Method and device for classifying eye opening data of at least one eye of an occupant of a vehicle, and method and device for detecting drowsiness and/or microsleep of an occupant of a vehicle

A method for classifying eye opening data of at least one eye of an occupant of a vehicle to detect drowsiness and/or microsleep of the occupant, the method comprising:

• generating a first eye opening data record at a first measuring time in a sliding time window, the first eye opening data record including at least one measuring point, which represents a first eye opening degree and/or a first eyelid speed of motion and/or a first eyelid acceleration of motion of the eye of the occupant at the first measuring time;
• acquiring a second eye opening data record at a second measuring time in the sliding time window, the second eye opening data record including at least one acquisition point, which represents a second eye opening degree and/or a second eyelid speed of motion and/or a second eyelid acceleration of motion of the eye of the occupant at the second measuring time;
• and
• executing a cluster analysis, using the at least one measuring point and the at least one acquisition point, to assign at least the first eye opening data record and/or second eye opening data record to a first data cluster, to classify the eye opening data, the first data cluster representing an opening state of the eye of the occupant.

A method for detecting drowsiness and/or microsleep of an occupant of a vehicle, the method comprising:

• ascertaining drowsiness and/or microsleep, using eye opening data;
• wherein the eye opening data is classified by classifying the eye opening data of at least one eye of the occupant of the vehicle to detect the drowsiness and/or the microsleep of the occupant, by performing the following:
• generating a first eye opening data record at a first measuring time in a sliding time window, the first eye opening data record including at least one measuring point, which represents a first eye opening degree and/or a first eyelid speed of motion and/or a first eyelid acceleration of motion of the eye of the occupant at the first measuring time;
• acquiring a second eye opening data record at a second measuring time in the sliding time window, the second eye opening data record including at least one acquisition point, which represents a second eye opening degree and/or a second eyelid speed of motion and/or a second eyelid acceleration of motion of the eye of the occupant at the second measuring time;
• and
• executing a cluster analysis, using the at least one measuring point and the at least one acquisition point, to assign at least the first eye opening data record and/or second eye opening data record to a first data cluster, to classify the eye opening data, the first data cluster representing an opening state of the eye of the occupant.

A device, comprising:

• a processing device configured to classify eye opening data of at least one eye of an occupant of a vehicle to detect drowsiness and/or microsleep of the occupant, by performing the following:
• generating a first eye opening data record at a first measuring time in a sliding time window, the first eye opening data record including at least one measuring point, which represents a first eye opening degree and/or a first eyelid speed of motion and/or a first eyelid acceleration of motion of the eye of the occupant at the first measuring time;
• acquiring a second eye opening data record at a second measuring time in the sliding time window, the second eye opening data record including at least one acquisition point, which represents a second eye opening degree and/or a second eyelid speed of motion and/or a second eyelid acceleration of motion of the eye of the occupant at the second measuring time;
• and
• executing a cluster analysis, using the at least one measuring point and the at least one acquisition point, to assign at least the first eye opening data record and/or second eye opening data record to a first data cluster, to classify the eye opening data, the first data cluster representing an opening state of the eye of the occupant.

A non-transitory computer readable medium having a computer program, which is executable by a processor, comprising:

• a program code arrangement having program code for classifying eye opening data of at least one eye of an occupant of a vehicle to detect drowsiness and/or microsleep of the occupant, by performing the following:
• generating a first eye opening data record at a first measuring time in a sliding time window, the first eye opening data record including at least one measuring point, which represents a first eye opening degree and/or a first eyelid speed of motion and/or a first eyelid acceleration of motion of the eye of the occupant at the first measuring time;
• acquiring a second eye opening data record at a second measuring time in the sliding time window, the second eye opening data record including at least one acquisition point, which represents a second eye opening degree and/or a second eyelid speed of motion and/or a second eyelid acceleration of motion of the eye of the occupant at the second measuring time;
• and
• executing a cluster analysis, using the at least one measuring point and the at least one acquisition point, to assign at least the first eye opening data record and/or second eye opening data record to a first data cluster, to classify the eye opening data, the first data cluster representing an opening state of the eye of the occupant.