The present disclosure relates to gaze tracking, such as determining a direction in which a user's gaze is directed.
Determining what a user looks at is of interest in a number of different fields. For example, a disabled person may be equipped with a gaze tracker enabling her to input characters to form words and sentences. As another example, an ambulance driver may be enabled to safely operate equipment of his ambulance, or a nuclear power station operator may have his gaze tracked to detect episodes of fatigue during a shift.
Eye-tracking solutions on and for ocular devices such as microscopes, eye-glasses, wearable displays, binoculars, and viewfinders may depend on prior knowledge of a constant geometrical relationship between an eye-tracking sensor and an illumination of the eye. In some advanced 3-D based gaze point computation methods the mutual geometrical relationship is required to be known for the method to work. In such methods, the relationship between the illumination and the detector comprising sensors should not be changed during the operation, for example, by moving, shifting, rotating, or otherwise spatially or geometrically manipulating the detector and/or the illumination device of the gaze tracking apparatus.
According to some aspects, there is provided the subject-matter of the independent claims. Some embodiments are defined in the dependent claims.
According to a first aspect of the present disclosure, there is provided an eye tracking apparatus comprising an illumination device comprising at least one light source, configured to illuminate a user's eye when the user is using the eye tracking apparatus, at least one detector configured to obtain information on the user's eye when the user is using the eye tracking apparatus, and at least one processing core configured to determine a direction of the user's gaze based on the information on the user's eye and based on an indication of place and/or orientation of the illumination device with respect to the at least one detector.
According to a second aspect of the present disclosure, there is provided a method comprising illuminating, using an illumination device of an eye tracker apparatus, a user's eye when the user is using the eye tracking apparatus, the illumination device comprising at least one light source, obtaining, using at least one detector, information on the user's eye when the user is using the eye tracking apparatus, and determining a direction of the user's gaze based on the information on the user's eye and based on an indication of place and/or orientation of the illumination device with respect to the at least one detector.
According to a third aspect of the present disclosure, there is provided an apparatus comprising means for illuminating, using an illumination device of an eye tracker apparatus, a user's eye when the user is using the eye tracking apparatus, the illumination device comprising at least one light source, obtaining, using at least one detector, information on the user's eye when the user is using the eye tracking apparatus, and determining a direction of the user's gaze based on the information on the user's eye and based on an indication of place and/or orientation of the illumination device with respect to the at least one detector.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable medium having stored thereon a set of computer readable instructions that, when executed by at least one processor, cause an apparatus to at least illuminate, using an illumination device of an eye tracker apparatus, a user's eye when the user is using the eye tracking apparatus, the illumination device comprising at least one light source, obtain, using at least one detector, information on the user's eye when the user is using the eye tracking apparatus, and determine a direction of the user's gaze based on the information on the user's eye and based on an indication of place and/or orientation of the illumination device with respect to the at least one detector.
According to a fifth aspect of the present disclosure, there is provided a computer program configured to cause a method in accordance with the second aspect to be performed.
In geometry, the orientation, angular position, attitude, or direction of an object such as a line, plane or rigid body is part of the description of how it is placed in the space it occupies. More specifically, it refers to an imaginary rotation that is needed to move the object from a reference placement to its current placement. A rotation may not be enough to reach the current placement. It may be necessary to add an imaginary translation, called the object's location, or place, or linear position, to the rotation. The place and orientation together fully describe how the object is placed in space. In detail, the place and orientation together may be referred to in brief as a geometrical relationship, such as between an eye-tracking sensor and the illumination device of the eye tracker apparatus.
In head-mounted versions of eye tracking the physical location of light sources illuminating the eye is typically fixed in the frame of the eye tracking apparatus, which rests on the user's head. In remote eye-tracking arrangements the same applies, as the light sources and sensor(s) are lodged into a non-movable frame and do not change their physical location nor geometrical relationship with regards to each other. However, in near-to-the eye gaze tracking applications, such as viewfinders and other ocular devices, the ocular device may need to be rotated, extended, bent or otherwise manipulated, which may result in changes to the geometrical relationship between the eye-tracking detector and the illumination device arranged to project light on the eye.
Based on methods disclosed herein, changes in the geometrical relationship between a detector comprising at least one eye-tracking sensor and the illumination device is detected and accounted for. A benefit is obtained in enhanced gaze tracking accuracy, as the geometrical changes do not to the same extent produce errors in gaze tracking results.
