Light spot determination method, device, equipment and storage medium

Abstract

The embodiment of the present invention discloses a light spot determination method, device, equipment and storage medium. It includes: determining the data change curve and anchor deviation of each light source based on the historical characteristic data cached by each light source; the characteristic data includes pupil information and light spot information; obtaining the first pupil information and first light spot information corresponding to the light source that is lit at the current moment; correcting the first pupil information according to the anchor deviation of the lit light source to obtain the target pupil information; for the unlit light source, determining the target light spot information of each unlit light source according to the timestamp of the current moment and the data change curve. The light spot determination method provided by the embodiment of the present invention corrects the first pupil information according to the anchor deviation of the lit light source, and determines the target light spot information of each unlit light source according to the timestamp of the current moment and the data change curve. It can realize the determination of the light spot of the unlit light source in the flicker-type eye tracker, thereby improving the accuracy of eye tracking.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of eye tracking technology, and in particular to a light spot determination method, device, equipment, and storage medium. Background Art

[0002] Currently, eye trackers are basically divided into two categories: non-flicker eye trackers and flicker eye trackers. For non-flicker eye trackers, each time the camera captures an image, all deployed infrared light sources are lit, that is, the light spots formed by all infrared light sources on the pupil cornea are visible. For flicker eye trackers, the deployed infrared light sources are alternately lit, that is, each time the camera captures an image, only the light spot formed by a certain infrared light source on the pupil cornea is visible. In the process of gaze point estimation, it is impossible to obtain the gaze point position information if only relying on the information of a single light spot. Therefore, for flicker eye trackers, it is particularly important to determine the light spot information of the currently unlit infrared light source. Summary of the Invention

[0003] Embodiments of the present invention provide a light spot determination method, apparatus, device, and storage medium to enable determination of the light spot of a currently unlit light source in a scintillation-type eye tracker, thereby improving the accuracy of eye tracking.

[0004] In a first aspect, an embodiment of the present invention provides a light spot determination method, which is used in a scintillation eye tracker, wherein the scintillation eye tracker includes at least two light sources, and the at least two light sources are alternately illuminated to illuminate the eye; the method includes:

[0005] Determine the data change curve and anchoring deviation of each light source based on the historical feature data cached by each light source; the feature data includes pupil information and light spot information;

[0006] Obtaining the first pupil information and the first light spot information corresponding to the light source currently lit;

[0007] Correcting the first pupil information according to the anchoring deviation of the illuminated light source to obtain target pupil information;

[0008] For unlit light sources, target light spot information of each unlit light source is determined according to the timestamp of the current moment and the data change curve.

[0009] Furthermore, the historical feature data includes real feature data and predicted feature data. The data change curve of each light source is determined based on the historical feature data cached by each light source, including:

[0010] For each light source, extract a first set number of real feature data closest to the current moment;

[0011] A straight line or curve fitting is performed on the set number of real characteristic data to obtain a data transformation curve of the light source; the transformation curve is used to represent the corresponding relationship between the timestamp and the characteristic data.

[0012] Furthermore, the target light spot information of each unlit light source is determined according to the current timestamp and the data change curve, including:

[0013] The light spot information corresponding to the timestamp at the current moment is searched in the data change curve to determine the target light spot information of the unlit light source.

[0014] Furthermore, the real feature data includes real pupil information; and determining the anchoring deviation of each light source based on the historical feature data cached by each light source includes:

[0015] For each light source, calculating average pupil information of a second set amount of real pupil information;

[0016] One of the light sources is set as a standard light source, and the deviation between the average pupil information of each light source and the average pupil information of the standard light source is calculated, and the deviation is used to determine the anchor deviation of each light source.

[0017] Furthermore, the first pupil information is corrected according to the anchoring deviation of the light source to obtain target pupil information, including:

[0018] If the light source is a standard light source, determining the first pupil information as target pupil information;

[0019] If the illuminated light source is a non-standard light source, the first pupil information and the anchoring deviation of the non-standard light source are accumulated to obtain target pupil information.

[0020] Furthermore, before determining the data change curve and anchoring deviation of each light source based on the historical characteristic data cached by each light source, the method further includes:

[0021] Cache the characteristic data obtained when each light source is turned on;

[0022] The cached feature data is screened for anomalies and the abnormal data is deleted.

