Method and system for reliable detection of smartphones within vehicles

1. A method of in-vehicle presence detection comprising:

detecting, by a first mobile device, a signal having a characteristic of an in-vehicle detection system;

detecting, by a second device, the signal, the signal including content that is unique within a time space of an offset between the first mobile device and the second device, wherein the second device is a second mobile device or is a vehicle mounted device;

transmitting, by the first mobile device and the second device, a first indication and a second indication to a cloud solution, wherein the first indication and the second indication represent respective detections of the signal having the characteristic of the in-vehicle detection system;

receiving, by the first mobile device, a first instruction from the cloud solution to analyze one or more first sensor signals to determine a first event;

receiving, by the second device, a second instruction from the cloud solution to analyze one or more second sensor signals to determine a second event;

transmitting, by the first mobile device, first information reflecting the first event and its respective first timing based on a first clock of the first mobile device;

transmitting, by the second device, second information reflecting the second event and its respective second timing based on a second clock of the second device; and

cross-correlating, by the cloud solution, the first event, the second event, the first timing, the second timing and the content to generate an indication of in-vehicle presence.

2. The method of claim 1 , wherein the signal is one of a Bluetooth low energy (BLE) signal, an ultrasound (US) signal, an infrared signal, or a combination thereof.

3. The method of claim 1 , wherein the one or more first sensor signals include signals from one or more of an accelerometer, a gyroscope, a magnetometer, or a pressure sensor.

4. The method of claim 1 , further comprising:

utilizing a stacked convolutional encoder configured to perform feature extraction and dimensionality reduction of the signal.

5. The method of claim 1 , wherein the cross-correlating includes warping a temporal dimension to find a best correlation in the first event and the second event.

6. The method of claim 1 , wherein at least one of the first event or the second event is a transition event that is identified as originating by a transmitter at a transition location on a travel route.

7. An in-vehicle presence detection system comprising at least one processor, the at least one processor configured to:

detect, by a first mobile device, a signal having a characteristic of an in-vehicle detection system;

detect, by a second device, the signal, the signal including content that is unique within a time space of an offset between the first mobile device and the second device, wherein the second device is a second mobile device or is a vehicle mounted device;

transmit, by the first mobile device and the second device, a first indication and a second indication to a cloud solution, wherein the first indication and the second indication represent respective detections of the signal having the characteristic of the in-vehicle detection system;

receive, by the first mobile device, a first instruction from the cloud solution to analyze one or more first sensor signals to determine a first event;

receive, by the second device, a second instruction from the cloud solution to analyze one or more second sensor signals to determine a second event;

transmit, by the first mobile device, first information reflecting the first event and its respective first timing based on a first clock of the first mobile device;

transmit, by the second device, second information reflecting the second event and its respective second timing based on a second clock of the second device; and

cross-correlate, by the cloud solution, the first event, the second event, the first timing, the second timing and the content to generate an indication of in-vehicle presence.

8. The system of claim 7 , wherein the signal is one of a Bluetooth low energy (BLE) signal, an ultrasound (US) signal, an infrared signal, or a combination thereof.

9. The system of claim 7 , wherein the one or more first sensor signals include signals from one or more of an accelerometer, a gyroscope, a magnetometer, or a pressure sensor.

10. The system of claim 7 , wherein the at least one processor is further configured to utilize a stacked convolutional encoder configured to perform feature extraction and dimensionality reduction of the signal.

11. The system of claim 7 , wherein the at least one processor is further configured to cross-correlate by warping a temporal dimension to find a best correlation in the first event and the second event.

12. The system of claim 7 , wherein at least one of the first event or the second event is a transition event that is identified as originating by a transmitter at a transition location on a travel route.

13. A method of in-vehicle presence detection comprising:

detecting, by a first mobile device, a signal having a characteristic of an in-vehicle detection system;

detecting, by a second device, the signal, the signal including content that is unique within a time space of an offset between the first mobile device and the second device, wherein the second device is a second mobile device or is a vehicle mounted device;

transmitting, by the first mobile device and the second device, a first indication and a second indication to a cloud solution, wherein the first indication and the second indication represent respective detections of the signal having the characteristic of the in-vehicle detection system;

selecting, using an algorithm executed by the first mobile device, one or more first portions of one or more first sensor signals for analysis to determine a first event;

selecting, using the algorithm executed by the second device, one or more second portions of one or more second sensor signals for analysis to determine a second event;

transmitting, by the first mobile device, first information reflecting the first event and its respective first timing based on a first clock of the first mobile device;

transmitting, by the second device, second information reflecting the second event and its respective second timing based on a second clock of the second device; and

cross-correlating, by the cloud solution, the first event, the second event, the first timing, the second timing and the content to generate an indication of in-vehicle presence.

14. The method of claim 13 , wherein the signal is one of a Bluetooth low energy (BLE) signal, an ultrasound (US) signal, an infrared signal, or a combination thereof.

15. The method of claim 13 , wherein the one or more first sensor signals include signals from one or more of an accelerometer, a gyroscope, a magnetometer, or a pressure sensor.

16. The method of claim 13 , further comprising:

utilizing a stacked convolutional encoder configured to perform feature extraction and dimensionality reduction of the signal.

17. The method of claim 13 , wherein the cross-correlating includes warping a temporal dimension to find a best correlation in the first event and the second event.

18. The method of claim 13 , wherein at least one of the first event or the second event is a transition event that is identified as originating by a transmitter at a transition location on a travel route.

19. An in-vehicle presence detection system comprising at least one processor, the at least one processor configured to:

detect, by a first mobile device, a signal having a characteristic of an in-vehicle detection system;

detect, by a second device, the signal, the signal including content that is unique within a time space of an offset between the first mobile device and the second device, wherein the second device is a second mobile device or is a vehicle mounted device;

transmit, by the first mobile device and the second device, a first indication and a second indication to a cloud solution, wherein the first indication and the second indication represent respective detections of the signal having the characteristic of the in-vehicle detection system;

select, using an algorithm executed by the first mobile device, one or more first portions of one or more first sensor signals for analysis to determine a first event;

select, using the algorithm executed by the second device, one or more second portions of one or more second sensor signals for analysis to determine a second event;

transmit, by the first mobile device, first information reflecting the first event and its respective first timing based on a first clock of the first mobile device;

transmit, by the second device, second information reflecting the second event and its respective second timing based on a second clock of the second device; and

cross-correlate, by the cloud solution, the first event, the second event, the first timing, the second timing and the content to generate an indication of in-vehicle presence.

20. The system of claim 19 , wherein the signal is one of a Bluetooth low energy (BLE) signal, an ultrasound (US) signal, an infrared signal, or a combination thereof.

21. The system of claim 19 , wherein the one or more first sensor signals include signals from one or more of an accelerometer, a gyroscope, a magnetometer, or a pressure sensor.

22. The system of claim 19 , wherein the at least one processor is further configured to utilize a stacked convolutional encoder configured to perform feature extraction and dimensionality reduction of the signal.

23. The system of claim 19 , wherein the at least one processor is further configured to cross-correlate by warping a temporal dimension to find a best correlation in the first event and the second event.

24. The system of claim 19 , wherein at least one of the first event or the second event is a transition event that is identified as originating by a transmitter at a transition location on a travel route.