Multi-sensor hand detection

1. A method comprising:

by a computing device, receiving real-time sensor data from sensors of a plurality of different sensor types on the computing device, the real-time sensor data from each of two or more of the plurality of different sensor type comprising a transition of the real-time sensor data, each transition of the real-time sensor data corresponding to a transition in a physical state of the computing device caused by a user of the computing device;

by the computing device, correlating the real-time sensor data from the two or more of the plurality of different sensor types on the computing device based on determining whether the respective transitions of the real-time sensor data from each of the two or more of the plurality of different sensor types chronologically overlap with each other based at least in part on a linear combination of the real-time sensor data received from each of the two or more of the plurality of different sensor types as a function of time;

by the computing device, determining based on the correlation an intended imminent use of the computing device by the user; and

by the computing device, automatically initiating based on the determination a pre-determined function of the computing device.

2. The method of claim 1 , wherein the plurality of sensors comprises a touch sensor, accelerometer, gyroscope, optical proximity sensor, ambient light sensor, image sensor, or any combination thereof.

3. The method of claim 2 , wherein the plurality of real-time sensor data comprises sensor data from the touch sensor and accelerometer.

4. The method of claim 1 , wherein the linear combination of the real-time sensor data comprises, by the computing device, applying a convolution operation to the real-time sensor data as a function of time.

5. The method of claim 4 , wherein the initiation comprises powering down the computing device in response to a result of the convolution operation correlating the chronological overlap of the respective transitions being higher than a pre-determined threshold.

6. The method of claim 4 , further comprising, by the computing device, remaining in a current state based at least in part on a result of the convolution operation correlating the chronological overlap of the respective transitions being lower than a pre-determined threshold.

7. The method of Claim 4 , further comprising, by the computing device, calculating a derivative of the real-time sensor data of each of two or more of the plurality of different sensor types as a function of time, wherein the convolution operation is applied to the calculated derivatives.

8. The method of claim 1 , wherein:

the computing device is a mobile computing device; and

the intended imminent use corresponds to the user contacting the mobile computing device.

9. One or more computer-readable non-transitory storage media embodying software configured when executed to:

receive real-time sensor data from sensors of a plurality of different sensor types on a computing device, the real-time sensor data from each of two or more of the plurality of different sensor type comprising a transition of the real-time sensor data, each transition of the real-time sensor data corresponding to a transition in a physical state of the computing device caused by a user of the computing device;

correlate the real-time sensor data from the two or more of the plurality of different sensor types on the computing device based on determining whether the respective transitions of the real-time sensor data from each of the two or more of the plurality of different sensor types chronologically overlap with each other based at least in part on a linear combination of the real-time sensor data received from each of the two or more of the plurality of different sensor types as a function of time;

determine based on the correlation an intended imminent use of the computing device by the user; and

automatically initiate based on the determination a pre-determined function of the computing device.

10. The media of claim 9 , wherein the plurality of sensors comprises a touch sensor, accelerometer, gyroscope, optical proximity sensor, ambient light sensor, image sensor, or any combination thereof.

11. The media of claim 10 , wherein the plurality of real-time sensor data comprises sensor data from the touch sensor and accelerometer.

12. The media of claim 9 , wherein the software is further configured to apply a convolution operation to the real-time sensor data a function of time.

13. The media of claim 12 , wherein the software is further configured to power down the computing device in response to a result of the convolution operation correlating the chronological overlap of the respective transitions being higher than a pre-determined threshold.

14. The media of claim 12 , wherein the software is further configured to remain in a current state based at least in part on a result of the convolution operation correlating the chronological overlap of the respective transitions being lower than a pre-determined threshold.

15. The media of claim 9 , wherein the software is further configured to calculate a derivative of the real-time sensor data of each of two or more of the plurality of different sensor types as a function of time, wherein the convolution operation is applied to the calculated derivatives.

16. The media of claim 9 , wherein:

the computing device is a mobile computing device; and

the intended imminent use corresponds to the user contacting the mobile computing device.

17. A device comprising:

a processor; and

one or more computer-readable non-transitory storage media coupled to the processor and embodying software that:

receive real-time sensor data from sensors of a plurality of different sensor types on the device, the real-time sensor data from each of two or more of the plurality of different sensor type comprising a transition of the real-time sensor data, each transition of the real-time sensor data corresponding to a transition in a physical state of the computing device caused by a user of the device;

correlate the real-time sensor data from the two or more of the plurality of different sensor types on the device based on determining whether the respective transitions of the real-time sensor data from each of the two or more of the plurality of different sensor types chronologically overlap with each other based at least in part on a linear combination of the real-time sensor data received from each of the two or more of the plurality of different sensor types as a function of time;

determine based on the correlation an intended imminent use of the device by the user; and

automatically initiate based on the determination a pre-determined function of the device.

18. The device of claim 17 , wherein the plurality of sensors comprises a touch sensor, accelerometer, gyroscope, optical proximity sensor, ambient light sensor, image sensor, or any combination thereof.

19. The device of claim 18 , wherein the plurality of real-time sensor data comprises sensor data from the touch sensor and accelerometer.

20. The device of claim 17 , wherein the software is further configured to apply a convolution operation to the real-time sensor data a function of time.