[0023] Furthermore, the cached feature data is screened for anomalies, including:

[0024] Determine feature data whose pupil information has a difference with adjacent feature data exceeding a set threshold as abnormal data; or

[0025] The eye movement trajectory is fitted based on pupil information of the cached feature data, and feature data that deviates from the movement trajectory is determined as abnormal data.

[0026] In a second aspect, an embodiment of the present invention further provides a light spot determination device, which is provided in a scintillation eye tracker, wherein the scintillation eye tracker includes at least two light sources, and the at least two light sources are alternately illuminated to illuminate the eye; the device includes:

[0027] A data change curve and anchoring deviation determination module is used to determine the data change curve and anchoring deviation of each light source based on the historical characteristic data cached by each light source; the characteristic data includes pupil information and light spot information;

[0028] A first feature data acquisition module is used to obtain first pupil information and first light spot information corresponding to the light source that is currently lit;

[0029] a target pupil information acquisition module, configured to correct the first pupil information according to the anchoring deviation of the illuminated light source to obtain target pupil information;

[0030] The target light spot information determination module is used to determine the target light spot information of each unlit light source according to the timestamp of the current moment and the data change curve.

[0031] In a third aspect, an embodiment of the present invention further provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the light spot determination method as described in the embodiment of the present invention is implemented.

[0032] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processing device, implements the light spot determination method as described in an embodiment of the present invention.

[0033] The embodiments of the present invention disclose a light spot determination method, device, equipment and storage medium. The method is used in a flicker-type eye tracker, which includes at least two light sources, which are alternately lit to illuminate the eye; the method includes: determining the data change curve and anchor deviation of each light source based on the historical feature data cached by each light source; obtaining the first pupil information and first light spot information corresponding to the light source that is lit at the current moment; correcting the first pupil information based on the anchor deviation of the lit light source to obtain the target pupil information; for the unlit light source, determining the target light spot information of each unlit light source based on the timestamp and data change curve at the current moment. The light spot determination method provided by the embodiment of the present invention corrects the first pupil information based on the anchor deviation of the lit light source, and determines the target light spot information of each unlit light source based on the timestamp and data change curve at the current moment. This can realize the determination of the light spot of the unlit light source in the flicker-type eye tracker, thereby improving the accuracy of eye tracking. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a flow chart of a light spot determination method in Embodiment 1 of the present invention;

[0035] Figure 2 is the eye image collected when the light source in the first embodiment of the present invention is on;

[0036] Figure 3 is the eye image collected when the light source in the first embodiment of the present invention is on;

[0037] Figure 4 is the eye image collected when the light source in the first embodiment of the present invention is on;

[0038] Figure 5 is a structural diagram of a light spot determination device in embodiment 2 of the present invention;

[0039] Figure 6 It is a structural diagram of a computer device in embodiment 3 of the present invention. DETAILED DESCRIPTION

[0040] The present invention will be further described in detail below with reference to the accompanying drawings and examples. It will be understood that the specific embodiments described herein are intended only to illustrate the present invention and are not intended to limit the present invention. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all structures.

[0041] Example 1

[0042] Figure 1 This is a flow chart of a light spot determination method provided in Example 1 of the present invention. This embodiment is applicable to determining light spot information for a currently unlit light source in a scintillation eye tracker. The method can be performed by a light spot determination device. This method is used in a scintillation eye tracker that includes at least two light sources that are alternately illuminated to illuminate the eye.

[0043] Among them, the flicker type eye tracker includes a multi-dark pupil flicker type eye tracker and a bright dark pupil flicker type eye tracker. For the multi-dark pupil flicker type eye tracker, each time the camera captures an image, the light source formed by a specific light source on the pupil cornea is visible and alternately changes, and all light sources are non-coaxial (coaxial with the camera) light sources, so the images generated are all dark pupil images. For the bright dark pupil flicker type eye tracker, each time the camera captures an image, the light source formed by a specific light source on the pupil cornea is visible and alternately changes, and there is a light source that is a coaxial (coaxial with the camera) light source, so the image generated is a bright dark pupil image. For the flicker type eye tracker, each time the camera captures an image, only one light source is lit, that is, the pupil information and light spot information corresponding to the lit light source can be directly obtained based on the currently captured image. When tracking eye movements, eye tracking needs to be performed based on at least two light spot information, so it is necessary to determine the light spot information of other unlit light sources.

