System and methods for detecting vehicle braking events using data from fused sensors in mobile devices
One or more braking event detection computing devices and methods are disclosed herein based on fused sensor data collected during a window of time from various sensors of a mobile device found within an interior of a vehicle. The various sensors of the mobile device may include a GPS receiver, an accelerometer, a gyroscope, a microphone, a camera, and a magnetometer. Data from vehicle sensors and other external systems may also be used. The braking event detection computing devices may adjust the polling frequency of the GPS receiver of the mobile device to capture non-consecutive data points based on the speed of the vehicle, the battery status of the mobile device, traffic-related information, and weather-related information. The braking event detection computing devices may use classification machine learning algorithms on the fused sensor data to determine whether or not to classify a window of time as a braking event.
1. An apparatus comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the apparatus to:
collect, via sensors associated with a computing device in a vehicle, during a first window of time, and using a polling frequency based on a speed of the vehicle, sensor data associated with the vehicle;
process the sensor data by removing at least one duplicate data point in the sensor data;
classify, based on the processed sensor data, a second window of time as a braking event;
generate, based on the braking event, a notification relating to the braking event; and
transmit, to a second computing device within a predetermined distance of the vehicle, the notification.
2. The apparatus of claim 1 , further including instructions that, when executed by the one or more processors, cause the apparatus to remove the at least one duplicate data point by replacing the at least one duplicate data point with an average value based on a previous data point and a subsequent data point.
3. The apparatus of claim 1 , further including instructions that, when executed by the one or more processors, cause the apparatus to classify the second window of time as the braking event based on a reference frame of the vehicle.
4. The apparatus of claim 1 , wherein the instructions, when executed by the one or more processors, cause the apparatus to modify the polling frequency based on determining that the speed of the vehicle satisfies a threshold.
5. The apparatus of claim 1 , wherein the polling frequency is further based on weather conditions associated with the vehicle.
6. The apparatus of claim 1 , wherein the polling frequency is further based on traffic conditions associated with the vehicle.
7. The apparatus of claim 1 , wherein the polling frequency is further based on a battery status of the computing device.
8. A method comprising:
collecting, via sensors associated with a computing device in a vehicle, during a first window of time, and using a polling frequency based on a speed of the vehicle, sensor data associated with the vehicle;
processing the sensor data by removing at least one duplicate data point in the sensor data;
classifying, based on the processed sensor data, a second window of time as a braking event;
generating, based on the braking event, a notification relating to the braking event; and
transmitting, to a second computing device within a predetermined distance of the vehicle, the notification.
9. The method of claim 8 , wherein removing the at least one duplicate data point comprises:
replacing the at least one duplicate data point with an average value based on a previous data point and a subsequent data point.
10. The method of claim 8 , further comprising:
determining a reference frame of the vehicle, wherein the classifying the second window of time as the braking event is based on the reference frame of the vehicle.
11. The method of claim 8 , further comprising:
modifying the polling frequency based on determining that the speed of the vehicle satisfies a threshold.
12. The method of claim 8 , wherein the polling frequency is further based on weather conditions associated with the vehicle.
13. The method of claim 8 , wherein the polling frequency is further based on traffic conditions associated with the vehicle.
14. The method of claim 8 , wherein the polling frequency is further based on a battery status of the computing device.
15. A method of detecting braking events comprising:
collecting, via sensors associated with a computing device in a vehicle and during a first window of time, sensor data associated with the vehicle;
determining a reference frame of the vehicle by comparing a first portion of the sensor data with a second portion of the sensor data;
classifying, based on the sensor data and the reference frame, a second window of time as a braking event;
generating, based on the braking event, a visual notification; and
transmitting, to one or more second computing devices within a predetermined distance of the vehicle, the visual notification.
16. The method of claim 15 , wherein determining the reference frame of the vehicle further comprises determining an orientation of the computing device.
17. The method of claim 15 , further comprising:
determining a duplicate data point in the sensor data; and
replacing the duplicate data point with an average value based on a previous data point and a subsequent data point.
18. The method of claim 15 , wherein classifying the second window of time as the braking event comprises comparing the sensor data to a predetermined threshold.
19. The method of claim 15 , wherein determining the reference frame of the vehicle further comprises determining axis associated with one or more of: maximum speed, or maximum acceleration.
20. The method of claim 15 , wherein determining the reference frame of the vehicle further comprises determining that an axis associated with a direction of gravity.