left, lower middle, and lower right of the screen, white dots are respectively displayed to guide the user's eyes to follow the mouse trajectory and click on the white dots at these nine positions respectively. Repeat this three times, where the positions clicked in each round appear randomly. Collect the user's eye image information to be used as basic data for calibrating subsequent eye movement predictions.

[0036] S36. Verify the calibration result. At four positions in the upper left, upper right, lower left, and lower right of the screen, white dots are displayed again. The user needs to fixate on the dots at these four positions respectively. Finally, draw a circle with each of the dots at these four positions as the center to obtain four circles. Determine whether the eye movement points of the user for these four positions respectively fall within the four circles. When the accuracy rate reaches the expected level, it proves that the calibration is successful, and the user is allowed to continue the experiment. Among them, the radius range of the circle is 150 - 250 pixels. For any one of the four circles A, conduct a verification separately, and calculate the percent_in_roi of circle A during the verification, where percent_in_roi = the number of eye movement points falling within the circle / the total number of eye movement points. After conducting the verification for all four circles, average the percent_in_roi of the four circles to obtain the accuracy rate.

[0037] Accuracy rate within the circle = the number of eye movement points falling within the four circles / the total number of eye movement points.

[0038] S37. According to the configuration in step S2, start to display trials. Among them, display different stimuli according to the stimulus type, determine the display time according to the display duration, determine the response method of the trial according to the response configuration, and combine the user's eye movement data to judge the user's true selection situation to obtain accurate experimental results.

[0039] S38. According to the trial feedback configuration, combine the response result of the actual response situation and the final display duration to display trial feedback, and give some incentives for the response to improve the user's concentration.

[0040] S39. Display the configured experiment conclusion, turn off the camera and exit full screen.

[0041] S310. Upload the eye movement data of all trials of the user and the response data of the experiment.

[0042] Furthermore,

[0043] When conducting picture trials, use the following method 1 or method 2 for the experiment:

[0044] The method 1 includes: within the screen, select a fixed square area as the experimental area, the side length of the square area ranges from 30% to 70% of the screen width, the square area is in the exact middle of the screen, and then uniformly display the pictures within the square area, where the long side of the picture is the same as the side length of the square area, so as to ensure that the display range of the stimulus pictures for all experiments is of a 1:1 size;

[0045] The method 2 includes: adopting a full-screen display mode, while maintaining the aspect ratio of the picture, using the area where the picture is located as the experimental area, and only taking the eye movement data within the picture.

[0046] Furthermore,

[0047] The radius range of the circle is 200 pixels;

[0048] The side length of the square area is 50%.

[0049] The present invention also provides an online eye movement tracking behavior experiment system based on a web camera, which includes: an eye movement tracking experiment embedding module, an eye movement tracking experiment configuration module, an eye movement tracking experiment answering module, and an eye movement data visualization module,

[0050] Among them,

[0051] The eye movement tracking experiment embedding module is used to implement the above-mentioned step S1;

[0052] The eye movement tracking experiment configuration module is used to implement the above-mentioned step S2;

[0053] The eye movement tracking experiment answering module is used to implement the above-mentioned step S3;

[0054] The eye movement data visualization module is used to implement the above-mentioned step S4.

[0055] The beneficial effects of the online eye movement tracking behavior experiment method and system based on a web camera provided by the present invention are as follows:

[0056] 1. The present invention directly combines eye movement tracking and experiments. When creating an experiment, select to turn on eye movement tracking, so that users can focus on their own experiment design and questionnaire content, reducing the learning cost of eye movement devices and the cost of the devices themselves.

[0057] 2. Using the respondent's own computer as an eye movement tracking device, there will inevitably be differences in the device resolutions of different respondents. To avoid this problem, our "scheme of drawing a middle square area" and "scheme of keeping the picture ratio and making the picture fill as much as possible" can both effectively help the publisher eliminate interference data caused by resolution in advance.