[0044] like Figure 1 As shown, the light spot determination method of this embodiment specifically includes the following steps:

[0045] Step 110 : determining the data variation curve and anchoring deviation of each light source based on the historical characteristic data cached by each light source.

[0046] The feature data includes pupil information and light spot information. Pupil information can be the location of the pupil center, and light spot information can be the location of the light spot center. The data change curve is used to represent the correspondence between timestamps and feature data. Historical feature data can be obtained by collecting images of each light source when illuminating the eye. Pupil information and light spot information can be extracted from eye images using any existing method and will not be further described here.

[0047] The historical feature data may include real feature data and predicted feature data. Real feature data can be understood as feature data directly acquired based on an image formed by a light source illuminating the eye, while predicted feature data can be understood as data inferred from the real feature data. In this embodiment, the data change curve includes a pupil change curve and a spot change curve, and the anchoring deviation is the anchoring deviation of the pupil information. This embodiment determines the data change curve and anchoring deviation for each light source based on the real feature data.

[0048] Specifically, the method of determining the data change curve of each light source based on the historical feature data cached by each light source can be: for each light source, extract the first set number of real feature data closest to the current moment; perform straight line or curve fitting on the set number of real feature data to obtain the data transformation curve of the light source.

[0049] In this embodiment, performing a straight line or curve fitting on a set amount of real feature data can be understood as fitting the uniform or variable speed pupil motion. If the pupil moves at a uniform speed, the fitted result is a straight line, and if the pupil moves at a variable speed, the fitted result is a curve.

[0050] The first set number can be any value between 3 and 6 frames. In this embodiment, the actual pupil information of the 3-6 frames closest to the current moment is extracted and fitted with a straight line or curve to obtain a pupil change curve; the actual spot information of the 3-6 frames closest to the current moment is extracted and fitted with a straight line or curve to obtain a spot change curve. The human eye consists of a left eye and a right eye, and the characteristic data of the left eye and the right eye need to be fitted separately to obtain the left eye pupil change curve, the right eye pupil change curve, and the left eye spot change curve and the right eye spot change curve.

[0051] Specifically, the anchoring deviation of each light source can be determined based on the historical feature data cached by each light source: for each light source, the average pupil information of a set number of real pupil information is calculated; one of the light sources is set as the standard light source, and the deviation between the average pupil information of each light source and the average pupil information of the standard light source is calculated, and the deviation is used to determine the anchoring deviation of each light source.

[0052] The human eye includes a left eye and a right eye, so the anchoring bias includes a left eye anchoring bias and a right eye anchoring bias. The standard light source can be any light source selected.

[0053] Step 120: Obtain first pupil information and first light spot information corresponding to the currently lit light source.

[0054] Specifically, at the current moment, a light source is illuminated to illuminate the eye, and the camera captures an image of the eye illuminated by the light source. The captured eye image is analyzed and processed to obtain first pupil information and first light spot information corresponding to the illuminated light source. The first pupil information can be information about the center position of the pupil, and the first light spot information can be information about the center position of the light spot.

[0055] Step 130 : Correct the first pupil information according to the anchoring deviation of the light source to obtain target pupil information.

[0056] Specifically, the anchoring deviation is accumulated with the first pupil information to obtain the target pupil information.

[0057] In this embodiment, the first pupil information is corrected according to the anchoring deviation of the lighting light source, and the target pupil information is obtained in the following manner: if the lighting light source is a standard light source, the first pupil information is determined as the target pupil information; if the lighting light source is a non-standard light source, the first pupil information is added to the anchoring deviation of the non-standard light source to obtain the target pupil information.

[0058] When the light source is a standard light source, the anchoring deviation is 0, and therefore the first pupil information can be directly determined as the target pupil information.

[0059] Step 140 : For the unlit light sources, determine the target light spot information of each unlit light source according to the current timestamp and the data change curve.

[0060] In this embodiment, the correspondence between the standard timestamp of the spot change curve and the spot information in the data change curve is as follows: Therefore, the target spot information of each unlit light source can be determined based on the current timestamp and the data change curve: the spot information corresponding to the current timestamp is searched in the data change curve to determine the target spot information of the unlit light source.

