Systems and methods for detecting airbag deployment resulting from a vehicle crash
A method for detecting airbag deployment includes operating a plurality of sensors of the mobile device disposed in a vehicle during a drive to obtain a plurality of measurement signals, determining a change in at least one measurement signal of the plurality of measurement signals and that the change exceeds a first threshold. In response to determining that the change exceeds the first threshold, obtaining a pressure measurement signal from a pressure sensor of the plurality of sensors, determining a derivative of the pressure measurement signal, and determining that the derivative of the pressure measurement signal exceeds a second threshold. In response to determining that the derivative of the pressure measurement signal exceeds the second threshold, detecting a deployment of a vehicle airbag based on the change in the at least one measurement signal exceeding the first threshold and the derivative of the pressure measurement signal exceeding the second threshold.
1. A method for detecting airbag deployment using a mobile device, the method comprising:
operating a plurality of sensors of the mobile device, wherein the mobile device is disposed in a vehicle during a drive;
obtaining a plurality of motion measurement signals from the plurality of sensors of the mobile device;
monitoring, by a processor of the mobile device, at least one motion measurement signal of the plurality of motion measurement signals, wherein the processor monitors the at least one motion measurement signal for a first time window;
calculating, by the processor of the mobile device, a first difference in the at least one motion measurement signal corresponding to a first leading edge of the first time window and a first trailing edge of the first time window;
determining, by the processor of the mobile device, that the first difference exceeds a first threshold;
in response to determining that the first difference exceeds the first threshold, monitoring by the processor of the mobile device, a pressure measurement signal, wherein the processor monitors the pressure measurement signal for a second time window;
calculating, by the processor of the mobile device, a second difference in the pressure measurement signal corresponding to a second leading edge of the second time window and a second trailing edge of the second time window;
determining, by the processor of the mobile device, that the second difference exceeds a second threshold;
in response to determining that the second difference exceeds the second threshold, detecting the airbag deployment based on the first difference exceeding the first threshold and the second difference exceeding the second threshold; and
based on detecting the airbag deployment:
identifying a vehicle crash event; and
transmitting a signal to at least one of the mobile device or a computer of a service provider to output an indication of the vehicle crash event.
2. The method of claim 1 , wherein the first leading edge of the first time window is prior in time to the second trailing edge of the second time window.
3. The method of claim 1 , wherein the at least one motion measurement signal is a magnitude of the at least one motion measurement signal.
4. The method of claim 1 , wherein the at least one motion measurement signal is a rate of change of the at least one motion measurement signal.
5. The method of claim 1 , wherein the plurality of sensors comprises a barometer, an accelerometer, a gyroscope, and a magnetometer.
6. The method of claim 5 , wherein the at least one motion measurement signal is generated by the accelerometer.
7. The method of claim 5 , wherein the at least one motion measurement signal is generated by the gyroscope.
8. The method of claim 5 , wherein the at least one motion measurement signal is generated by the magnetometer.
9. The method of claim 5 , wherein the at least one motion measurement signal is generated by any combination of the accelerometer, the gyroscope, or the magnetometer.
10. The method of claim 1 , wherein the at least one motion measurement signal is a rate of change of a global positioning system (GPS) speed signal received by the mobile device.
11. The method of claim 1 , wherein the second threshold is based on a sampling frequency of the pressure measurement signal.
12. The method of claim 11 , wherein the second threshold is based on a regression function that relates between a set of second thresholds and a set of sampling frequencies; and
wherein the regression function is generated based on pressure measurement signals collected from past vehicle crash events.
13. The method of claim 1 , wherein detecting the airbag deployment comprises inputting information representing the pressure measurement signal and the at least one motion measurement signal to a trained classifier to detect the airbag deployment.
14. The method of claim 13 , wherein the trained classifier is trained to extract features from the information representing the pressure measurement signal and the at least one motion measurement signal, the features comprising at least one of: a peak acceleration and acceleration changes of the vehicle due to an impact, a rotation rate of the mobile device to sense vibrations from the impact, or a pressure and pressure changes based on the pressure measurement signal due to the airbag deployment; and
wherein the trained classifier is trained to detected airbag deployment based on the features.
15. The method of claim 1 , wherein the pressure measurement signal is a rate of change of a pressure measurement signal computed by the processor of the mobile device.
16. The method of claim 15 , wherein determining the rate of change of the pressure measurement signal comprises:
obtaining a plurality of air pressure measurement signals measuring an air pressure inside the vehicle from a barometer of the mobile device; and
determining a change in the air pressure inside the vehicle over time based on the plurality of motion measurement signals generated by the barometer.