CN112987910A - Testing method, device, equipment and storage medium of eyeball tracking equipment - Google Patents
Testing method, device, equipment and storage medium of eyeball tracking equipment Download PDFInfo
- Publication number
- CN112987910A CN112987910A CN201911304381.1A CN201911304381A CN112987910A CN 112987910 A CN112987910 A CN 112987910A CN 201911304381 A CN201911304381 A CN 201911304381A CN 112987910 A CN112987910 A CN 112987910A
- Authority
- CN
- China
- Prior art keywords
- angle information
- distance
- deviation angle
- target
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/013—Eye tracking input arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/19—Sensors therefor
Abstract
The embodiment of the invention discloses a testing method, a testing device, equipment and a storage medium of eyeball tracking equipment. The method comprises the following steps: acquiring a vertical distance between eyes of a user and a screen, and determining the vertical distance as a first distance; acquiring a plurality of calculation fixation points generated when a user gazes at a target fixation point; determining deviation angle information according to the plurality of calculated fixation points, the target fixation point and the first distance; the deviation angle information comprises first deviation angle information and second target deviation angle information; and determining a test result according to the deviation angle information. According to the technical scheme of the embodiment of the invention, the accuracy and precision of the eyeball tracking equipment are represented by the deviation angle information, so that the accuracy and reliability of the test of the eyeball tracking equipment can be improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of eyeball tracking, in particular to a testing method, a testing device, testing equipment and a storage medium of eyeball tracking equipment.
Background
With the popularization and use of eyeball tracking technology in VR/AR head-mounted equipment and electronic equipment, especially the realization and development of virtual reality technology, eyeball tracking is a technology that VR equipment must be integrated, and its accuracy and precision gradually become the necessary basis for judging the performance of a piece of VR equipment. The accuracy refers to the difference between the calculated fixation point and the real fixation point when the user uses the eyeball tracking device, and the accuracy refers to the discrete degree of the eye movement data when the user continuously focuses on the same target fixation point.
Eyeball tracking, also known as gaze point tracking, is a technique that uses sensors to capture and extract eyeball feature information, measure eye movement, and estimate gaze direction or eye gaze point location. However, when the user uses the device, due to the characteristics of the eyeball tracking technology and the physiological characteristics of the human eyes, the accuracy of eyeball tracking differs with different spatial distribution, and the dispersion degrees of the eye movement data are different. The degree of dispersion of the eye movement data can be expressed as accuracy, which is an important index for determining the stability of the eyeball tracking.
However, since the accuracy and precision testing of the eye tracking device is a complicated process, there is no official uniform testing process. Therefore, there is a need for an eye tracking test method for determining the accuracy and stability of the gaze point of an eye tracking device in a three-dimensional application scene.
Disclosure of Invention
The invention provides a testing method, a testing device, testing equipment and a storage medium of eyeball tracking equipment, and aims to judge the accuracy and stability of a fixation point of the eyeball tracking equipment.
In a first aspect, an embodiment of the present invention provides a method for testing an eyeball tracking device, including:
acquiring a vertical distance between eyes of a user and a screen, and determining the vertical distance as a first distance;
the method comprises the steps of obtaining a plurality of calculation fixation points generated when a user gazes at a target fixation point, wherein the target fixation point is a point displayed on a screen watched by the user, and the calculation fixation points are points calculated according to a sight tracking technology and watched by the user;
determining deviation angle information according to the plurality of calculated fixation points, the target fixation point and the first distance; the deviation angle information comprises first deviation angle information and second target deviation angle information;
and determining a test result according to the deviation angle information.
Further, the acquiring a plurality of calculated gaze points generated when the user gazes at the target gaze point includes:
acquiring a plurality of eye images generated when a user watches a target fixation point;
and determining a plurality of calculation fixation points according to the plurality of eye images.
Further, the acquiring a plurality of calculated gaze points generated when the user gazes at the target gaze point includes:
acquiring a gazing angle of a user, and comparing the gazing angle with a set maximum field angle;
and reserving the calculated fixation point with the fixation angle smaller than the set maximum field angle.
Further, the obtaining of the gazing angle of the user includes:
acquiring the vertical foot points of the eyes of the user and the screen;
obtaining the distance between the calculation gazing point and the foot drop point, and determining the distance as a second distance;
acquiring the ratio of the second distance to the first distance, and determining the ratio as the first ratio;
and performing arc tangent calculation on the first ratio to obtain a user's gaze angle, wherein the gaze angle represents a gaze deviation angle of the user relative to the front of the front view.
Further, determining deviation angle information from at least one of the plurality of calculated gaze points, the target gaze point, and the first distance, comprising:
determining a central fixation point according to the plurality of calculation fixation points;
acquiring the distance between the central fixation point and the target fixation point, and determining the distance as a third distance;
obtaining the distances between the plurality of calculated fixation points and the central fixation point respectively to obtain a plurality of fourth distances;
and determining deviation angle information according to the first distance, the third distance and the plurality of fourth distances.
Further, determining a central gaze point from the plurality of calculated gaze points comprises:
calculating the horizontal coordinate average value of a plurality of calculation fixation points, and taking the horizontal coordinate average value as the horizontal coordinate of the central fixation point;
and calculating the mean value of the vertical coordinates of the plurality of calculation fixation points, and taking the mean value of the vertical coordinates as the vertical coordinate of the central fixation point.