Tracking the gaze of a user of a microscope gives valuable information concerning how the user observes the sample under study, for example which parts of the sample the user focuses on, for how long the user remains focused on each part of the sample and what kind of gaze strategy the user uses. Gaze information may also be used in controlling the functioning of an optical device, such as a microscope, for example. Thus the need for manual control may be reduced, freeing the user from operating another set of controls or manipulating other devices.
In addition, the pupil size may be estimated. This information may be used to estimate the pupillary response, the user's awareness, the user's workload and his level of expertise, in educational purposes, and in assisting annotation of image areas, for example. The relative pupil size may be inferred in image units, pixels, using the eye image alone, or in real-world units, for example square millimetres, by using the image of the eye and/or information provided by glints on the corneal surface, for example. Other features of the eyes, such as iris, iris colour and pattern, eyelids, eyelids characteristics, blink and blinks characteristics may also be estimated, for the purposes including, but not limited to, eye tracking, user state monitoring, and user identification. Glints 112 are illustrated in
A pathologist or laboratory worker may also use his gaze point on a sample plate to guide the microscope to move the sample. As a further example, a digital viewfinder may provide a visual indication when the user is looking at a target which may be a human, for example when the ocular device in question is binoculars. Further, a sample may be automatically associated, based on the gaze point identification, with metadata indicating an extent to which it has been analysed, for example, whether a threshold has been reached.
In the system of
Likewise in the system of
In gaze tracking in general, a transformation may be determined from a coordinate system of a detector to a coordinate system of the scene of a scene camera. The transformation may be initialized using a calibration procedure which produces calibration information. The detector may be assisted by the light sources to generate glints 112 and illuminate the eye, as described above, to enable determining a direction where the eye is turned toward. In an ocular device, the presence of optical equipment 130 may make it more difficult to accurately project a gaze point into a scene camera's coordinates. Further, if the geometrical relationship between the detector and the illumination device of the gaze tracking apparatus changes, the calibration information may need updating, or the gaze tracking may need to apply corrective measures to account for the change in the geometrical relationship. A change in the geometrical relationship may comprise a rotation of the detector and/or of the illumination device, and/or a translation, that is, a physical movement to another location, of the detector and/or of the illumination device.
In general, a gaze tracking apparatus may process an indication of place and/or orientation of the illumination device with respect to the detector. The apparatus may derive the indication in a processing core, and/or receive the indication from an illumination device. In some embodiments, the illumination device is comprised in the gaze tracking apparatus while in other embodiments the illumination device is not comprised in the gaze tracking apparatus. Processing the indication may comprise updating calibration information to account for the movement and/or rotation of the illumination device with respect to the detector. In some embodiments, the illumination device is configured to communicate the indication to the detector as information encoded on a light signal, for example amplitude modulated, such that the detector may receive the indication from observing how one or more glints on the user's eye develops over time.
An illumination device may be configured to derive the indication based on data obtained from the at least one of a position-detecting sensor, an acceleration sensor and a rotation-detecting sensor comprised in the illumination device. A rotation-detecting sensor may comprise an accelerometer and/or a gyroscope, such as a microelectromechanical MEMS circuit providing these functions, for example. The position-detecting sensor may comprise an electromagnetic multilateration device or an electromagnetic triangulation device, which may be configured to act responsive to electromagnetic beacon transmissions, for example electromagnetic beacons transmitted by other part(s) of the gaze tracking apparatus. The illumination device may determine it has rotated and/or moved based on outputs of these sensor(s), and the illumination device may provide an indication that describes this change in the geometrical relationship between the illumination device and the detector.
The indication of place and/or orientation of the illumination device with respect to the detector may be derived by identifying one from among plural light sources of the illumination device. Such identifying may be based on at least one physical characteristic of the light source, for example. More precisely, the indication may relate to the place and/or orientation of light sources comprised in the illumination device to the detector. Thus, glints reflected from the eye are detected in an image obtained by the detector of the eye, and then having knowledge of the physical location of the light sources of the illumination device, the problem of locating the eye (corneal sphere) and then the pupil may be solved.
The at least one physical characteristic of the at least one identified light source may comprise at least one of the following: a size of the light source, a shape of the light source, a spectrum feature of light emitted by the light source, a feature of temporal variance of light output by the light source and a feature of polarization of light output by the light source.