[0058] 3. The amount of eye movement data is large, and users who are not good at programming may not be able to clean the data well, thus obtaining the eye movement data of each area stimulated by the picture. Our visualization application can help this part of users quickly check the data situation and obtain research results.

[0059] 4. The data of traditional eye movement devices is collected independently of the experiment, and users need to clean it by themselves to find out which eye movement data corresponds to each experimental stimulus. This process is very prone to errors. By embedding the experiment, we have made distinctions for users in the data, and the data that users finally collect is the data corresponding to each experimental stimulus.

[0060] Other features and advantages of the present invention will be described in the following specification, and in part will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained by the structures pointed out in the specification, claims and drawings. Brief Description of the Drawings

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0062] Figure 1 It shows a flowchart of an online eye movement tracking behavior experiment method based on a webcam according to an embodiment of the present invention. Detailed Embodiments

[0063] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs; the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above drawings are intended to cover non-exclusive inclusion. The terms "first", "second", "third", etc. in the specification and claims of this application or the above drawings are used to distinguish different objects and are not used to describe a specific order or primary-secondary relationship. The "plurality" referred to in this application means two or more (including two).

[0065] Reference to "embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0066] Figure 1 The flowchart of an online eye movement tracking behavior experiment method based on a webcam according to an embodiment of the present invention is shown. Refer to Figure 1 , the online eye movement tracking behavior experiment method based on a webcam includes the following steps.

[0067] S1. Embedding of the eye movement tracking experiment.

[0068] Design the eye movement tracking experiment as an independent section of an online questionnaire to ensure the independence of the eye movement tracking experiment. At the same time, the eye movement tracking experiment section is at the same level as other questionnaire content sections. The display order and display logic of each section, including the eye movement tracking experiment section and other questionnaire content sections, such as random display, can be flexibly implemented through the process control function. The other questionnaire content sections include: a questionnaire section containing various question types, a conjoint analysis section, a non-eye movement behavior experiment section, etc.

[0069] S2. Configuration of the eye movement tracking experiment.

[0070] It includes basic experiment style configuration, trial group configuration, trial stimulus configuration, trial response configuration, trial feedback configuration, etc. Here, a trial is a unit of the experiment, and generally includes a stimulus, a response method, and a response feedback. Generally, an experiment consists of multiple trials.

[0071] Among them, the basic experiment style configuration includes the following: experiment name, instructions and conclusion, screen background color, experiment stimulus text color and font size, cross fixation point for switching between trials, trial presentation duration and switching method, full screen setting, progress bar display, etc. The trial group configuration includes the following: trial group name, content and sequential movement within the group, presentation method within the group (such as whether it is random), etc. The trial stimulus configuration includes the following: trial description, stimulus type, display duration, duration between trials, and content to be presented, etc. The stimulus type is the content to be shown to the responder in the experiment, which can be audio, video, picture, text, etc. The trial response configuration includes the following: configure the response method, and the response method includes at least one of continuing with any key, button, keyboard, and text input. The trial feedback configuration includes the following: whether there is feedback, feedback type, and feedback content. The feedback type includes response duration and subject's answer, etc. The feedback content includes text, pictures, audio and video, etc. It should be noted that in the present invention, the subject refers to the responder, and the responder's response situation and response duration determine the content of the trial feedback.

[0072] S3. Conduct the eye-tracking experiment response.

[0073] S31. The user enters full screen. The eye-tracking experiment of the present invention is an experiment based on a computer camera. The acquisition area of the eye-tracking point is the entire computer screen. Therefore, the user is prohibited from exiting full screen.

[0074] S32. Pre-load the user's pictures and videos. To ensure that the user can complete the experiment without being affected by network factors, the present invention requires that all pictures and videos be downloaded before the start of the entire experiment.

[0075] S33. Display the configured experiment instructions. Before the start of the entire experiment, guide the user on how to respond to the experiment and some experiment specifications for this experiment.

[0076] S34. Request the user's camera. After obtaining the user's permission, start the camera, start collecting the user's facial information, and help the user adjust their position. When the user's head position is in the center of the screen and the distance from the screen is the user's arm length, the detection passes and the user is allowed to continue the experiment.