Further, determining deviation angle information according to the first distance, the third distance and the plurality of fourth distances includes:
acquiring the ratio of the third distance to the first distance, and determining the ratio as a second ratio;
and performing arc tangent calculation on the second ratio to obtain first deviation angle information.
Further, determining deviation angle information according to the first distance, the third distance and the plurality of fourth distances includes:
obtaining the ratio of the plurality of fourth distances to the first distance respectively, and determining the ratio as a plurality of third ratios;
performing arc tangent calculation on the third ratios respectively to obtain second deviation angle information;
and acquiring an average value of the plurality of second deviation angle information to acquire second target deviation angle information.
Further, when the target fixation point is plural, determining deviation angle information according to the first distance, the third distance and the fourth distance, including:
the method includes the steps of obtaining a plurality of first deviation angle information corresponding to a plurality of target fixation points respectively, calculating an average value of the plurality of first deviation angle information, and taking the average value of the plurality of first deviation angle information as new first deviation angle information.
Further, when the target fixation point is plural, determining deviation angle information according to the first distance, the third distance and the fourth distance, including:
and acquiring a plurality of second target deviation angle information corresponding to the plurality of target fixation points respectively, calculating an average value of the plurality of second target deviation angle information, and taking the average value of the plurality of second target deviation angle information as new second target deviation angle information.
Further, determining a test result according to the deviation angle information, comprising:
if the first deviation angle information is smaller than a first preset standard value and/or the second deviation angle information is smaller than a second preset standard value, determining that the test result is qualified; otherwise, the determined test result is not qualified.
In a second aspect, an embodiment of the present invention further provides a testing apparatus for an eye tracking device, where the testing apparatus for an eye tracking device includes:
the first distance determining module is used for acquiring the vertical distance between the eyes of the user and the screen and determining the vertical distance as a first distance;
the system comprises a fixation point acquisition module, a fixation point acquisition module and a fixation point acquisition module, wherein the fixation point acquisition module is used for acquiring a plurality of calculation fixation points generated when a user gazes at a target fixation point, the target fixation point is a point displayed on a screen watched by the user, and the calculation fixation point is a point watched by the user calculated according to a sight tracking technology;
the angle information determining module is used for determining deviation angle information according to the plurality of calculation fixation points, the target fixation point and the first distance; the deviation angle information comprises first deviation angle information and second target deviation angle information;
and the test result determining module is used for determining a test result according to the deviation angle information.
In a third aspect, an embodiment of the present invention further provides an apparatus, where the apparatus includes:
one or more processors;
storage means for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors implement the method for testing an eye tracking device as provided in any of the embodiments of the present invention.
In a fourth aspect, embodiments of the present invention further provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method for testing an eye tracking device according to any of the embodiments of the present invention.
According to the embodiment of the invention, the vertical distance between the eyes of the user and the screen is obtained and determined as the first distance; the method comprises the steps of obtaining a plurality of calculation fixation points generated when a user watches a target fixation point, wherein the target fixation point is a point displayed on a screen watched by the user, and the calculation fixation point is a point watched by the user calculated according to a sight tracking technology; determining deviation angle information according to the plurality of calculated fixation points, the target fixation point and the first distance; the deviation angle information comprises first deviation angle information and second target deviation angle information; and determining a test result according to the deviation angle information. According to the testing method provided by the embodiment, the plurality of calculated fixation points are determined according to the plurality of eye images, and the deviation angle information is obtained according to the plurality of calculated fixation points so as to represent the accuracy and precision of the eyeball tracking equipment, so that the accuracy of testing the eyeball tracking equipment is improved. And determining deviation angle information according to the plurality of calculated fixation points, the target fixation point and the first distance, representing the accuracy and the precision of the eyeball tracking equipment through the deviation angle information, and improving the accuracy and the reliability of the test of the eyeball tracking equipment.
Drawings
Fig. 1 is a flowchart of a testing method of an eye tracking device according to a first embodiment of the invention;
fig. 2 is a flowchart of a testing method of an eyeball tracking apparatus in the second embodiment of the invention;
fig. 3 is a flowchart of a testing method of an eyeball tracking apparatus in a third embodiment of the invention;
fig. 4 is a schematic structural diagram of a testing apparatus of an eyeball tracking device in a fourth embodiment of the invention;
fig. 5 is a schematic structural diagram of an apparatus in the fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures. The test method can also be applied to the test of AR equipment and telemetric eyeball tracking equipment.
Example one
Fig. 1 is a flowchart of a testing method for an eye tracking device according to an embodiment of the present invention, where the testing method is applicable to a testing situation of the eye tracking device, the testing method can be executed by a testing apparatus of the eye tracking device, the testing apparatus of the eye tracking device can be implemented by software and/or hardware, and the testing apparatus of the eye tracking device can be configured on a computing device, and specifically includes the following steps:
The screen may be a virtual screen or a projection screen of the VR device, or may be any display screen with a display function.
Optionally, the vertical distance between the eyes of the user and the screen may be obtained by using methods such as distance measurement by a distance sensor, electromagnetic wave distance measurement, or image algorithm distance measurement. Specifically, the process of obtaining the first distance may be making a perpendicular line to the screen through the user's eyes, and taking a distance between the user's eyes and a perpendicular foot of the perpendicular line as the first distance.
And 120, acquiring a plurality of calculated fixation points generated when the user gazes at a target fixation point, wherein the target fixation point is a point displayed on a screen gazed by the user, and the calculated fixation points are points calculated according to a sight tracking technology and gazed by the user.