Where the physical characteristic comprises the size of the light source, a light source with a size different from the other light sources may define a direction of an axis, such as axis 223 of
Where the physical characteristic comprises a shape of the light source, a light source with a shape differing from shapes of other light sources may define a direction of an axis, such as axis 223 of
Where the physical characteristic comprises a spectrum feature of light emitted by the light source, the identified light source is configured to emit light with a different spectral characteristic from the other light sources, or light with a predetermined spectral characteristic. For example, the centre frequency may be offset from that of the other light sources, enabling the identification of this light source. The offset needs to be large enough to be detectable, wherefore all the light sources may be in the infra-red range, for example, with one of them merely in a slightly different point of the infra-red range. The same applies when the physical characteristic is a feature of polarization, in which case one of the light sources may emit light polarized in a different way from the other light sources, or polarized in a predetermined way. For example, one of the light sources may emit light which is not polarized whereas the others emit polarized light. Alternatively, one of the light sources may emit light polarized in a direction rotated with respect to the polarization of light emitted by the other light sources. When a predetermined spectrum feature or feature of polarization is used, all the light sources may emit light of different spectra or polarization, the axis being determined by identifying one of the light sources as having the predetermined spectrum feature or the predetermined feature of polarization.
Where the physical characteristic comprises a feature of temporal variance of light output by the light source, the identified light may be configured to vary its intensity as a function of time while other light sources maintain a constant- or a predefined pattern of intensity. Alternatively, at least one of the light sources may be configured to change the direction of its light beam as a function of time, while the others remain static. Alternatively, one of the light sources may in general be configured to vary or to modulate its light output in a predetermined manner.
In some embodiments, a physical characteristic of a light source is used together with a movement and/or rotation sensor of the illumination device, to obtain a higher accuracy for the indication. In these cases, the indication may be derived separately based on the physical characteristic of the light source and on the sensor of the illumination device, and then an average may be obtained for the rotation and/or movement indicated by these indications. The averaged rotation and/or movement may then be used to adjust the calibration information.
In some embodiments, the light source may take the shape of a single larger structural entity such as a continuous ring or other shape such as a square, triangle, etc. or a continuous larger surface of light such as a filled circle, square or triangle with equal or patterned illumination across its surface. This adds the benefit of detecting and extrapolating continuous surface reflections on top of the eye, with distinguishable features such as corners or the minimum/maximum extent of the shape in different directions for matching with physical features of the source of illumination. Such continuous features may be more robustly detected in circumstances where single point light sources or multiple sources even with the methods mentioned above may be challenging to track or identify.
On the other hand on the right is illumination device 220, which comprises eight light sources 222. Light sources 222 are arranged on illumination device 220 such that distances between light sources 222 vary. In detail, a closed path may be traversed along the illumination device, the light sources along the closed path, the distances between consecutive light sources along the closed path not all being equal. This enables determining whether the illumination device has rotated, as the denser arrangement of light sources 222 uniquely defines an axis 223, which may be determined visually based on glints from the light sources. In case axis 223 points in a different direction than before, illumination device 220 has been rotated.
An arrangement such as in illumination device 200 has been favoured in the past as it produces a uniform, smooth illumination of the eye. The arrangement of illumination device 220 also illuminates all aspects of the eye, additionally enabling determination of rotation based on axis 223.
It should be noted, that whereas
In some embodiments, an intermediate board with physical connectors is employed to maintain active light sources of a preselected pattern, such that rotation of the illumination device has no, or little, effect on the illumination pattern produced by the illumination device. Thus illumination device position need not be detected, since the illumination device itself maintains its output at a more or less constant pattern.
Device 400 may comprise memory 420. Memory 420 may comprise random-access memory and/or permanent memory. Memory 420 may comprise at least one RAM chip. Memory 420 may comprise solid-state, magnetic, optical and/or holographic memory, for example. Memory 420 may be at least in part accessible to processor 410. Memory 420 may be at least in part comprised in processor 410. Memory 420 may be a means for storing information. Memory 420 may comprise computer instructions that processor 410 is configured to execute. When computer instructions configured to cause processor 410 to perform certain actions are stored in memory 420, and device 400 overall is configured to run under the direction of processor 410 using computer instructions from memory 420, processor 410 and/or its at least one processing core may be considered to be configured to perform said certain actions. Memory 420 may be at least in part comprised in processor 410. Memory 420 may be at least in part external to device 400 but accessible to device 400.
Device 400 may comprise a transmitter 430. Device 400 may comprise a receiver 440. Transmitter 430 and receiver 440 may be configured to transmit and receive, respectively, information in accordance with a predetermined protocol.
Device 400 may comprise user interface, UI, 460. UI 460 may comprise at least one of a display, a keyboard, a touchscreen, a vibrator arranged to signal to a user by causing device 400 to vibrate, a speaker and a microphone. A user may be able to operate device 400 via UI 460, for example to inspect samples on a microscope.
