Dynamic delivery of vehicle event data
An improved system and method of selectively transmitting asset data from one or more sensors associated with the vehicle to a backend server, which is configured to analyze the asset data and, if necessary for further analysis of the asset data (e.g., to determine whether a safety event has occurred) and/or to provide actionable data for review by a safety analyst, requests further asset data from a vehicle device.
1. A method performed by an event analysis system having one or more hardware computer processors and one or more non-transitory computer readable storage device storing software instructions executable by the computing system, the method comprising:
receiving, from a vehicle device coupled to a vehicle, first event data including at least metadata associated with a safety event detected by the vehicle device, wherein the metadata indicates at least a vehicle device identifier, a type of event, an event time, and a maximum G force detected by one or more sensors of the vehicle device, wherein the vehicle device is configured to emit an audible alert in response to detecting the safety event, wherein the safety event indicates one or more of a collision, harsh braking, harsh acceleration, or harsh turning of the vehicle;
determining, based at least on the type of event indicated in the first event data, second event data including one or more assets associated with the type of event, the one or more assets including at least a video file for a first duration prior to the event time and a second duration after the event time;
transmitting an asset data request for the second event data to the vehicle device;
receiving, from the vehicle device, the second event data;
training an event model associated with the type of event based on at least some of the event data; and
providing the event model to the vehicle device, wherein the event model is used by the vehicle device to detect the type of event.
2. The method of claim 1 , wherein the determined one or more assets are received via a cellular data communication network.
3. The method of claim 1 , further comprising:
analyzing the first event data and the second event data to determine accuracy of the detected safety event; and
generating user interface data configured to display the video file and at least some of the first event data.
4. The method of claim 3 , wherein the user interface data includes an option for a user to indicate accuracy of the detected safety event.
5. The method of claim 1 , wherein the vehicle device is configured to detect the safety event in response to a detected G force exceeding a threshold.
6. The method of claim 5 , wherein the threshold is user configurable.
7. The method of claim 6 , wherein the threshold is user configurable based on preset G force levels associated with a type of vehicle, wherein types of vehicles include at least passenger, light duty, and heavy duty.
8. A computing system comprising:
a vehicle device coupled to a vehicle, the vehicle device configured to:
access sensor data from one or more vehicle sensors;
for each of a plurality of safety events:
determine whether criteria for a harsh event are matched and, if matched, provide an audible and/or visual alert of the harsh event within the vehicle;
transmit metadata associated with the harsh event to an event analysis system, the metadata including at least a type of event and a G force level sensed by one or more accelerometers associated with the vehicle; and
receive and respond to requests for data assets from the event analysis system; and
the event analysis system configured to:
receive the metadata associated with the detected harsh event;
determine, based at least on a type of event indicated in the metadata, whether data assets associated with the detected harsh event should be requested;
in response to determining that data assets should be requested, transmitting a data asset request to the vehicle device, wherein the data assets include at least a video file from an outward-facing or a driver-facing camera within the vehicle; and
generating user interface data configured to display the video file and the metadata.
9. The computing system of claim 8 , wherein the data assets include one or more of: video files, still images, audio data, accelerometer data, global positioning system (GPS) data, ECU data, vehicle speed data, forward camera object tracking data, driver facing camera data, and hand tracking data.
10. The computing system of claim 8 , wherein a still image is transmitted with the metadata.
11. The computing system of claim 8 , wherein the metadata includes sensor data from a first sensor and the data assets include sensor data from one or more additional sensors.
12. The computing system of claim 11 , wherein the first sensor comprises an accelerometer and the one or more additional sensors comprise one or more cameras mounted to the vehicle.
13. The computing system of claim 8 , wherein said determining whether data assets associated with the detected harsh event should be requested is based on a listing of data assets associated with the event type.
14. The computing system of claim 8 , wherein the event type is one or more of a collision, harsh acceleration, harsh braking, or harsh turning.