In this embodiment, the plurality of calculated gaze points may be obtained according to a gaze tracking technique, which may also be referred to as eye movement tracking, which is a technique for estimating a gaze direction and/or a gaze point of an eye by measuring eye movement. The method specifically comprises the steps that an eye image of a user to be detected is captured in real time, and the relative position of eye features is analyzed through the eye image of the user to be detected, so that the fixation point information of the user to be detected is obtained; or detecting eyeball movement through a capacitance value between the eyeballs and the capacitance plate to obtain the information of the fixation points of the user to be detected; or electrodes are arranged at the bridge of the nose, the forehead, the ears or the earlobes, the eyeball movement is detected through the detected myoelectric current signal mode, and the information of the fixation point of the user to be detected is obtained. Of course, other methods for acquiring the gaze point information of the user to be detected in real time may be adopted, which all fall within the scope of the present invention.
Taking the optical recording method as an example, the method for acquiring a plurality of calculated gaze points may comprise the steps of:
step 1201, acquiring a plurality of eye images generated when the user gazes at the target fixation point.
Optionally, the target fixation point may be multiple and may be located at any position of the whole screen;
optionally, the target fixation point should be of a suitable size, the color clearly contrasts with the background color, and the size is in a suitable proportion to the depth.
Specifically, when the user gazes at the target fixation point, the eye tracking device collects eye images of the user at fixed time intervals, thereby obtaining a plurality of eye images.
Optionally, for example, if the display duration of the target gaze point is 2 seconds, the eye tracking device may perform eye pattern acquisition within a duration of 0.5 to 1.5 seconds, and not acquire eye patterns in the former and latter two periods of time, so as to prevent the user from not looking at the target gaze point urgently or getting away from the target gaze point too early, which may cause inaccurate gaze capture.
Step 1202, determining a plurality of target calculation fixation points according to the plurality of eye images.
Specifically, eye features are extracted from the collected multiple eye images and used for establishing a fixation point estimation model, and multiple calculation fixation points are obtained through calculation.
In this embodiment, the eye tracking device includes an infrared camera and a near-infrared light source. Tracking of the eye can be achieved by optical recording. The principle of the optical recording method is that an infrared camera is used for recording the eye movement condition of a tested person, namely, an eye image capable of reflecting the eye movement is obtained, and eye features are extracted from the obtained eye image to be used for establishing an estimation model of the sight. Wherein the eye features may include: pupil location, pupil shape, iris location, iris shape, eyelid location, canthus location, spot location (or purkinje spot), and the like. Optical recording methods include pupil-cornea reflectometry. The principle of the pupil-cornea reflection method is that a near-infrared light source irradiates an eye, an infrared camera shoots the eye, and meanwhile, a reflection point of the light source on the cornea, namely a light spot, is shot, so that an eye image with the light spot is obtained.
Along with the rotation of the eyeball, the relative position relationship between the pupil center and the position coordinates of the light spot in the image changes. The collected eye images with the light spots can reflect the position change of the pupil light spots, and the sight direction is estimated according to the pupil light spots, so that the gazing direction of the user is obtained.
A plurality of calculation fixation points are determined according to the eye images, and deviation angle information is obtained according to the calculation fixation points so as to represent the accuracy and precision of the eyeball tracking equipment, so that the accuracy of testing the eyeball tracking equipment is improved.
Of course, the eye tracking device may be a MEMS micro-electromechanical system, including, for example, a MEMS infrared scanning mirror, an infrared light source, an infrared receiver; or a capacitance sensor which detects the eyeball movement through the capacitance value between the eyeball and the capacitance plate; and more, the device can be a myoelectric current detector which detects eye movement through a detected myoelectric current signal mode by placing an electrode at the bridge of the nose, forehead, ear or earlobe.
At present, there are various methods for the gaze tracking technology to acquire the gaze information of the user, which are not described in detail herein.
The first deviation angle information may be used to characterize the accuracy of the eye tracking device, and the second target deviation angle information may be used to characterize the accuracy of the eye tracking device.
Specifically, a central gaze point is determined according to the plurality of calculation gaze points, first deviation angle information is determined according to the distance between the central gaze point and the target gaze point and the first distance, a plurality of second deviation angle information is determined according to the distance between the plurality of calculation gaze points and the central gaze point and the first distance, then the average value of the plurality of second deviation angle information is obtained, and the second target deviation angle information is obtained.
And step 140, determining a test result according to the deviation angle information.
Specifically, when the first deviation angle information is smaller than a first preset standard value and/or the second deviation angle information is smaller than a second preset standard value, the test result of the eyeball tracking equipment is determined to be qualified, otherwise, the test result of the eyeball tracking equipment is determined to be unqualified.
Alternatively, the first predictive criterion value may be 0.5 ° and the second predictive criterion value may be 0.1 °.
It should be noted that the first prediction standard value and the second prediction standard value may be set to other values, and the specific set value is determined according to the accuracy of the design of the device itself and the specific requirements of the user.