[0061] Specifically, for each unlit light source, the light spot change curve corresponding to each unlit light source is obtained, and the light spot information corresponding to the current timestamp is searched in the light spot change curve to determine the light spot information of each unlit light source. For a lit light source, the first light spot information can be directly determined as the target light spot information.

[0062] Optionally, before determining the data change curve and anchoring deviation of each light source based on the historical characteristic data cached by each light source, the following steps are also included: caching the characteristic data obtained when each light source is lit; and screening the cached characteristic data for abnormalities and deleting the abnormal data.

[0063] The feature data acquired when each light source is illuminated can be considered true feature data. Specifically, the cached feature data can be screened for abnormalities by determining as abnormal data any feature data whose pupil information differs from that of adjacent feature data by a value exceeding a set threshold; or by fitting eye movement trajectories based on the pupil information of the cached feature data, determining as abnormal data any feature data that deviates from the eye movement trajectory.

[0064] In this embodiment, feature data can also be screened for abnormalities based on the light spot information. Specifically, feature data where the difference between the light spot information and the adjacent feature data exceeds a set threshold is determined to be abnormal data; alternatively, feature data whose eye movement trajectory is fitted based on the cached feature data light spot information can be determined to be abnormal data if the feature data deviates from the movement trajectory. For the eye tracking device in this embodiment, the relative position between the pupil and the light spot should meet certain preset conditions. If the deviation from the preset conditions is too large, it can be confirmed that the data itself is abnormal. In addition, the movement of the human eye generally conforms to objective laws, so this abnormal data can be screened out based on the human eye movement mechanism.

[0065] Optionally, after deleting the abnormal data, the prediction feature data associated with the abnormal data also needs to be deleted.

[0066] The technical solution of this embodiment determines the data change curve and anchoring deviation of each light source based on the historical characteristic data cached by each light source; obtains the first pupil information and first light spot information corresponding to the light source that is currently lit; corrects the first pupil information based on the anchoring deviation of the lit light source to obtain the target pupil information; and for the unlit light sources, determines the target light spot information of each unlit light source based on the timestamp and data change curve at the current moment. The light spot determination method provided by this embodiment of the present invention corrects the first pupil information based on the anchoring deviation of the lit light source and determines the target light spot information of each unlit light source based on the timestamp and data change curve at the current moment. This can realize the determination of the light spot of the unlit light source in a flicker-type eye tracker, thereby improving the accuracy of eye tracking.

[0067] The following is a detailed explanation of the light spot determination method of this embodiment using a specific example:

[0068] Taking a set of real left eye data with bright and dark pupils as an example, assuming that the eye tracker is equipped with three light sources, three buffers need to be set, as shown in Tables 1-3:

[0069] Table 1

[0070]

[0071]

[0072] Table 2

[0073] signal light Pupil x pupil Glint x Glint y Confidence Frame rate 2 2

[0074] Table 3

[0075] signal light Pupil x pupil Glint x Glint y Confidence Frame rate 3 3

[0076] As the light sources are alternately lit, the characteristic data of each light source can be collected. Figure 2 This is the eye image when light 3 is on in this embodiment. Table 4 shows the characteristic data corresponding to light 3:

[0077] Table 4

[0078] signal light Pupil x pupil Glint x Glint y Confidence Frame rate 3 734.074 758.917 745.027 766.997 0.9607 1 3

[0079] Then wait for 2 to light up, Figure 3 This is the eye image when light 2 is on. Table 5 shows the feature data corresponding to light 2:

[0080] Table 5

[0081] signal light Pupil x Pupil Glint x Glint y Confidence Frame rate 2 735.239 758.829 729.846 767.168 0.9444 2 2

[0082] Then wait for 1 to light up, Figure 4This is the eye image when light 1 is on. Table 6 shows the feature data corresponding to light 1:

[0083] Table 6

[0084] signal light Pupil x Pupil Glint x Glint y Confidence Frame rate 1 736.331 759.742 737.657 766.884 0.9375 3 1

[0085] The three lights light up alternately in the flashing order 3->2->1->3->2->1.

