Detection of driving actions that mitigate risk
Systems and methods are provided for detecting a driving action that mitigates risk.
1. A method comprising:
detecting, by at least one processor of a computing device in communication with a camera, the presence of a first vehicle in a field of view of the camera, wherein the camera is mounted on or in a second vehicle;
predicting, by the at least one processor, that the first vehicle will move into a lane in which the second vehicle is traveling;
determining, by the at least one processor, that the first vehicle moved at least partially into the lane at a first point in time, wherein determining that the first vehicle moved at least partially into the lane comprises:
detecting, by the at least one processor, the presence of the first vehicle in the field of view of the camera at the first point in time;
determining, by the at least one processor, a bounding box that surrounds the first vehicle in visual data captured by the camera at the first point in time; and
determining, by the at least one processor, a location of a lane line in the visual data where the lane line intersects a bottom of the bounding box;
determining, by the at least one processor, that the second vehicle slowed down or changed lanes within a predetermined amount of time from the first point in time; and
determining, by the at least one processor, that a driver of the second vehicle mitigated a predicted risk based on the prediction that the first vehicle will move into the lane, the determination that the first vehicle moved into the lane, and the determination that the second vehicle slowed down or changed lanes.
2. The method of claim 1 , further comprising determining a predicted following distance between the second vehicle and the first vehicle, wherein the predicted following distance is below a predetermined safety threshold, and where the predicted risk is based at least in part on the predicted following distance.
3. The method of claim 2 , wherein the second vehicle slowed down within the predetermined amount of time, and wherein determining that the driver of the second vehicle mitigated the predicted risk further comprises determining an actual following distance between the second vehicle and the first vehicle, wherein the actual following distance is above a predetermined safety threshold.
4. The method of claim 1 , wherein the second vehicle slowed down after the first point in time, and wherein determining that the driver of the second vehicle mitigated risk further comprises determining a following distance between the second vehicle and the first vehicle at a second point in time, wherein the second point in time is subsequent to the first point in time.
5. The method of claim 1 , wherein the second vehicle slowed down or changed lanes before the first vehicle moved at least partially into the lane.
6. The method of claim 1 , wherein determining that the driver of the second vehicle mitigated a predicted risk further comprises determining a following distance between the second vehicle and the first vehicle at a point in time before the first point in time at which the first vehicle moved at least partially into the lane.
7. The method of claim 1 , further comprising:
positively adjusting a driver grade for the driver based on the determination that the driver of the second vehicle mitigated the predicted risk.
8. The method of claim 2 , further comprising determining, by the at least one processor, the predetermined safety threshold at least in part based on a speed of the second vehicle.
9. The method of claim 8 , wherein the predetermined safety threshold is lower when the speed of the second vehicle is higher.
10. The method of claim 1 , further comprising transmitting, by the at least one processor, an alert notification to a second device, wherein the alert notification includes an indication that the driver took action to mitigate driving risk.
11. The method of claim 10 , further comprising transmitting, by the at least one processor, visual data to a remote cloud server, wherein the visual data comprises data captured by the camera when the second vehicle slowed down or changed lanes.
12. The method of claim 11 , further comprising training an autonomous vehicle driving system with the visual data.
13. The method of claim 1 , wherein the first vehicle moved at least partially into the lane from a merging lane of a highway.
14. The method of claim 13 , further comprising:
detecting, by the at least one processor, a dotted lane line, and wherein predicting that the first vehicle will move into the lane is based on at least the detected dotted lane line.