According to the technical scheme of the embodiment, the vertical distance between the eyes of the user and the screen is obtained and determined as the first distance; the method comprises the steps of obtaining a plurality of calculation fixation points generated when a user watches a target fixation point, wherein the calculation fixation points are points watched by the user calculated according to a sight tracking technology; determining deviation angle information according to the plurality of calculated fixation points, the target fixation point and the first distance; the deviation angle information comprises first deviation angle information and second target deviation angle information; and determining a test result according to the deviation angle information. According to the testing method provided by the embodiment, the plurality of calculated fixation points are determined according to the plurality of eye images, and the deviation angle information is obtained according to the plurality of calculated fixation points so as to represent the accuracy and precision of the eyeball tracking equipment, so that the accuracy of testing the eyeball tracking equipment is improved. And determining deviation angle information according to the plurality of calculated gaze points, the target gaze point and the first distance, and representing the accuracy and precision of the eyeball tracking equipment by the deviation angle information, so that the reliability of testing the eyeball tracking equipment can be improved.
Example two
Fig. 2 is a flowchart of a testing method of an eyeball tracking apparatus according to a second embodiment of the invention. The technical scheme of the embodiment is further refined on the basis of the technical scheme, and specifically comprises the following steps:
And step 220, generating a plurality of calculation fixation points when the user watches the target fixation point, wherein the target fixation point is a point displayed on a screen watched by the user, and the calculation fixation points are points calculated according to a sight tracking technology and watched by the user.
The embodiment of the above steps is the same as the steps 110-120, and the description is not repeated here.
And step 230, acquiring the gazing angle of the user, and comparing the gazing angle with the set maximum field angle.
The gazing angle of the user can be understood as a deviation angle between a sight line when the user gazes at the target gazing point and a sight line when the user looks directly at the screen. The set maximum field angle may be understood as the maximum range that the user is allowed to gaze when the eye tracking device is tested.
Specifically, the process of obtaining the gaze angle of the user may be: firstly, acquiring the eye parts of the user and the drop foot point of the screen; obtaining the distance between the calculation gazing point and the foot drop point, and determining the distance as a second distance; acquiring the ratio of the second distance to the first distance, and determining the ratio as the first ratio; and performing arc tangent calculation on the first ratio to obtain the gazing angle of the user, wherein the gazing angle represents the gazing deviation angle of the user relative to the front of the front sight, and finally comparing a plurality of gazing angles obtained by a plurality of eye images with the set maximum field angle respectively.
The method for acquiring the drop foot point comprises the following steps: and (3) making a perpendicular line perpendicular to the screen through the positions of the eyes of the user, wherein the intersection point of the perpendicular line and the screen is a foot hanging point. The position of the eyes of the user can be the position of the left eye of the user, the position of the right eye of the user or the position of the middle point of the connecting line of the two eyes of the user.
Illustratively, let any one of the n calculated gaze points have coordinates of (x)i,yi) Wherein i can be any positive integer between 1 and n, and the coordinate of the foot point is (C)x,Cy) Then, the pixel difference PixelCenter between the gazing point and the nearest gazing point is calculated as:
if the first distance is D and the ratio of the pixels converted into the distances is screen size, the eyeball deflection angle of a single user with the gaze point calculated is:
the screen size is a preset ratio value, which is mainly related to the resolution of the image, and the resolution ppi (pixel per inch) expresses the number of pixels per inch of the image. For example, if ppi 300 means 300 pixels per inch and 1 inch 2.54 cm, the screen size 2.54/ppi can be obtained by scaling according to the above relationship, which is the scaled ratio of pixels to cm in the image at the current resolution.
And step 240, reserving the calculated fixation point with the fixation angle smaller than the set maximum field angle.
When the gaze angle is greater than or equal to the set maximum field angle, the fact that the sight line of the user drifts and does not fall in the screen or at the edge of the screen is indicated, the data collected at the position cannot be used as a sample for judging the accuracy and stability of the eyeball tracking equipment, and therefore the calculated gaze point with the gaze angle smaller than the set maximum field angle is selected.
Alternatively, the set maximum angle of view may be any value between 40 ° and 45 °. Other angle values are also possible.
And step 260, determining a test result according to the deviation angle information.
According to a large amount of experimental data, the accuracy and the precision of the eye tracking equipment are stable within a certain range, and the test result is not accurate after the accuracy exceeds the certain range. This range is defined empirically as the maximum angle of deflection of the eyeball. According to the technical scheme, the calculation fixation points are screened, the calculation fixation points with the fixation angles larger than or equal to the set maximum field angle are removed, and the problem that a user does not watch a target fixation point due to inattention or the sampling is inaccurate due to the fact that the fixation points drift when fixation conversion is carried out among different target fixation points is avoided.
EXAMPLE III
Fig. 3 is a flowchart of a testing method of an eyeball tracking device according to a third embodiment of the invention. The technical scheme of the embodiment is further refined on the basis of the technical scheme, and specifically comprises the following steps:
in step 310, a vertical distance between the eyes of the user and the screen is obtained and determined as a first distance.
And 320, acquiring a plurality of calculated fixation points generated when the user gazes at the target fixation point, wherein the target fixation point is a point displayed on a screen watched by the user, and the calculated fixation point is a point watched by the user calculated according to a sight tracking technology.
The embodiment of the above steps is the same as the steps 110-120, and the description is not repeated here.
A central gaze point is understood to mean the central position of a plurality of calculated gaze points. Specifically, the central gaze point may be obtained by: calculating the horizontal coordinate average value of a plurality of calculation fixation points, and taking the horizontal coordinate average value as the horizontal coordinate of the central fixation point; and calculating the mean value of the vertical coordinates of the plurality of calculation fixation points, and taking the mean value of the vertical coordinates as the vertical coordinate of the central fixation point.