[0086] Table 7 shows the two frames of feature data cached by lamp 3:

[0087] Table 7

[0088] signal light Pupil x pupil Glint x Glint y Confidence Frame rate 3 734.074 758.917 745.027 766.997 0.9607 1 3 734.329 758.497 745.225 766.509 0.9574 4

[0089] Table 8 shows the two frames of feature data cached by lamp 2:

[0090] Table 8

[0091] signal light Pupil x pupil Glint x Glint y Confidence Frame rate 2 735.239 758.829 729.846 767.168 0.9444 2 2 735.214 758.769 729.655 766.643 0.9595 5

[0092] Set Light 2 as the standard light source. The mean pupil position for Light 2 is (735.227, 758.799), and the mean pupil position for Light 3 is (734.202, 758.707). Calculate pupil deviation delta_p23 = (-1.025, -0.092).

[0093] Combined with the relationship between frame numbers, the time from data 1 to data 2 of light 3 is about 3 frame cycles, and the time from data 2 to the current moment is about 1 frame cycle. By uniformly inferring, we can get the data table 9 of light 3 at the current moment:

[0094] Table 9

[0095] signal light Pupil x Pupil Glint x Glint y Confidence Frame rate 3 734.074 758.917 745.027 766.997 0.9607 1 3 734.329 758.497 745.225 766.509 0.9574 4 3 734.414 758.357 745.291 766.346 0.9591 5

[0096] Combining the above pupil anchoring deviation and inferred data, the fused feature data output at frame number 5 is: pupil information (735.214, 758.769); light spot information: light 1 (temporarily unavailable), light 2 (729.655, 766.643), light 3 (745.291, 766.346), where the light spot information of light 3 is the result of data inference.

[0097] At the next moment, it is the turn of lamp 1 to light up, and two frames of feature data of lamp 1 are obtained:

[0098] Table 10

[0099] signal light Pupil x pupil Glint x Glint y Confidence Frame rate 1 736.331 759.742 737.657 766.884 0.9375 3 1 736.002 759.708 737.223 766.788 0.9639 6

[0100] Calculate the anchor deviation for the data for Light 1 and Light 2: The mean pupil position for Light 1 is (736.167, 759.725), and the mean pupil position for Light 2 is (735.227, 758.799). You can see that there is a significant deviation between Lights 1 and 2 in both the x and y directions. Calculate the pupil deviation delta_p21 = (0.94, 0.926).

[0101] At this point, the characteristic data of lamps 2 and 3 can be calculated at a uniform speed: Table 11 shows the cache data corresponding to lamp 3, and Table 12 shows the cache data corresponding to lamp 2:

[0102] Table 11

[0103]

[0104]

[0105] Table 12

[0106] signal light Pupil x pupil Glint x Glint y Confidence Frame rate 2 735.239 758.829 729.846 767.168 0.9444 2 2 735.214 758.769 729.655 766.643 0.9595 5 2 735.206 758.749 729.591 766.468 0.9520 6

[0107] According to the actual pupil information of the current light 1 (736.002, 759.708) and delta_p21 (0.94, 0.926), the target pupil information is calculated as (735.062, 758.782).

[0108] In summary, the final feature data at the moment of frame number 6 is:

[0109] Pupil information (735.062, 758.782); light spot information: light 1 (737.223, 766.788), light 2 (729.591, 766.468), light 3 (745.357, 766.183).

[0110] The pupil information is the pupil information of lamp 1 and the target pupil information is calculated by pupil deviation. The spot data of lamps 2 and 3 are both obtained by inference.

[0111] Example 2

[0112] Figure 5 : This is a schematic diagram of the structure of a light spot determination device provided in Example 2 of the present invention. The device is provided in a scintillation eye tracker, which includes at least two light sources, and the at least two light sources are alternately illuminated to illuminate the eye. As shown, the device includes:

[0113] The data change curve and anchoring deviation determination module 210 is used to determine the data change curve and anchoring deviation of each light source based on the historical characteristic data cached by each light source; the characteristic data includes pupil information and light spot information;

[0114] The first feature data acquisition module 220 is used to obtain the first pupil information and the first light spot information corresponding to the light source at the current moment;

[0115] a target pupil information acquisition module 230, configured to correct the first pupil information according to the anchoring deviation of the illuminated light source to obtain target pupil information;

[0116] The target light spot information determination module 240 is configured to determine the target light spot information of each unlit light source according to the current timestamp and the data change curve.

