Devices and methods for monitoring drivers of vehicles
An apparatus includes: a camera configured to view a driver of a vehicle; and a processing unit configured to receive an image of the driver from the camera; wherein the processing unit is configured to process the image of the driver to determine whether the driver is engaged with a driving task or not; and wherein the processing unit is configured to determine whether the driver is engaged with the driving task or not based on a pose of the driver as it appears in the image without a need to determine a gaze direction of an eye of the driver.
1. An apparatus comprising:
a camera configured to view a driver of a vehicle;
an additional camera configured to view an environment outside the vehicle; and
a processing unit configured to receive an image of the driver from the camera;
wherein the processing unit is configured to process the image of the driver;
wherein the processing unit is configured to determine whether the driver is engaged with a driving task or not based on a pose of the driver as it appears in the image, and also based on one or more images from the additional camera that is configured to view the environment outside the vehicle, the one or more images from the additional camera comprising an image of the environment outside the vehicle;
wherein the processing unit is configured to determine the pose of the driver as it appears in the image based on a pose classification threshold, and wherein the pose classification threshold is for comparison with a pose classification score provided by a neural network model, the pose classification score comprising a head orientation score; and
wherein the processing unit is configured to adjust the pose classification threshold based on the image of the environment outside the vehicle.
2. The apparatus of claim 1 , wherein the processing unit is configured to attempt to determine a gaze direction of an eye of the driver; and
wherein the processing unit is configured to determine whether the driver is engaged with the driving task or not based on the one or more pose classifications for the driver after the processing unit is unable to determine the gaze direction.
3. The apparatus of claim 1 , further comprising a non-transitory medium storing the neural network model.
4. The apparatus of claim 1 , further comprising a communication unit configured to obtain the neural network model.
5. The apparatus of claim 1 , wherein the neural network model is trained based on images of other drivers.
6. The apparatus of claim 1 , wherein the processing unit is configured to obtain metric values for multiple respective pose classifications, one of the metric values being the head orientation score, and wherein the processing unit is configured to determine whether the driver is engaged with the driving task or not based on one or more of the metric values.
7. The apparatus of claim 6 , wherein the pose classifications comprise two or more of: looking-down pose, looking-up pose, looking-left pose, looking-right pose, cellphone-using pose, smoking pose, holding-object pose, hand(s)-not-on-the wheel pose, not-wearing-seatbelt pose, eye(s)-closed pose, looking-straight pose, one-hand-on-wheel pose, and two-hands-on-wheel pose.
8. The apparatus of claim 6 , wherein the processing unit is configured to compare the metric values with respective thresholds for the respective pose classifications, and wherein the pose classification threshold is one of the thresholds.
9. The apparatus of claim 8 , wherein the processing unit is configured to determine the driver as belonging to one of the pose classifications after the corresponding one of the metric values meets or surpasses the corresponding one of the thresholds.
10. The apparatus of claim 8 , wherein the processing unit is configured to determine the driver as engaged with the driving task or not after one or more of the metric values meet or surpass the corresponding one or more of the thresholds.
11. The apparatus of claim 1 , wherein the processing unit is also configured to process the image to determine whether a face of the driver is detected or not, and wherein the processing unit is configured to process the image of the driver to determine whether the driver is engaged with the driving task or not after the face of the driver is detected from the image.
12. The apparatus of claim 1 , wherein the processing unit is also configured to process the image to determine whether an eye of the driver is closed or not.
13. The apparatus of claim 1 , wherein the processing unit is also configured to determine a gaze direction of an eye of the driver, and to determine whether the driver is engaged with the driving task or not based on the gaze direction.
14. The apparatus of claim 1 , wherein the processing unit is also configured to determine a collision risk based on whether the driver is engaged with the driving task or not.
15. The apparatus of claim 1 , wherein the camera and the processing unit are integrated as parts of an aftermarket device for the vehicle.
16. The apparatus of claim 15 , wherein the additional camera is a part of the aftermarket device.
17. An apparatus comprising:
a camera configured to view a driver of a vehicle; and
a processing unit configured to receive an image of the driver from the camera;
wherein the processing unit is configured to attempt to determine a gaze direction of an eye of the driver;
wherein the processing unit is configured to determine whether the driver is engaged with a driving task or not based on one or more pose classifications for the driver and also based on an image from an additional camera viewing an environment outside the vehicle, when the processing unit is unable to determine the gaze direction, the image from the additional camera comprising an image of the environment outside the vehicle; and
wherein the processing unit is configured to adjust a threshold for determining at least one of the pose classifications, wherein the threshold is for comparison with a pose classification score provided by a neural network model, the pose classification score comprising a head orientation score, and wherein the processing unit is configured to adjust the threshold based on the image of the environment outside the vehicle.
18. The apparatus of claim 17 , wherein the processing unit is configured to process the image of the driver to determine whether the image of the driver meets one or more pose classifications or not; and
wherein the processing unit is configured to determine whether the driver is engaged with the driving task or not based on the image of the driver meeting the one or more pose classifications or not.
19. The apparatus of claim 17 , wherein the processing unit is configured to process the image of the driver based on the neural network model to determine whether the driver is engaged with the driving task or not.
20. A method performed by an apparatus, the method comprising:
obtaining an image of a driver of a vehicle generated by a camera viewing the driver of the vehicle;
obtaining another image generated by an additional camera that is configured to view an environment outside the vehicle;
processing, by a processing unit, the image of the driver;
determining a pose of the driver based on a threshold, wherein the threshold is for comparison with a pose classification score provided by a neural network model, the pose classification score comprising a head orientation score; and
determining whether the driver is engaged with a driving task or not based on the pose of the driver, and also based on the another image generated by the additional camera that is configured to view the environment outside the vehicle, the another image generated by the additional camera comprises an image of the environment outside the vehicle;
wherein the method further comprises adjusting the threshold, wherein the threshold is adjusted based on the image of the environment outside the vehicle.
21. The apparatus of claim 1 , wherein the pose classification score has a value that is anywhere from 0 to 1.
22. The apparatus of claim 1 , wherein the pose classification score indicates a pose classification probability.
23. The apparatus of claim 17 , wherein the pose classification score has a value that is anywhere from 0 to 1.
24. The apparatus of claim 17 , wherein the pose classification score indicates a pose classification probability.
25. The method of claim 20 , wherein the pose classification score has a value that is anywhere from 0 to 1.
26. The method of claim 20 , wherein the pose classification score indicates a pose classification probability.