Illustratively, let us assume that the coordinates of the point of gaze are calculated as (x)1,y1)、(x2,y2)……(xn,yn) Wherein n is the number of the calculated fixation points corresponding to a single target fixation point, and the coordinate of the central fixation point is (X, Y), then the coordinate calculation mode of the central fixation point is as follows:
and 340, acquiring the distance between the central fixation point and the target fixation point, and determining the distance as a third distance.
Illustratively, let the center fixation point coordinate be
The coordinate of the target fixation point is (T)x,Ty) According to the pythagorean theorem, the pixel difference PixelError from the central fixation point to the target fixation point is as follows:
the proportional value of the distance converted by the pixels is screen size, and the pixel difference value from the central gaze point to the target gaze point is converted into the distance screen size × PixelError, that is, the third distance.
And step 350, obtaining the distances between the plurality of calculated fixation points and the central fixation point respectively, and obtaining a plurality of fourth distances.
Specifically, the distances between each of the calculated gazing points and the center gazing point are calculated as a plurality of different fourth distances.
Exemplarily, let the ith coordinate of the n calculated gazing points be (x)i,yi) Wherein i can be any positive integer between 1-n, and the center fixation pointThe coordinates are
Calculating the pixel difference PixelErri from the fixation point to the central fixation point according to the ith Pythagorean theoremiComprises the following steps:
the proportional value of the distance converted by the pixels is screen size, and the pixel difference value from the ith calculation fixation point to the central fixation point is converted into the distance screen size pixel ErriiI.e. the ith fourth distance. A plurality of fourth distances is obtained according to the above formula.
And step 360, determining deviation angle information according to the first distance, the third distance and the plurality of fourth distances.
Wherein the deviation angle information includes first deviation angle information and second target deviation angle information.
Specifically, a ratio of the third distance to the first distance is obtained and determined as a second ratio; and performing arc tangent calculation on the second ratio to obtain first deviation angle information.
Wherein the first deviation angle information indicates an accuracy of the eye tracking device, and the smaller the first deviation angle is, the higher the accuracy of the eye tracking device is.
For example, if the first distance is D, the first deviation angle information angleraccuracy is:
specifically, the ratio of each of the plurality of fourth distances to the first distance is obtained and determined as a plurality of third ratios; performing arc tangent calculation on the third ratios respectively to obtain second deviation angle information; and acquiring an average value of the plurality of second deviation angle information to acquire second target deviation angle information.
Wherein the second target deviation angle information indicates the accuracy of the eye tracking device, and the smaller the second target deviation angle is, the smaller the degree of dispersion of the eye movement data is, and the higher the accuracy of the eye tracking device is.
Exemplarily, assuming that the first distance is D, the second deviation angle information singleangleErri of the ith calculation fixation pointiComprises the following steps:
among them, singleangleErriiIt can be understood that the accuracy of the ith calculated point of regard is calculated.
When there are n calculated gaze points for a single target gaze point, n is a positive integer, and the second target deviation angle information AnglePrecision is:
specifically, when the target gaze point is multiple, multiple pieces of first deviation angle information corresponding to the multiple target gaze points are obtained, an average value of the multiple pieces of first deviation angle information is calculated, and the average value of the multiple pieces of first deviation angle information is used as new first deviation angle information.
Specifically, when the target gaze points are multiple, multiple pieces of second target deviation angle information corresponding to the multiple target gaze points are obtained, an average value of the multiple pieces of second target deviation angle information is calculated, and the average value of the multiple pieces of second target deviation angle information is used as new second target deviation angle information.
And step 370, determining a test result according to the deviation angle information.
The embodiment of this step is the same as step 105, and will not be repeated here.
According to the technical scheme of the embodiment, the deviation angle information is determined according to the plurality of calculated fixation points, the target fixation point and the first distance, the accuracy and precision of the eyeball tracking equipment are represented through the deviation angle information, and the reliability of testing the eyeball tracking equipment can be improved.
Example four
Fig. 4 is a schematic structural diagram of a testing apparatus of an eye tracking device according to a fourth embodiment of the present invention, the testing apparatus of the eye tracking device includes: the first distance determining module 410, the gazing point obtaining module 420, the angle information determining module 430, and the test result determining module 440.
The first distance determining module 410 is configured to obtain a vertical distance between the eyes of the user and the screen, and determine the vertical distance as the first distance; a gaze point obtaining module 420, configured to obtain a plurality of calculated gaze points generated when a user gazes at a target gaze point, where the target gaze point is a point displayed on a screen gazed by the user, and the calculated gaze point is a point gazed by the user calculated according to a gaze tracking technology; an angle information determining module 430, configured to determine deviation angle information according to the plurality of calculated gaze points, the target gaze point, and the first distance; the deviation angle information comprises first deviation angle information and second target deviation angle information; and a test result determining module 440, configured to determine a test result according to the deviation angle information.
According to the technical scheme, the problem that no official unified test on the accuracy and the accuracy process of the eyeball tracking equipment exists at the present stage is solved, and the effect of determining the accuracy and the stability of the fixation point of the eyeball tracking equipment in the three-dimensional application scene is achieved.
Optionally, the gazing point obtaining module 420 includes:
the image acquisition unit is used for acquiring a plurality of eye images generated when a user gazes at a target fixation point;
and the fixation point determining unit is used for determining a plurality of calculation fixation points according to the eye images.
