System and method for learning driving information in vehicle

1. A system for learning driving information in a vehicle, the system comprising:

a first camera mounted on an inner ceiling of the vehicle and configured to detect a projected position of a nose of the driver;

a second camera mounted on an inner front of the vehicle and configured to detect a front position of the nose of the driver;

a driver's status information processing unit configured to

detect the line of sight of the driver by calibrating an image corresponding to the projected position and an image corresponding to the front position in real time,

analyze information about the line of sight that is detected, and

store the analyzed information in a driving learning database as learning data,

wherein the driver's status information processing unit is further configured to

recognize driver information of the driver after temporally storing images captured by the first and second cameras,

determine whether the driver who gets in the vehicle is a pre-registered driver based on the driver information,

register the driver information of the driver who gets in the vehicle when the driver is the pre-registered driver, and

register the driver as a new driver when the driver is not the pre-registered driver.

2. The system of claim 1 , wherein the first camera has a capability of rotation and movement.

3. The system of claim 1 , wherein the first camera comprises a depth sensor.

4. The system of claim 1 , wherein the driver's status information processing unit updates the driving learning database.

5. The system of claim 1 , further comprising:

a voice recognition unit configured to recognize a voice of the driver who gets in the vehicle and provide information about the recognized voice to the driver's status information processing unit.

6. The system of claim 1 , further comprising:

a camera controlling unit configured to calibrate the operations of the first camera and second camera in accordance with a processed result from the driver's status information processing unit.

7. The system of claim 1 , further comprising:

a user interface unit configured to input user interface information to the driver's status information processing unit or receive a feedback on a processed result of a user interface from the driver's status information processing unit.

8. The system of claim 7 , wherein the user interface is based on a multi-modal interface.

9. The system of claim 1 , wherein the learning data in the driving learning database is exchanged with another system to learn driving information in another vehicle.

10. A method for learning driving information in a vehicle through the use of images captured by first and second cameras, the method comprising:

recognizing a voice of a driver when the driver is detected in the vehicle;

recognizing a face image of the driver through the first and second cameras;

calculating a mutual location between the first and second cameras;

detecting an uttered position of the voice and a location of a face of the driver by moving and rotating each of the first and second cameras; and

building learning data by tracking a line of sight of the driver,

wherein said recognizing a face image comprises:

recognizing driver information of the driver after temporally storing the images captured by the first and second cameras;

determining whether the driver who gets in the vehicle is a pre-registered driver based on the driver information;

registering the driver information of the driver who gets in the vehicle when the driver is a pre-registered driver; and

registering the driver as a new driver when the driver is not a pre-registered driver.

11. The method of claim 10 , further comprising:

detecting a projected position of a nose of the driver using the first camera, which is mounted on an inner ceiling of the vehicle.

12. The method of claim 10 , further comprising:

detecting a front position of the nose of the driver using the second camera, which is mounted on an inner front of the vehicle.

13. The method of claim 10 , wherein said building learning data comprises:

recognizing the line of sight of the driver in the vehicle to detect the driver information of the driver; and

storing learning data from the detected driver information.

14. The method of claim 13 , wherein said building learning data comprises:

combining one or more of a voice instruction, a gesture instruction of the driver, or the line of sight of the driver in accordance with the detected driver information.

15. The method of claim 10 , wherein said building learning data comprises:

updating the learning data in real time;

providing a feedback based on the learning data that is updated in real time from the learning data that is built previously.

16. A system for learning driving information in a vehicle, the system comprising:

a first camera mounted on an inner ceiling of the vehicle and including a depth sensor, the depth sensor being configured to capture first image information of a driver of the vehicle, the first image information comprising a depth map image of the driver's head;

a second camera mounted on an inner front of the vehicle and configured to capture second image information of the driver;

a driver's status information processing unit configured to

detect a projected position of a nose of the driver from the depth map image, the projected position of the nose of the driver being the most prominent feature in a forward-looking direction of the driver in the depth map image,

detect a front position of the nose of the driver from the second image information,

detect the line of sight of the driver by calibrating the first image information corresponding to the projected position of the nose of the driver and the second image information corresponding to the front position of the nose of the driver,

analyze information about the line of sight that is detected, and

store the analyzed information in a driving learning database as learning data.