[0077] S35. Calibrate the user's eyeballs. At the 9 positions of the upper left, upper middle, upper right, left middle, middle middle, right middle, lower left, lower middle, and lower right of the screen, small white dots are respectively displayed to guide the user's eyeballs to follow the mouse trajectory and click on the small white dots at these 9 positions respectively. Repeat 3 rounds, and the positions clicked in each round appear randomly. Collect the user's eye image information for use as basic data to calibrate subsequent eye movement predictions.

[0078] S36. Verify the calibration result. At the upper left, upper right, lower left, and lower right positions on the screen, show small white dots again. The user needs to fixate on the dots at these four positions respectively. Finally, draw a circle with each of these four dots as the center, and determine whether the eye movement points (i.e., fixation points, and the original data collected in the present invention is the collection of fixation points) of the user for the above four positions fall within these four circles respectively. When the accuracy rate reaches the expected level, it proves that the calibration is successful and the user is allowed to continue the experiment. Among them, the radius range of the circle is 150 - 250 pixels (px), preferably 200 px; for any one of the four circles, say circle A, conduct a verification separately, and calculate the percent_in_roi of circle A during the verification period, such as within 3 seconds, where percent_in_roi = the number of eye movement points falling within the circle / the total number of eye movement points. After conducting the verification for all four circles, average the percent_in_roi of the four circles, that is, take the expectation to obtain the accuracy rate.

[0079] S37. According to the configuration in step S2, start showing trials. Show different stimuli according to the stimulus type, determine the display time according to the display duration, and determine the response method for this trial according to the response configuration. For example, show an advertisement on the left and right sides of the screen respectively and let the user choose which one has a better effect. The real choice of the user can be judged by combining the user's eye movement data to obtain more accurate experimental results. Among these trials, the picture trials are relatively special. Since the online eye movement experiment is carried out on the user's own device, the screen resolutions of different devices are different, so the final display of the picture will also be affected, ultimately affecting the accuracy of the eye movement experiment. To solve this problem, the present invention proposes two methods:

[0080] Method 1. Adopt a square picture presentation area design to ensure that the aspect ratio of the experimental stimulus pictures under all screens is 1:1, thus avoiding the influence of the screen width and height on the eye movement data. Specifically, within the screen, select a fixed square area as the experimental area. The side length range of the square area is 30% - 70% of the screen width, preferably 50%, and the square area is in the center of the screen. Then display the pictures uniformly within this square area. Among them, the long side of the picture is the same as the side length of the square area, that is, the picture is displayed or shown completely according to the long side, so as to ensure that the display range of all experimental stimulus pictures is 1:1 in size. The advantage of this solution is that all eye movement data within the square area can be obtained, that is, in the case where the picture display range is not 1:1, it can include the eye movement data outside the picture.

[0081] Method 2: Adopt a full-screen display method as much as possible. While maintaining the aspect ratio of the picture, use the area where the picture is located as the experimental area, and only take the eye movement data within the picture. The advantage of this method is that the display size of the picture is relatively larger than that of Method 1. The reason is that Method 1 essentially uniformly reduces the screen that actually plays the display role to the square area, that is, Method 1 adopts the square area display method to exclude the influence of resolution. While Method 2 only focuses on the points within the picture in the full-screen mode, so as long as the picture ratio is correct.

[0082] S38. According to the feedback configuration, combine the answer results and the final display duration of the actual answering situation, display the trial feedback, and give some incentives for the answering to improve the user's concentration.

[0083] S39. Display the configured experimental ending remarks, turn off the user's camera and exit the full screen.

[0084] S310. Upload the eye movement data of all trials of the user and the answering data of the experiment. Different from the traditional eye movement experiment, the eye movement data of this application is the eye movement data collected for each trial. The final eye movement data has been classified, and there is no need for the user to compare the time of the answering data and the time of the eye movement data, which greatly saves the time of data cleaning and effectively improves the accuracy of the data. And it can also calculate the percentage of eye movement points in each area for each trial according to the area of interest (AOI) area configured by the user.