Optionally, the gazing point determining module 420 further includes:
and the gazing angle determining unit is used for acquiring the gazing angle of the user.
And the fixation point selecting unit is used for comparing the fixation angle with the set maximum field angle and reserving the calculation fixation point of which the fixation angle is smaller than the set maximum field angle.
Furthermore, the gaze angle determination unit is also used for acquiring a foot drop point between the eyes of the user and the screen; obtaining the distance between the calculated gazing point and the foot drop point, and determining the distance as a second distance; acquiring the ratio of the second distance to the first distance, and determining the ratio as the first ratio; and performing arc tangent calculation on the first ratio to obtain the gazing angle of the user, wherein the gazing angle represents the gazing deviation angle of the user relative to the front of the front view.
Optionally, the angle information determining module 430 includes:
and the central fixation point determining unit is used for determining a central fixation point according to the plurality of calculation fixation points.
And the third distance determining unit is used for acquiring the distance between the central fixation point and the target fixation point and determining the distance as a third distance.
And the fourth distance determining unit is used for acquiring the distances between the plurality of calculated fixation points and the central fixation point respectively to acquire a plurality of fourth distances.
And the angle information determining unit is used for determining deviation angle information according to the first distance, the third distance and the plurality of fourth distances.
Further, the central fixation point determining unit is further configured to calculate an average of abscissa of the plurality of calculated fixation points, and use the average of the abscissa as an abscissa of the central fixation point; and calculating the mean value of the vertical coordinates of the plurality of calculation fixation points, and taking the mean value of the vertical coordinates as the vertical coordinate of the central fixation point.
Further, the angle information determining unit is further configured to obtain a ratio of the third distance to the first distance, and determine the ratio as a second ratio; and performing arc tangent calculation on the second ratio to obtain first deviation angle information.
Further, the angle information determining unit is further configured to obtain ratios of the plurality of fourth distances to the first distance, and determine the ratios as a plurality of third ratios; performing arc tangent calculation on the third ratios respectively to obtain second deviation angle information; and acquiring an average value of the plurality of second deviation angle information to acquire second target deviation angle information.
Further, the angle information determining unit is further configured to, when the target gaze point is multiple, obtain multiple first deviation angle information corresponding to the multiple target gaze points, respectively, and calculate an average value of the multiple first deviation angle information, and use the average value of the multiple first deviation angle information as new first deviation angle information.
Further, the angle information determining unit is further configured to, when the target gaze point is multiple, obtain multiple second target deviation angle information corresponding to the multiple target gaze points, respectively, and calculate an average value of the multiple second target deviation angle information, and use the average value of the multiple second target deviation angle information as new second target deviation angle information.
Optionally, the test result determining module 440 is specifically configured to: if the first deviation angle information is smaller than a first preset standard value and/or the second deviation angle information is smaller than a second preset standard value, determining that the test result is qualified; otherwise, the determined test result is not qualified.
The testing device for the eyeball tracking equipment provided by the embodiment of the invention can execute the testing method for the eyeball tracking equipment provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE five
Fig. 5 is a schematic structural diagram of an apparatus according to a fifth embodiment of the present invention, as shown in fig. 5, the apparatus includes a processor 510, a memory 520, an input device 530, and an output device 540; the number of the processors 510 in the device may be one or more, and one processor 510 is taken as an example in fig. 5; the processor 510, the memory 520, the input device 530 and the output device 540 of the apparatus may be connected by a bus or other means, as exemplified by the bus connection in fig. 5.
The memory 520 may be used as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the testing method of the eye tracking apparatus according to the embodiments of the present invention (e.g., the first distance determining module 410, the gazing point obtaining module 420, the angle information determining module 430, and the testing result determining module 440). The processor 510 executes various functional applications and data processing of the device by executing software programs, instructions and modules stored in the memory 520, so as to implement the testing method of the eye tracking device.
The memory 520 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 520 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 520 may further include memory located remotely from processor 510, which may be connected to devices through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 530 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the computing device, and may include a keyboard and a mouse, etc. The output device 540 may include a display device such as a display screen.
EXAMPLE six
A sixth embodiment of the present invention also provides a storage medium containing computer-executable instructions that, when executed by a computer processor, perform a method for testing an eye tracking apparatus.
Of course, the storage medium containing computer-executable instructions provided by the embodiments of the present invention is not limited to the above method operations, and may also perform related operations in a testing method of an eyeball tracking apparatus provided by any embodiments of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods of the embodiments of the present invention.
It should be noted that, in the above embodiment of the testing apparatus of the eyeball tracking device, the included units and modules are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments illustrated herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (14)
1. A method of testing an eye tracking device, comprising:
acquiring a vertical distance between eyes of a user and a screen, and determining the vertical distance as a first distance;
the method comprises the steps of obtaining a plurality of calculation fixation points generated when a user gazes at a target fixation point, wherein the target fixation point is a point displayed on a screen watched by the user, and the calculation fixation points are points calculated according to a sight tracking technology and watched by the user;
determining deviation angle information according to the plurality of calculated fixation points, the target fixation point and the first distance; the deviation angle information comprises first deviation angle information and second target deviation angle information;
and determining a test result according to the deviation angle information.
2. The method of claim 1, wherein the obtaining a plurality of calculated gaze points generated when a user gazes at a target gaze point comprises:
acquiring a plurality of eye images generated when a user watches a target fixation point;
and determining a plurality of calculation fixation points according to the plurality of eye images.
