Driver state sensing system, driver state sensing method, and vehicle including the same
Disclosed are a driver state sensing system, a driver state sensing method, and a vehicle including the same. The driver state sensing system includes an image photographing unit composed of a single channel to photograph images, a controller that extracts at least one shape point from a driver image sensed in the images and compares a motion vector calculated based on the amount of change of the shape point with at least one drowsiness vector stored in advance to determine whether a driver is in a drowsiness state, and a warning unit to warn when it is determined that the driver is in a drowsiness state.
1. A driver state sensing system comprising:
an image photographing unit comprising a channel to photograph images;
a controller that extracts at least two shape points from driver images sensed in the images and compares a motion vector calculated based on an amount of change of the shape points with at least one drowsiness vector stored in advance to determine whether a driver is in a drowsiness state; and
a warning unit to warn when it is determined that the driver is in a drowsiness state.
2. The driver state sensing system according to claim 1 ,
wherein the controller calculates the motion vector based on a first shape point of a first frame captured at a first time and a second shape point of a second frame captured a second time which is different from the first time.
3. The driver state sensing system according to claim 2 ,
wherein the controller comprises a frame buffer to store the first frame of the first time and the second frame of the second time.
4. The driver state sensing system according to claim 1 ,
wherein the controller determines that a driver is in the drowsiness state and learns the calculated motion vector if difference between the calculated motion vector and the at least one drowsiness vector stored in advance has an error smaller than a preset first threshold value.
5. A driver state sensing method comprising:
photographing images based on a camera sensor;
extracting at least two shape points from driver images sensed in the images;
calculating a motion vector based on an amount of change of the shape points;
comparing the calculated motion vector with at least one drowsiness vector stored in advance to determine whether a driver is in a drowsiness state; and
warning when it is determined that the driver is in the drowsiness state.
6. The driver state sensing method according to claim 5 ,
wherein the calculating the motion vector comprises:
storing a first shape point of a first frame captured at a first time;
storing a second shape point of a second frame captured at a second time which is different from the first time; and
calculating the motion vector based on the first shape point and the second shape point.
7. The driver state sensing method according to claim 5 ,
wherein the comparing the calculated motion vector with the at least one drowsiness vector comprises:
determining that the driver is in the drowsiness state if difference between the calculated motion vector and the at least one drowsiness vector stored in advance has an error smaller than a preset first threshold value.
8. The driver state sensing method according to claim 7 , further comprising learning the calculated motion vector.
9. A vehicle comprising a driver state sensing system,
wherein the driver state sensing system comprises:
an image photographing unit comprising a channel to photograph images;
a controller that extracts at least two shape points from driver images sensed in the images and compares a motion vector calculated based on an amount of change of the shape points with at least one drowsiness vector stored in advance to determine whether a driver is in a drowsiness state; and
a warning unit to warn when it is determined that the driver is in the drowsiness state.
10. The vehicle according to claim 9 ,
wherein the image photographing unit comprises a camera sensor, and
the camera sensor is installed at a position of at least one of a front pillar, a rearview mirror, and a dashboard of the vehicle to photograph the driver.
11. The vehicle according to claim 10 ,
wherein the controller calculates the motion vector based on a first shape point of a first frame captured at a first time and a second shape point of a second frame captured at a second time which is different from the first time.
12. The vehicle according to claim 11 ,
wherein the controller determines that the driver is in the drowsiness state and learns the calculated motion vector if the difference between the calculated motion vector and the at least one drowsiness vector stored in advance has an error smaller than a preset first threshold value.