System and method for contextualized vehicle operation determination
A method for determining event data including: sampling a first data stream within a first time window at a first sensor of an onboard vehicle system coupled to a vehicle, extracting interior activity data from the first data stream; determining an interior event based on the interior activity data; sampling a second data stream within a second time window at a second sensor of the onboard vehicle system; extracting exterior activity data from the second image stream; determining an exterior event based on the exterior activity data; correlating the exterior event and the interior event to generate combined event data; automatically classifying the combined event data to generate an event label; and automatically labeling the first time window of the first data stream and the second time window of the second data stream with the combined event label to generate labeled event data.
1. A method involving a first image stream and a second image stream, the method comprising:
sampling the first image stream within a first time window at an interior-facing camera of an onboard vehicle system, wherein the onboard vehicle system is configured to couple to a vehicle;
electronically extracting interior activity data indicating a state of a driver from the first image stream;
determining an interior event based on the interior activity data;
sampling the second image stream within a second time window at an exterior-facing camera of the onboard vehicle system;
electronically extracting exterior activity data from the second image stream;
determining an exterior event based on the exterior activity data;
correlating the interior event and the exterior event to generate combined event data, wherein the act of correlating comprises:
determining a first metric based on the interior event,
determining a second metric associated with the exterior event, and
determining a third metric based on the first metric and the second metric associated with the exterior event; and
classifying the combined event data;
wherein the act of determining the interior event, the act of determining the exterior event, and the act of correlating the interior event and the exterior event to generate combined event data, are performed by one or more electronic processing units.
2. The method of claim 1 , wherein the act of electronically extracting the exterior activity data comprises:
determining a relative distance between the vehicle and an object depicted in the second image stream.
3. The method of claim 2 , wherein the object is a secondary vehicle, and wherein the act of determining the exterior event comprises determining that the relative distance between the vehicle and the secondary vehicle is below a threshold.
4. The method of claim 1 , wherein the exterior event comprises a near-miss event, wherein the near-miss event occurs within the first-time window, and wherein the act of correlating the interior event and the exterior event comprises associating the interior event with the near-miss event; and
wherein the combined event data comprises the near-miss event, and the associated interior event.
5. The method of claim 1 , wherein the state of the driver comprises a distracted state, and the electronically extracted interior activity data indicates the distracted state of the driver.
6. The method of claim 1 , wherein the second metric associated with the exterior event indicates a severity of the exterior event.
7. The method of claim 1 , further comprising generating training data based on the classified combined event data.
8. The method of claim 7 , further comprising:
training a vehicle control model using the training data; and
transmitting a copy of the vehicle control model to the vehicle for controlling the vehicle.
9. The method of claim 1 , wherein the first metric comprises a weight.
10. A method involving a first image stream and a second image stream, the method comprising:
sampling the first data stream within a first time window at a first sensor of an onboard vehicle system that is configured to couple to a vehicle;
electronically extracting interior activity data from the first data stream;
determining an interior event based on the interior activity data;
sampling the second data stream within a second time window at a second sensor of the onboard vehicle system;
electronically extracting exterior activity data from the second image stream;
determining an exterior event based on the exterior activity data;
correlating the exterior event and the interior event to generate combined event data, wherein the act of correlating the interior event with the exterior event comprises calculating a probability that the interior event and the exterior event are related, wherein the combined event data comprises the exterior event, the interior event, the probability, or any combination of the foregoing; and
classifying the combined event data;
wherein the act of determining the interior event, the act of determining the exterior event, and the act of correlating the exterior event and the interior event to generate the combined event data, are performed by one or more electronic processing units.
11. The method of claim 10 , wherein the first data stream comprises gyroscope data.
12. The method of claim 11 , wherein the act of electronically extracting the interior activity data comprises determining a mean time interval between steering inputs based on the gyroscope data; and
wherein the act of determining the interior event comprises determining a driver distraction event based on the mean time interval exceeding a threshold duration.
13. The method of claim 10 , wherein the act of correlating the exterior event and the interior event comprises:
determining a first metric based on the interior event;
determining a second metric associated with the exterior event; and
determining a third metric based on the first metric and the second metric.
14. The method of claim 13 , wherein the first metric comprises a weight.
15. The method of claim 10 , wherein the onboard vehicle system is integrated into a mountable unit configured to couple to the vehicle.
16. The method of claim 10 , wherein the interior event and the exterior event are correlated based on relative geometric arrangement between the first sensor and the second sensor.
17. The method of claim 10 , wherein the first data stream comprises a first image stream, and the first sensor comprises a first camera of the onboard vehicle system; and
wherein the second data stream comprises a second image stream, and the second sensor comprises a second camera of the onboard vehicle system.
18. The method of claim 10 , wherein the first time window is coextensive with the second time window.
19. The method of claim 10 , further comprising generating training data based on the classified combined event data.
20. The method of claim 19 , further comprising:
outputting the training data for training a vehicle control model.