3. The method of claim 2, wherein the obtaining a plurality of calculated gaze points generated when a user gazes at a target gaze point comprises:
acquiring a gazing angle of a user, and comparing the gazing angle with a set maximum field angle;
and reserving the calculated fixation point with the fixation angle smaller than the set maximum field angle.
4. The method of claim 3, wherein the obtaining the gaze angle of the user comprises:
acquiring the vertical foot points of the eyes of the user and the screen;
obtaining the distance between the calculation fixation point and the foot drop point, and determining the distance as a second distance;
acquiring the ratio of the second distance to the first distance, and determining the ratio as a first ratio;
and performing arc tangent calculation on the first ratio to obtain the gazing angle of the user, wherein the gazing angle represents the gazing deviation angle of the user relative to the front of the front view.
5. The method of claim 1, wherein determining deviation angle information from the plurality of calculated gaze points, the target gaze point, and the first distance comprises:
determining a central fixation point according to the plurality of calculation fixation points;
acquiring the distance between the central fixation point and the target fixation point, and determining the distance as a third distance;
obtaining the distances between the plurality of calculated fixation points and the central fixation point respectively to obtain a plurality of fourth distances;
determining deviation angle information according to the first distance, the third distance and the plurality of fourth distances.
6. The method of claim 5, wherein determining a central gaze point from the plurality of calculated gaze points comprises:
calculating the horizontal coordinate average value of the plurality of calculation fixation points, and taking the horizontal coordinate average value as the horizontal coordinate of the central fixation point;
and calculating the mean value of the vertical coordinates of the plurality of calculation fixation points, and taking the mean value of the vertical coordinates as the vertical coordinate of the central fixation point.
7. The method of claim 5, wherein determining deviation angle information from the first distance, the third distance, and the plurality of fourth distances comprises:
acquiring the ratio of the third distance to the first distance, and determining the ratio as a second ratio;
and performing arc tangent calculation on the second ratio to obtain first deviation angle information.
8. The method of claim 5, wherein determining deviation angle information from the first distance, the third distance, and the plurality of fourth distances comprises:
obtaining ratios of the plurality of fourth distances to the first distance respectively, and determining the ratios as a plurality of third ratios;
performing arc tangent calculation on the third ratios respectively to obtain second deviation angle information;
and acquiring an average value of the plurality of second deviation angle information to acquire second target deviation angle information.
9. The method of claim 7, wherein when the target gaze point is plural, the determining deviation angle information from the first distance, the third distance, and the fourth distances comprises:
the method includes the steps of obtaining a plurality of first deviation angle information corresponding to a plurality of target fixation points respectively, calculating an average value of the plurality of first deviation angle information, and taking the average value of the plurality of first deviation angle information as new first deviation angle information.
10. The method of claim 8, wherein when the target gaze point is plural, the determining deviation angle information from the first distance, the third distance, and the fourth distances comprises:
and acquiring a plurality of second target deviation angle information corresponding to the plurality of target fixation points respectively, calculating an average value of the plurality of second target deviation angle information, and taking the average value of the plurality of second target deviation angle information as new second target deviation angle information.
11. The method of claim 1, wherein determining a test result from the deviation angle information comprises:
if the first deviation angle information is smaller than a first preset standard value and/or the second deviation angle information is smaller than a second preset standard value, determining that the test result is qualified; otherwise, the determined test result is not qualified.
12. A test apparatus for an eye tracking device, comprising:
the first distance determining module is used for acquiring the vertical distance between the eyes of the user and the screen and determining the vertical distance as a first distance;
the system comprises a fixation point acquisition module, a fixation point acquisition module and a fixation point acquisition module, wherein the fixation point acquisition module is used for acquiring a plurality of calculation fixation points generated when a user gazes at a target fixation point, the target fixation point is a point displayed on a screen watched by the user, and the calculation fixation point is a point watched by the user calculated according to a sight tracking technology;
an angle information determination module for determining deviation angle information according to the plurality of calculation fixation points, the target fixation point and the first distance; the deviation angle information comprises first deviation angle information and second target deviation angle information;
and the test result determining module is used for determining a test result according to the deviation angle information.
13. An apparatus, characterized in that the apparatus comprises:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method of testing an eye tracking device according to any of claims 1-11.
