Gesture and facial expressions control for a vehicle

1. A vehicle comprising:

a plurality of devices; and

a human-machine interface for a facial expression-based and/or gesture-based actuation of the plurality of devices, wherein the human-machine interface comprises:

a first camera for recording a first occupant of the vehicle,

a second camera for recording a second occupant of the vehicle, and

a control unit connected to the first and second cameras, the control unit configured to extract a first facial expression and a first hand motion performed by the first occupant from image sequences captured by the first camera and to combine the extracted first facial expression and the extracted first hand motion of the first occupant to determine a first function to be actuated by a first device of the plurality of devices, the control unit further configured to extract a second facial expression and a second hand motion performed by the second occupant from image sequences captured by the second camera and to combine the extracted second facial expression and the extracted second hand motion of the second occupant to determine a second function to be actuated by a second device of the plurality of devices, the control unit further configured to actuate the first and second functions simultaneously.

2. The vehicle according to claim 1 , wherein the human-machine interface is configured to recognize the first occupant by means of the first facial expression performed by the first occupant and to determine the first function to be actuated by means of at least one of the first facial expression or the first hand motion performed by the first occupant.

3. The vehicle according to claim 1 , wherein the human-machine interface comprises a data memory for storing interaction profiles of occupants of the vehicle, the interaction profiles comprising a plurality of mappings of a recognized facial expression combined with a recognized hand motion performed by the occupants respectively to the function of one or more of the plurality of devices.

4. The vehicle according to claim 3 , further comprising:

a communications unit connected to the control unit, the communications unit configured to wirelessly communicate with a server arranged outside of the vehicle to load an interaction profile of an occupant stored in a data memory of the server into the control unit, or to store an interaction profile of an occupant of the vehicle in the data memory of the server.

5. The vehicle according to claim 1 , wherein the first occupant is a driver of the vehicle or a passenger in the vehicle.

6. A method for facial expression-based and gesture-based actuation of a function of a plurality of devices of a vehicle, the method comprising:

recording, by a first camera associated with the vehicle, first image sequences of a first occupant of the vehicle, the first image sequences being recorded continuously in real time;

recording, by a second camera associated with the vehicle, second image sequences of a second occupant of the vehicle, the second image sequences being recorded continuously in real time;

analyzing, by a control unit associated with the vehicle, the recorded first and second image sequences;

extracting, by the control unit, a first facial expression and a first hand motion of the first occupant from the first image sequences based at least in part on the analyzing, the first facial expression and the first hand motion extracted separately;

extracting, by the control unit, a second facial expression and a second hand motion of the second occupant from the second image sequences based at least in part on the analyzing, the second facial expression and the second hand motion extracted separately;

(i) combining, by the control unit, the first extracted facial expression and the first hand motion;

(ii) combining, by the control unit, the second extracted facial expression and the second hand motion;

determining, by the control unit, a first function of a first device to be actuated based at least in part on the combining (i);

determining, by the control unit, a second function of a second device to be actuated based at least in part on the combining (ii); and

actuating, by the control unit, the first device according to the determined first function, and simultaneously actuating the second device according to the determined second function.

7. The method according to claim 6 , further comprising:

identifying, by the control unit, the first occupant based at least in part on the first facial expression; and

identifying, by the control unit, the first function based at least in part on at least one of the first facial expression or the first hand motion.

8. The method according to claim 6 , further comprising:

identifying, by the control unit, the first and second facial expressions using a facial expression recognition algorithm; and

identifying, by the control unit, the first and second hand motions using a gesture recognition algorithm;

wherein extracting the first and second facial expressions and the first and second hand motions comprises extracting the first and second facial expressions and the first and second hand motions based on visible and spatially separate skin regions, the skin regions corresponding to a face and a hand of the first and second occupants respectively.

9. The method according to claim 6 , further comprising:

processing, by the control unit, the first and second facial expressions and the first and second hand motions using a learning module; and

identifying, by the control unit, at least one of the first facial expression, the second facial expression, the first hand motion, or the second hand motion based at least in part on the processing.

10. The method according to claim 6 , further comprising:

consolidating, by the control unit, a plurality of mappings of facial expression and hand motion combinations of the first and second occupants respectively to functions of the plurality of devices of the vehicle;

consolidating a plurality of allocations of a recognized facial expression combined with a recognized hand motion of the first and second occupants to a function of a device of the vehicle into interaction profiles associated with the first and second occupants stored by means of a communications unit provided in the vehicle in a data memory of a server arranged outside the vehicle.

11. The method according to claim 10 , in which the interaction profiles are stored in the data memory and loaded out of the data memory for optional use in various different vehicles, particularly vehicles of a vehicle fleet of a company or a car-sharing pool.