[0117] Optionally, the historical feature data includes real feature data and predicted feature data, and the data change curve and anchoring deviation determination module 210 is further used to:

[0118] For each light source, extract a first set number of real feature data closest to the current moment;

[0119] A straight line or curve fitting is performed on the set number of real characteristic data to obtain a data transformation curve of the light source; the transformation curve is used to represent the corresponding relationship between the timestamp and the characteristic data.

[0120] Optionally, the target light spot information determination module 240 is further configured to:

[0121] The light spot information corresponding to the timestamp at the current moment is searched in the data change curve to determine the target light spot information of the unlit light source.

[0122] Optionally, the real feature data includes real pupil information; the data change curve and anchoring deviation determination module 210 is further used to:

[0123] For each light source, calculating average pupil information of a second set amount of real pupil information;

[0124] One of the light sources is set as a standard light source, and the deviation between the average pupil information of each light source and the average pupil information of the standard light source is calculated, and the deviation is used to determine the anchor deviation of each light source.

[0125] Optionally, the target pupil information acquisition module 230 is further configured to:

[0126] If the light source is a standard light source, determining the first pupil information as target pupil information;

[0127] If the illuminated light source is a non-standard light source, the first pupil information and the anchoring deviation of the non-standard light source are accumulated to obtain target pupil information.

[0128] Optionally, it further includes: a feature data cache module for:

[0129] Cache the characteristic data obtained when each light source is turned on;

[0130] The cached feature data is screened for anomalies and the abnormal data is deleted.

[0131] Optionally, the feature data cache module is also used to:

[0132] Determine feature data whose pupil information has a difference with adjacent feature data exceeding a set threshold as abnormal data; or

[0133] The eye movement trajectory is fitted according to pupil information of the cached feature data, and feature data that deviates from the movement trajectory is determined as abnormal data.

[0134] The above device can execute the methods provided by all the above embodiments of the present invention, and has the corresponding functional modules and beneficial effects of executing the above methods. For technical details not fully described in this embodiment, please refer to the methods provided by all the above embodiments of the present invention.

[0135] Example 3

[0136] Figure 6 A schematic diagram of the structure of a computer device provided in Example 3 of the present invention. Figure 6 A block diagram of a computer device 312 suitable for implementing embodiments of the present invention is shown. Figure 6 The computer device 312 shown is only an example and should not limit the functionality and scope of use of the embodiments of the present invention. The device 312 is a typical computing device for light spot determination.

[0137] like Figure 6 As shown, computer device 312 is implemented as a general-purpose computing device. Components of computer device 312 may include, but are not limited to, one or more processors 316, storage device 328, and a bus 318 that connects various system components (including storage device 328 and processor 316).

[0138] Bus 318 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0139] The computer device 312 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 312, including volatile and non-volatile media, removable and non-removable media.

[0140] The storage device 328 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 330 and / or cache memory 332. The computer device 312 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 334 may be used to read and write non-removable, non-volatile magnetic media ( Figure 6 Not shown, often called a "hard drive"). Although Figure 6 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a floppy disk) and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a Compact Disc-Read Only Memory (CD-ROM), a Digital Video Disc-Read Only Memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 318 via one or more data media interfaces. Storage device 328 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present invention.

[0141] A program 336 having a set (at least one) of program modules 326 may be stored, for example, in a storage device 328. Such program modules 326 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 326 generally implement the functions and / or methods of the embodiments described herein.

[0142] The computer device 312 may also communicate with one or more external devices 314 (e.g., a keyboard, a pointing device, a camera, a display 324, etc.), one or more devices that enable a user to interact with the computer device 312, and / or any device that enables the computer device 312 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 322. Furthermore, the computer device 312 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 320. As shown, the network adapter 320 communicates with the other modules of the computer device 312 via a bus 318. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in conjunction with the computer device 312, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, disk arrays (Redundant Arrays of Independent Disks, RAID) systems, tape drives, and data backup storage systems.

[0143] The processor 316 executes various functional applications and data processing by running the programs stored in the storage device 328 , such as implementing the light spot determination method provided in the above embodiment of the present invention.