14. A storage medium containing computer-executable instructions for performing a method of testing an eye tracking device according to any one of claims 1-11 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911304381.1A CN112987910B (en) | 2019-12-17 | 2019-12-17 | Testing method, device, equipment and storage medium of eyeball tracking equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911304381.1A CN112987910B (en) | 2019-12-17 | 2019-12-17 | Testing method, device, equipment and storage medium of eyeball tracking equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112987910A true CN112987910A (en) | 2021-06-18 |
| CN112987910B CN112987910B (en) | 2023-04-07 |
Family
ID=76342484
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911304381.1A Active CN112987910B (en) | 2019-12-17 | 2019-12-17 | Testing method, device, equipment and storage medium of eyeball tracking equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112987910B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113589532A (en) * | 2021-07-30 | 2021-11-02 | 歌尔光学科技有限公司 | Display calibration method and device of head-mounted equipment, head-mounted equipment and storage medium |
| CN114578975A (en) * | 2022-05-09 | 2022-06-03 | 南昌虚拟现实研究院股份有限公司 | Method and system for evaluating quality of fixation point of eye movement tracking equipment |
| CN114646457A (en) * | 2022-05-20 | 2022-06-21 | 南昌虚拟现实研究院股份有限公司 | Eye tracking accuracy testing method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003307774A (en) * | 2002-04-17 | 2003-10-31 | Canon Inc | Optical apparatus with line-of-sight detecting function |
| US20150049013A1 (en) * | 2013-08-19 | 2015-02-19 | Qualcomm Incorporated | Automatic calibration of eye tracking for optical see-through head mounted display |
| CN104808836A (en) * | 2014-01-23 | 2015-07-29 | 京瓷办公信息系统株式会社 | Electronic Device, Method, and Program for Supporting Touch Panel Operation |
| CN108968907A (en) * | 2018-07-05 | 2018-12-11 | 四川大学 | The bearing calibration of eye movement data and device |
| CN109558012A (en) * | 2018-12-26 | 2019-04-02 | 北京七鑫易维信息技术有限公司 | Eyeball tracking method and device |
| CN109976514A (en) * | 2019-03-01 | 2019-07-05 | 四川大学 | Eye movement data bearing calibration based on eyeball error model |
| CN110427101A (en) * | 2019-07-08 | 2019-11-08 | 北京七鑫易维信息技术有限公司 | Calibration method, device, equipment and the storage medium of eyeball tracking |
-
2019
- 2019-12-17 CN CN201911304381.1A patent/CN112987910B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003307774A (en) * | 2002-04-17 | 2003-10-31 | Canon Inc | Optical apparatus with line-of-sight detecting function |
| US20150049013A1 (en) * | 2013-08-19 | 2015-02-19 | Qualcomm Incorporated | Automatic calibration of eye tracking for optical see-through head mounted display |
| CN104808836A (en) * | 2014-01-23 | 2015-07-29 | 京瓷办公信息系统株式会社 | Electronic Device, Method, and Program for Supporting Touch Panel Operation |
| CN108968907A (en) * | 2018-07-05 | 2018-12-11 | 四川大学 | The bearing calibration of eye movement data and device |
| CN109558012A (en) * | 2018-12-26 | 2019-04-02 | 北京七鑫易维信息技术有限公司 | Eyeball tracking method and device |
| CN109976514A (en) * | 2019-03-01 | 2019-07-05 | 四川大学 | Eye movement data bearing calibration based on eyeball error model |
| CN110427101A (en) * | 2019-07-08 | 2019-11-08 | 北京七鑫易维信息技术有限公司 | Calibration method, device, equipment and the storage medium of eyeball tracking |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113589532A (en) * | 2021-07-30 | 2021-11-02 | 歌尔光学科技有限公司 | Display calibration method and device of head-mounted equipment, head-mounted equipment and storage medium |
| CN114578975A (en) * | 2022-05-09 | 2022-06-03 | 南昌虚拟现实研究院股份有限公司 | Method and system for evaluating quality of fixation point of eye movement tracking equipment |
| CN114646457A (en) * | 2022-05-20 | 2022-06-21 | 南昌虚拟现实研究院股份有限公司 | Eye tracking accuracy testing method and system |
| CN114646457B (en) * | 2022-05-20 | 2022-08-12 | 南昌虚拟现实研究院股份有限公司 | Eye movement tracking accuracy testing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112987910B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109086726B (en) | Local image identification method and system based on AR intelligent glasses | |
| CN112987910B (en) | Testing method, device, equipment and storage medium of eyeball tracking equipment | |
| Lee et al. | 3D gaze tracking method using Purkinje images on eye optical model and pupil | |
| CN109008944B (en) | Sight line measuring device, ROM, and sight line measuring method | |
| EP2150170A1 (en) | Methods and apparatus for estimating point-of-gaze in three dimensions | |
| JP2018196730A (en) | Method and system for monitoring eye position | |
| KR20120060978A (en) | Method and Apparatus for 3D Human-Computer Interaction based on Eye Tracking | |
| CN108537103B (en) | Living body face detection method and device based on pupil axis measurement | |
| CN114931353B (en) | Convenient and fast contrast sensitivity detection system | |
| JP2019215688A (en) | Visual line measuring device, visual line measurement method and visual line measurement program for performing automatic calibration | |
| JP6881755B2 (en) | Line-of-sight detection calibration methods, systems, and computer programs | |
| Tatler et al. | Eye movement recordings in natural settings | |
| AU2014234955A1 (en) | Automatic detection of task transition | |
| JP5719216B2 (en) | Gaze measurement apparatus and gaze measurement program | |
| JP2002000567A (en) | Method of measuring pupil center position and method of detecting view point position | |
| EP3922166B1 (en) | Display device, display method and display program | |
| Bozomitu et al. | Methods of control improvement in an eye tracking based human-computer interface | |
| CN113491502A (en) | Eyeball tracking calibration inspection method, device, equipment and storage medium | |
| CN114740966A (en) | Multi-modal image display control method and system and computer equipment | |
| CN112784655A (en) | Living body detection method and device based on gazing information and detection equipment | |
| JP2021096537A (en) | Biological information acquisition device, terminal device, biological information acquisition method, biological information acquisition program, and computer readable recording medium | |
| CN109634431B (en) | Medium-free floating projection visual tracking interaction system | |
| CN103764015A (en) | Blink measurement device, method therefor and program | |
| CN109917923A (en) | Method and terminal device based on free movement adjustment watching area | |
| RU2818028C1 (en) | Method and device for calibration in oculography |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |