Could someone please direct me to a benchmarked dataset for the subject of driver attention/distraction detection using machine learning, I've surveyed a few papers and they seem to collect their own data, which I was not able to acquire, the data signals used usually include the following, in both attention and distraction scenarios:
- Speed [m/s].
- Time to collision [s].
- Time to lane crossing [s].
- Steering angle [deg].
- Lateral position [m].
- Position of the accelerator pedal [%].
- Position of the brake pedal [%].
- Heading angle: angle between the longitudinal axis of the vehicle and the tangent on the centerline of the street.
- Lateral deviation: deviation of the center of the car from the middle of the traffic lane.
- Head rotation: rotation around the vertical axis of the car, measured using the head tracking system installed in the car console.
Thanks.