Eye gesture tracking
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for eye gesture recognition. In one aspect, a method includes obtaining an electrical signal that represents a measurement, by a photodetector, of an optical signal reflected from an eye and determining a depth map of the eye based on phase differences between the electrical signal generated by the photodetector and a reference signal. Further, the method includes determining gaze information that represents a gaze of the eye based on the depth map and providing output data representing the gaze information.
1. A computer-implemented method, comprising:
obtaining an electrical signal including a first phase generated by one or more photodetectors from a modulated optical signal reflected from an eye, wherein the modulated optical signal is generated by one or more optical sources that are biased by a modulation signal including a second phase;
determining a depth map of the eye based on phase differences between the first phase of the electrical signal generated by the one or more photodetectors from the modulated optical signal reflected from the eye and a third phase of a reference signal in sync with the second phase of the modulation signal, wherein the depth map of the eye comprises a three-dimensional model representing the eye;
determining a gaze information that represents a gaze of the eye based on the depth map; and
providing output data representing the gaze information.
2. The computer-implemented method of claim 1 , further comprising:
providing one or more filters to the modulated optical signal reflected from the eye to remove non-target wavelength signals.
3. The computer-implemented method of claim 1 , further comprising:
providing one or more lenses to the modulated optical signal reflected from the eye to focus the modulated optical signal to the one or more photodetectors.
4. The computer-implemented method of claim 1 , wherein the depth map further comprises one or more data sets of three-dimensional information.
5. The computer-implemented method of claim 1 , wherein the gaze information includes one or more of an identification of a particular region of the eye, an identification of a pupil of the eye, an identification of an iris of the eye, or an identification of a physiological structure of the eye.
6. The computer-implemented method of claim 1 , wherein the providing of the output data representing the gaze information comprises providing the output data representing the gaze information as input data to another device, machine, or system.
7. The computer-implemented method of claim 1 , further comprising:
determining an eye gesture based on the gaze information; and
providing output data representing the eye gesture.
8. The computer-implemented method of claim 7 , wherein the eye gesture includes one or more of a movement of the eye, a rotation of the eye, a steady state of the eye, a duration of the steady state of the eye, a closed state of the eye, a duration of the closed state of the eye, an open state of the eye, a duration of the open state of the eye, a blinking state of the eye, a duration of the blinking state of the eye, or a frequency of the blinking state of the eye.
9. The computer-implemented method of claim 7 , wherein the providing of the output data representing the eye gesture comprises providing the output data representing the eye gesture as input data to another device, machine, or system.
10. The computer-implemented method of claim 1 , further comprising:
generating an iris vector normal to a plane that is tangential to the eye; and
determining the gaze information that represents the gaze of the eye based on the depth map and the iris vector.
11. The computer-implemented method of claim 1 , further comprising:
generating a pupil position of the eye on a plane that is tangential to the eye; and
determining the gaze information that represents the gaze of the eye based on the depth map and the pupil position.