[0085] S4. Visualize the eye movement data.

[0086] Select a certain data set for a certain trial. This data set includes the data of one subject or multiple subjects. Then, according to the selected data set, draw an eye movement heat map above the picture in the form of a heat map. Specifically include:

[0087] Only take the eye movement points within the experimental area, and use the upper left vertex of the experimental area as the origin of the coordinate axis. The distance from the left side of the experimental area is the abscissa of the eye movement point, and the distance from the upper side of the experimental area is the ordinate of the eye movement point. The original data of the eye movement point coordinates is obtained with the upper left corner of the screen as the origin.

[0088] Normalized abscissa of eye movement point = (abscissa of eye movement point - origin of coordinate axis) / side length of the upper side of the experimental area,

[0089] Normalized ordinate of eye movement point = (ordinate of eye movement point - origin of coordinate axis) / side length of the left side of the experimental area.

[0090] After the above formula calculation, the normalized eye movement point coordinate data within the experimental area can be obtained. At this time, the data of all selected subjects can be integrated;

[0091] The experimental area is sequentially divided into 100 small squares numbered from 1 to 100 and marked. The frequency, i.e., the number, of eye movement points in each small square is calculated. According to the frequency and the positions of the eye movement points, a heat map is drawn to achieve the visualization of eye movement data. The darker the color of the heat map, the more the frequency of the corresponding eye movement points at that place.

[0092] The present invention also provides an online eye movement tracking behavior experiment system based on a web camera. The system includes an eye movement tracking experiment embedding module, an eye movement tracking experiment configuration module, an eye movement tracking experiment answering module, and an eye movement data visualization module. The eye movement tracking experiment embedding module is used to implement step S1; the eye movement tracking experiment configuration module is used to implement step S2; the eye movement tracking experiment answering module is used to implement step S3, and the eye movement data visualization module is used to implement step S4.

[0093] Based on the current online eye movement tracking technology, to solve the above problems, the present invention proposes and designs a set of systems for online behavioral experiment design, answering, data saving, and eye movement heat map display that support eye movement tracking, enabling users to complete online eye movement behavioral experiment design and answering. It has the characteristics of low cost and wide application, and is of great help to the development and application of eye movement tracking technology in the field of behavioral experiments.

[0094] Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An online eye tracking behavior experimental method based on a webcam, characterized in that: Includes steps: S1, eye tracking experiment embedding; S2, the eye tracking experiment configuration; S3. Answer the eye tracking experiment; S4. Visualization of eye movement data.

2. The online eye tracking behavior experimental method based on a webcam according to claim 1, characterized in that: In step S1, the eye tracking experiment is designed as an independent section of an online questionnaire, and the eye tracking experiment section is on the same level as other questionnaire content sections.

3. The online eye tracking behavior experimental method based on a webcam according to claim 2, characterized in that: The display order and display logic of each section including the eye tracking experiment section and other questionnaire content sections can be flexibly realized through the process control function.

4. The online eye tracking behavior experimental method based on a webcam according to claim 3, characterized in that: The step S2 includes basic experimental pattern configuration, trial group configuration, trial stimulation configuration, trial answer configuration, and trial feedback configuration. in, The basic experiment style configuration includes the following configurations: experiment name, instructions and ending words, screen background color, experimental stimulus text color and font size, cross fixation point for switching between trials, trial presentation duration and switching mode, full screen setting, and progress bar display; The trial group configuration includes configuring the following contents: trial group name, trial content and sequential movement within the group, and presentation method of trials within the group; The trial stimulation configuration includes configuring the following contents: trial description, stimulation type, display duration, inter-trial duration and presented content, wherein the stimulation type is the content to be presented to the respondent in the experiment; The trial answer configuration includes configuring the answer mode, and the answer mode includes answering by using at least one of any key to continue, button, keyboard, and text input; The trial feedback configuration includes configuring the following contents: whether there is feedback, feedback type and feedback content, the feedback type includes answering time and subject's answer, and the feedback content includes text, picture, audio and video.

