Decoding the visual attention of an individual from electroencephalographic signals

1. A method for determining a focus of visual attention of an individual from electroencephalographic signals, the method comprising;

generating a set of at least one visual stimulus to be displayed based on at least one graphical object of a human-machine interface of a computational device, at least one elementary transformation, and a set of at least one modulation signal, a visual stimulus of the set of at least one visual stimulus being an animated graphical object obtained by applying to a graphical object a temporal succession of elementary transformations that is temporally parameterized by a corresponding modulation signal;

presenting the at least one visual stimulus in a display to the individual;

recording a plurality of electroencephalographic signals produced by the individual while the individual is paying attention to the displayed at least one visual stimulus; and

performing, in real-time, operations comprising:

reconstructing a modulation signal from the plurality of electroencephalographic signals produced by the individual in order to obtain a reconstructed modulation signal;

computing a degree of statistical dependence between the reconstructed modulation signal and each modulation signal of the set of at least one modulation signal;

in response to identifying at least one visual stimulus corresponding to a modulation signal for which the degree of statistical dependence is higher than a first threshold, triggering one or more operations of the computational device.

2. The method as claimed in claim 1 , wherein the set of at least one visual stimulus comprises a plurality of visual stimuli and the set of at least one modulation signal comprises a plurality of modulation signals, the method further comprising:

searching, among the plurality of modulation signals, for a modulation signal for which a degree of statistical dependence with the reconstructed modulation signal is maximal; and

identifying a visual stimulus corresponding to a modulation signal for which the degree of statistical dependence is maximal;

the plurality of modulation signals being composed so that an overall degree of statistical dependence, which is determined in a time and/or frequency domain, for all pairs of the plurality of modulation signals corresponding to two separate visual stimuli, is lower than a second threshold.

3. The method as claimed in claim 1 , wherein the reconstruction is carried out by applying a reconstruction model to the plurality of electroencephalographic signals.

4. The method as claimed in claim 3 ,

wherein the reconstruction model comprises a plurality of parameters of combinations of electroencephalographic signals, and

wherein the method further comprises determining values of parameters of the plurality of parameters of the combinations of electroencephalographic signals in an initial learning phase.

5. The method as claimed in claim 4 , wherein, in the initial learning phase applied to a subset of at least one visual stimulus among the plurality of visual stimuli, the method further comprises:

obtaining, for each visual stimulus of said subset of at least one visual stimulus, a respective electroencephalographic signal of a plurality test electroencephalographic signals produced by the individual focusing attention on the each visual stimulus; and

determining optimal values for the plurality of parameters of combinations of electroencephalographic signals, for which values the application of the reconstruction model to the plurality of test electroencephalographic signals recorded for a visual stimulus allows a reconstructed modulation signal to be generated that approximates as best as possible the modulation signal corresponding to the visual stimulus in question.

6. The method as claimed in claim 1 , wherein each modulation signal defines variations as a function of time in at least one parameter of application of an elementary transformation to a graphical object.

7. The method as claimed in claim 6 , wherein the at least one parameter of application is a degree of transformation or a rate of application of an elementary transformation.

8. The method as claimed in claim 1 , wherein an elementary transformation is a transformation of the set of transformations consisting of a variation in light intensity, a variation in contrast, a colorimetric transformation, a geometric deformation, a rotation, an oscillation, a movement along a path, a change in shape and a change in graphical object or a combination of transformations chosen from said set of transformations.

9. A system for determining a focus of visual attention of an individual from electroencephalographic signals, the system comprising;

a device for generating display signals, which is configured to:

generate a set of at least one visual stimulus to be displayed based on at least one graphical object of a human-machine interface of a computational device, at least one elementary transformation, and a set of at least one modulation signal, a visual stimulus of the set of at least one visual stimulus being an animated graphical object obtained by applying to a graphical object a temporal succession of elementary transformations that is temporally parameterized by a corresponding modulation signal; and

present the at least one visual stimulus in a display to the individual; and

a real-time signal-processing device configured to:

obtain a plurality of electroencephalographic signals produced by the individual while the individual is paying attention to the displayed at least one visual stimulus;

obtain a reconstructed modulation signal by reconstructing a modulation signal from the plurality of electroencephalographic signals;

compute a degree of statistical dependence between the reconstructed modulation signal and each modulation signal of said set of at least one modulation signal; and

in response to identifying at least one visual stimulus corresponding to a modulation signal for which the degree of statistical dependence is higher than a first threshold, trigger one or more operations of the computational device.

10. The system as claimed in claim 9 , wherein the set of at least one visual stimulus comprises a plurality of visual stimuli and the set of at least one modulation signal comprises; a plurality of modulation signals, the signal-processing device furthermore being configured to;

search, among the plurality of modulation signals, for a modulation signal for which the degree of statistical dependence with the reconstructed modulation signal is maximal;

identify the visual stimulus corresponding to the modulation signal for which the degree of statistical dependence is maximal;

the plurality of modulation signals being composed so that an overall degree of statistical dependence, which is determined in a time and/or frequency domain, for all pairs of modulation signals of the set of at least one modulation signal corresponding to two separate visual stimuli, is lower than a second threshold.

11. The system as claimed in claim 9 , wherein the reconstructed modulation signal is obtained by applying a reconstruction model to the plurality of electroencephalographic signals.

12. The system as claimed in claim 9 , wherein each modulation signal defines variations as a function of time in at least one parameter of application of an elementary transformation to a graphical object.

13. The system as claimed in claim 12 , wherein the at least one parameter of application is a degree of transformation or a rate of application of an elementary transformation.

14. A non-transitory computer-readable storage medium storing computer-executable instructions, that when executed by the computer, cause the computer to perform operations comprising:

generating a set of at least one visual stimulus to be displayed from at least one graphical object of a human-machine interface of a computational device, from at least one elementary transformation and from a set of at least one modulation signal, a visual stimulus being an animated graphical object obtained by applying to a graphical object a temporal succession of elementary transformations that is temporally parameterized by a corresponding modulation signal;

presenting the at least one visual stimulus in a display to the individual;

recording a plurality of electroencephalographic signals produced by the individual while the individual is paying attention to the displayed at least one visual stimulus; and

performing in real-time, operations comprising:

reconstructing a modulation signal from the plurality of electroencephalographic signals produced by the individual in order to obtain a reconstructed modulation signal;

computing a degree of statistical dependence between the reconstructed modulation signal and each modulation signal of the set of at least one modulation signal; and

in response to identifying at least one visual stimulus corresponding to a modulation signal for which the degree of statistical dependence is higher than a first threshold, triggering one or more operations of the computational device.

15. The non-transitory computer-readable storage medium as claimed in claim 14 ,

wherein the set of at least one visual stimulus comprises a plurality of visual stimuli and the set of at least one modulation signal comprises a plurality of modulation signals, and

wherein the instructions when executed by the computer further case the computer to perform operations comprising:

searching, among the plurality of modulation signals, for a modulation signal for which a degree of statistical dependence with the reconstructed modulation signal is maximal; and

identifying the visual stimulus corresponding to the modulation signal for which the degree of statistical dependence is maximal;

the modulation signals being composed so that an overall degree of statistical dependence, which is determined in a time and/or frequency domain, for all pairs of modulation signals of the plurality of modulation signals corresponding to two separate visual stimuli, is lower than a second threshold.

16. The non-transitory computer-readable storage medium as claimed in claim 14 , wherein the reconstructed modulation signal is obtained by applying a reconstruction model to the plurality of electroencephalographic signals.