Apparatus and method of using events for user interface

1. An apparatus for processing event data, the apparatus comprising:

at least one event-based vision sensor configured to detect an event corresponding to a change of light by a movement of an object and to generate the event data associated with the change of light; and

one or more processors configured to:

determine a class, from among at least two classes, having a representative value most similar to the event data, based on respective similarities being calculated between the event data and corresponding representative values for each of the at least two classes;

classify the event as corresponding to the class among the at least two classes, based on a result of the determining of the class having the representative value most similar to the event data;

update class information related to the class corresponding to the event; and

determine a user input corresponding to the event based on the updated class information.

2. The apparatus of claim 1 , wherein the representative values are coordinates or position-related information regarding each of the at least two classes.

3. The apparatus of claim 1 , wherein, to classify the event, the one or more processors are configured to:

compare an event value corresponding to the event to the representative values; and

detect a class, from among the at least two classes, having a representative value most similar to the event value.

4. The apparatus of claim 1 , wherein the updated class information comprises a representative value representing the class of the classified event.

5. The apparatus of claim 1 , wherein the at least two classes correspond to at least two objects associated with the user input.

6. The apparatus of claim 1 , wherein, to determine the user input, the one or more processors are configured to:

calculate optical flows corresponding to the at least two classes; and

calculate velocity components corresponding to the at least two classes based on the calculated optical flows.

7. The apparatus of claim 6 , wherein the velocity components comprise at least one of:

a first velocity component at which an object generating the event moves in an x-axial direction on a virtual plane used to detect the event;

a second velocity component at which the object moves in a y-axial direction on the virtual plane;

a third velocity component at which the object moves in a direction orthogonal to the virtual plane; and

a fourth velocity component at which the object rotates on the virtual plane.

8. The apparatus of claim 6 , wherein, to determine the user input, the one or more processors are configured to:

recognize the user input by analyzing the velocity components based on a user input context.

9. The apparatus of claim 6 , wherein, to determine the user input, the one or more processors are configured to:

recognize the user input by analyzing a relative velocity between the class of the classified event and at least one remaining class based on the velocity components.

10. The apparatus of claim 1 , wherein, to determine the user input, the one or more processors are configured to:

recognize the user input by analyzing a representative value representing the class of the classified event and a representative value representing at least one remaining class based on a user input context.

11. The apparatus of claim 1 , wherein the one or more processors are configured to classify the event irrespective of other events.

12. The apparatus of claim 1 , wherein the event data is generated in an asynchronous manner.

13. The apparatus of claim 1 , wherein the event indicates a change occurrence in brightness with respect to a corresponding object.

14. The apparatus of claim 1 , wherein the classifying includes classifying events to a corresponding class based on respective classifiers of the classes, and

wherein the updating of the class information includes updating a classifier of the corresponding class after each event is classified in the classifying.

15. A method of operating a user interface for processing event data generated by at least one event-based vision sensor configured to detect events, the method comprising:

receiving the events corresponding to changes of light by movements of a plurality of objects;

determine a corresponding class, from among a plurality of classes that correspond to the plurality of objects, having a representative value most similar to each of the events, based on respective similarities being calculated between each event, of the events, and corresponding representative values for each of the plurality of classes;

classifying each of the events as the corresponding class, based on the determining of the corresponding class having the representative value most similar to each of the events;

updating class information relating to the one or more of the classes based on the events; and

determining a user input based on the updated class information.

16. The method of claim 15 , wherein the classifying comprises detecting, for each of the events, a class having a representative value most similar to a value of the corresponding event, among the plurality of classes.

17. The method of claim 15 , wherein the class information comprises at least one of pixels included in the classes, events included in the classes, and representative values of the classes stored in a memory.

18. The method of claim 15 , wherein the determining of the user input based on the updated class information further comprises:

calculating optical flows for the classes;

calculating velocity components of the classes based on the calculated optical flows; and

recognizing a command to process the user input based on the velocity components of the classes.

19. An apparatus for processing event data, the apparatus comprising:

at least one event-based vision sensor configured to detect an event corresponding to a change of light by a movement of an object and to generate the event data associated with the change of light; and

one or more processors configured to:

determine a class, from among at least two classes, having a representative value most similar to the event data, based on respective similarities being calculated between the event data and corresponding representative values for each of the at least two classes;

classify the event as corresponding to an object, among a plurality of objects, being associated with the class, based on a result of the determining of the class having a representative value most similar to the event data;

update representative values corresponding to at least one of the plurality of objects based on the classified event; and

determine a user input corresponding to the event based on the updated representative values.

20. The apparatus of claim 19 , wherein the representative values are coordinates or position-related information regarding each of the at least two classes, or to frequency, amplitude or intensity related information regarding each of the at least two classes.

21. The apparatus of claim 19 , wherein, to determine the user input, the one or more processors are configured to determine the user input by determining a direction of change regarding one or more of the plurality of objects based on the updated representative values.

22. An apparatus for processing event data, the apparatus comprising:

at least one event-based vision sensor configured to detect an event corresponding to a change of light by a movement of an object and to generate the event data associated with the change of light; and

one or more processors configured to:

calculate a first similarity between the event data and a first representative value, wherein the first representative value corresponds to a first group of events detected by the event-based vision sensor;

calculate a second similarity between the event data and a second representative value, wherein the second representative value corresponds to a second group of events detected by the event-based vision sensor;

compare the first similarity and the second similarity with each other;

classify the event as one of the first group of events and the second group of events, based on a result of the comparison; and

update the first representative value or the second representative value, based on the classified event.

23. The apparatus of claim 22 , wherein the event data includes a target coordinate of a target pixel, from among a plurality of pixels included in the event data, at which the event occurred,

wherein the first representative value is a first center coordinate of a first group of pixels, from among a plurality of pixels, which generate the first group of events, and

wherein the second representative value is a second center coordinate of a second group of pixels, from among a plurality of pixels, which generate the second group of events.

24. The apparatus of claim 23 , wherein the first similarity is a first distance between the target coordinate and the first center coordinate, and the second similarity is a second distance between the target coordinate and the second center coordinate.

25. The apparatus of claim 24 , wherein the one or more processor further configured to:

classify the event as the first group of events, when the second distance is greater than the first distance; and

classify the event as the second group of events, when the first distance is greater than the second distance.