5. The online eye tracking behavior experimental method based on a webcam according to claim 4, characterized in that: The step S3 comprises the steps of: S31, the user enters the full screen; S32, preloading user's pictures and videos; S33, experimental instructions for display configuration; S34, requesting the user's camera, and after obtaining the user's permission, starting the camera, starting to collect the user's facial information and helping the user to adjust his position; when the user's head is located in the middle of the screen and the distance from the screen is the user's arm length, the detection is passed, and the user is allowed to continue the experiment; S35, calibrating the user's eyeballs, displaying white dots at 9 positions of the screen, namely, upper left, upper middle, upper right, middle left, middle middle, middle right, lower left, lower middle, and lower right, to guide the user's eyeballs to follow the mouse track and click the white dots at the 9 positions respectively, repeating 3 rounds, wherein the click positions appear randomly in each round, collecting the user's eye image information, and using it as basic data to calibrate subsequent eye movement prediction; S36, verify the calibration result, display white dots again at the upper left, upper right, lower left and lower right positions of the screen, and the user needs to look at the points at the four positions respectively. Finally, draw a circle with the points at the four positions as the center to get four circles, and judge whether the user's eye movement points at the four positions fall within the four circles respectively. When the accuracy reaches the expected level, it proves that the calibration is successful, and the user is allowed to continue the experiment, wherein the radius range of the circle is 150-250 pixels, and for any circle A among the four circles, perform a separate verification, and calculate the percent_in_roi of the circle A during the verification period = the number of eye movement points falling within the circle / the total number of eye movement points. After the verification is performed on the four circles, the percent_in_roi of the four circles are averaged, that is, the expectation is taken to obtain the accuracy rate; Accuracy rate within the circle = number of eye movement points falling within the four circles / total number of eye movement points; S37, according to the configuration performed in step S2, start presenting trials, wherein different stimuli are presented according to the stimulus type, the presentation time is determined according to the display duration, the answer mode of the trial is determined according to the answer configuration, and the actual selection of the user is judged in combination with the eye movement data of the user, so as to obtain accurate experimental results; S38, displaying trial feedback according to the trial feedback configuration, combined with the actual answer result and final display time, and providing some incentives for answering, so as to improve the user's concentration; S39, displaying the experiment ending statement of the configuration, closing the camera and exiting the full screen; S310, uploading the eye movement data of all trials and the experimental answer data of the user.

6. The online eye tracking behavior experimental method based on a webcam according to claim 5, characterized in that: When conducting the picture test, use the following method 1 or method 2 to conduct the experiment: The method 1 comprises: selecting a fixed square area as an experimental area in a screen, wherein the side length of the square area ranges from 30% to 70% of the screen width, and the square area is located in the middle of the screen, and then uniformly displaying pictures in the square area, wherein the long side of the picture is the same as the side length of the square area, thereby ensuring that the display range of the stimulus pictures of all experiments is 1:1; The method 2 includes: adopting a full-screen display mode, while maintaining the aspect ratio of the picture, taking the area where the picture is located as the experimental area, and only obtaining the eye movement data in the picture.

7. The online eye tracking behavior experimental method based on a webcam according to claim 6, characterized in that: The radius of the circle is 200 pixels; The side length of the square area is 50%.

8. An online eye tracking behavior experiment system based on a webcam, characterized in that: include: Eye tracking experiment embedding module, eye tracking experiment configuration module, eye tracking experiment answering module and eye tracking data visualization module. in, The eye tracking experiment embedding module is used to implement step S1 in any one of claims 1 to 7; The eye tracking experiment configuration module is used to implement step S2 in any one of claims 1 to 7; The eye tracking experiment answering module is used to implement step S3 in any one of claims 1 to 7; The eye movement data visualization module is used to implement step S4 in any one of claims 1 to 7.

Images