Processor 410 may be furnished with a transmitter arranged to output information from processor 410, via electrical leads internal to device 400, to other devices comprised in device 400. Such a transmitter may comprise a serial bus transmitter arranged to, for example, output information via at least one electrical lead to memory 420 for storage therein. Alternatively to a serial bus, the transmitter may comprise a parallel bus transmitter. Likewise processor 410 may comprise a receiver arranged to receive information in processor 410, via electrical leads internal to device 400, from other devices comprised in device 400. Such a receiver may comprise a serial bus receiver arranged to, for example, receive information via at least one electrical lead from receiver 440 for processing in processor 410. Alternatively to a serial bus, the receiver may comprise a parallel bus receiver.
Device 400 may comprise further devices not illustrated in
Processor 410, memory 420, transmitter 430, receiver 440, and/or UI 460 may be interconnected by electrical leads internal to device 400 in a multitude of different ways. For example, each of the aforementioned devices may be separately connected to a master bus internal to device 400, to allow for the devices to exchange information. However, as the skilled person will appreciate, this is only one example and depending on the embodiment various ways of interconnecting at least two of the aforementioned devices may be selected without departing from the scope of the present invention.
Phase 510 comprises illuminating, using an illumination device of an eye tracker apparatus, a user's eye when the user is using an eye tracking apparatus, the illumination device comprising at least one light source. Phase 520 comprises obtaining, using a detector, a information on the user's eye when the user is using the eye tracking apparatus. Finally, phase 530 comprises determining a direction of the user's gaze based on the information on the user's eye and based on an indication of place and/or orientation of the illumination device with respect to the detector of the eye tracker apparatus. The information on the user's eye may comprise an image of the user's eye. The indication of place and/or orientation of the illumination device with respect to the detector of the eye tracker apparatus may indicate a change in the place and/or orientation of the illumination device with respect to an original orientation, for example. The determining of the direction of the user's gaze may comprise reading the current geometry and referencing a pre-calculated table of shapes and/or solving equations concerning shape in real time.
It is to be understood that the embodiments of the invention disclosed are not limited to the particular structures, process steps, or materials disclosed herein, but are extended to equivalents thereof as would be recognized by those ordinarily skilled in the relevant arts. It should also be understood that terminology employed herein is used for the purpose of describing particular embodiments only and is not intended to be limiting.
Reference throughout this specification to one embodiment or an embodiment means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, appearances of the phrases “in one embodiment” or “in an embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment. Where reference is made to a numerical value using a term such as, for example, about or substantially, the exact numerical value is also disclosed.
As used herein, a plurality of items, structural elements, compositional elements, and/or materials may be presented in a common list for convenience. However, these lists should be construed as though each member of the list is individually identified as a separate and unique member. Thus, no individual member of such list should be construed as a de facto equivalent of any other member of the same list solely based on their presentation in a common group without indications to the contrary. In addition, various embodiments and example of the present invention may be referred to herein along with alternatives for the various components thereof. It is understood that such embodiments, examples, and alternatives are not to be construed as de facto equivalents of one another, but are to be considered as separate and autonomous representations of the present invention.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the preceding description, numerous specific details are provided, such as examples of lengths, widths, shapes, etc., to provide a thorough understanding of embodiments of the invention. One skilled in the relevant art will recognize, however, that the invention can be practiced without one or more of the specific details, or with other methods, components, materials, etc. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring aspects of the invention.
While the forgoing examples are illustrative of the principles of the present invention in one or more particular applications, it will be apparent to those of ordinary skill in the art that numerous modifications in form, usage and details of implementation can be made without the exercise of inventive faculty, and without departing from the principles and concepts of the invention. Accordingly, it is not intended that the invention be limited, except as by the claims set forth below.
The verbs “to comprise” and “to include” are used in this document as open limitations that neither exclude nor require the existence of also un-recited features. The features recited in depending claims are mutually freely combinable unless otherwise explicitly stated. Furthermore, it is to be understood that the use of “a” or “an”, that is, a singular form, throughout this document does not exclude a plurality.
At least some embodiments of the present invention find industrial application in gaze tracking applications, for example with ocular devices.
Number | Date | Country | Kind |
---|---|---|---|
20215098 | Jan 2021 | FI | national |
Filing Document | Filing Date | Country | Kind |
---|---|---|---|
PCT/FI2022/050053 | 1/27/2022 | WO |