[0144] Example 4

[0145] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processing device, the method for determining a light spot in the embodiment of the present invention is implemented. The computer-readable medium of the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal transmitted in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0146] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0147] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0148] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: determines the data change curve and anchoring deviation of each light source based on the historical characteristic data cached by each light source; the characteristic data includes pupil information and light spot information; obtains the first pupil information and first light spot information corresponding to the light source that is lit at the current moment; corrects the first pupil information according to the anchoring deviation of the lit light source to obtain target pupil information; for unlit light sources, determines the target light spot information of each unlit light source based on the timestamp of the current moment and the data change curve.

[0149] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0150] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0151] The units involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a unit does not necessarily limit the unit itself.

[0152] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0153] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0154] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the concept of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for determining a light spot, characterized in that: The method is used in a scintillation eye tracker, which includes at least two light sources, and the at least two light sources are alternately lit to illuminate the eyes; comprising: Determine the data change curve and anchoring deviation of each light source based on the historical feature data cached by each light source; the feature data includes pupil information and light spot information; Obtaining the first pupil information and the first light spot information corresponding to the light source currently lit; Correcting the first pupil information according to the anchoring deviation of the illuminated light source to obtain target pupil information; For unlit light sources, determining target light spot information of each unlit light source according to the current timestamp and the data change curve; Wherein, the historical feature data includes real feature data and predicted feature data, and the real feature data includes real pupil information; The anchoring bias of each light source is determined based on the historical feature data cached by each light source, including: For each light source, calculating average pupil information of a second set amount of real pupil information; One of the light sources is set as a standard light source, and the deviation between the average pupil information of each light source and the average pupil information of the standard light source is calculated, and the deviation is determined as the anchor deviation of each light source.

2. The method according to claim 1, characterized in that The data change curve of each light source is determined based on the historical characteristic data cached by each light source, including: For each light source, extract a first set number of real feature data closest to the current moment; A straight line or curve fitting is performed on the first set number of real feature data to obtain a data transformation curve of the light source; the transformation curve is used to represent the corresponding relationship between the timestamp and the feature data.

3. The method according to claim 2, characterized in that Determining target light spot information of each unlit light source according to the current timestamp and the data change curve includes: The light spot information corresponding to the timestamp at the current moment is searched in the data change curve to determine the target light spot information of the unlit light source.

4. The method according to claim 1, wherein Correcting the first pupil information according to the anchoring deviation of the illuminated light source to obtain target pupil information includes: If the light source is a standard light source, determining the first pupil information as target pupil information; If the illuminated light source is a non-standard light source, the first pupil information and the anchoring deviation of the non-standard light source are accumulated to obtain target pupil information.

5. The method according to claim 1, wherein Before determining the data change curve and anchoring deviation of each light source based on the historical characteristic data cached by each light source, the following steps are also included: Cache the characteristic data obtained when each light source is turned on; The cached feature data is screened for anomalies and the abnormal data is deleted.

6. The method according to claim 5, characterized in that The cached feature data is screened for anomalies, including: Determine feature data whose pupil information has a difference with adjacent feature data exceeding a set threshold as abnormal data; or The eye movement trajectory is fitted according to pupil information of the cached feature data, and feature data that deviates from the movement trajectory is determined as abnormal data.

7. A light spot determination device, characterized in that: The device is provided in a scintillation eye tracker, wherein the scintillation eye tracker comprises at least two light sources, and the at least two light sources are alternately lit to illuminate the eyes; and comprises: A data change curve and anchoring deviation determination module is used to determine the data change curve and anchoring deviation of each light source based on the historical characteristic data cached by each light source; the characteristic data includes pupil information and light spot information; A first feature data acquisition module is used to obtain first pupil information and first light spot information corresponding to the light source that is currently lit; a target pupil information acquisition module, configured to correct the first pupil information according to the anchoring deviation of the illuminated light source to obtain target pupil information; a target light spot information determination module, configured to determine, for each unlit light source, target light spot information of the unlit light source according to a current timestamp and the data change curve; Wherein, the historical feature data includes real feature data and predicted feature data, and the real feature data includes real pupil information; The data change curve and anchoring deviation determination module is specifically used to: For each light source, calculating average pupil information of a second set amount of real pupil information; One of the light sources is set as a standard light source, and the deviation between the average pupil information of each light source and the average pupil information of the standard light source is calculated, and the deviation is determined as the anchor deviation of each light source.

8. A computer device, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the light spot determination method according to any one of claims 1 to 6 when executing the program.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processing device, the light spot determination method according to any one of claims 1 to 6 is implemented.

Images