Detection and analysis of percussive sounds
A system is disclosed for detecting and correlating percussive sounds with previously identified spectral signatures of a plurality of events so as to notify a user of an occurrence of a particular event. The system may include a sensor component which includes a piezoelectric transducer at a periphery of the sensor component for coupling with a surface and converting percussive sounds from the surface into an electrical signal. The sensor component may also include a local processor configured to produce a data signal based on the electrical signal, and a communication device for sending the data signal to a remote processor. The system may also include a remote processor configured to receive the data signal and compare the data signal to at least one reference signal and send a notification to a user based at least in part on the data signal correlating to at least one reference signal.
1. A system comprising:
a first processor configured to send, to a second processor and based on determining that an electrical signal associated with a sound satisfies a threshold, a data signal based on the electrical signal, wherein the threshold is based at least in part on one or more electrical signals received during an ambient noise period; and
the second processor configured to:
receive, from the first processor, the data signal; and
send, based on determining that the data signal is associated with an event, a notification indicative of the event.
2. The system recited in claim 1 , wherein the threshold is associated with at least one of an amplitude of the sound or a frequency of the sound.
3. The system recited in claim 1 , wherein the threshold is further based on a comparison of the one or more electrical signals received during the ambient noise period to one or more reference signals indicative of ambient noise.
4. The system recited in claim 1 , wherein the data signal is based on a spectral analysis of the electrical signal.
5. The system recited in claim 4 , wherein the spectral analysis comprises a Fourier transform.
6. The system recited in claim 1 , wherein the determining that the data signal is associated with the event comprises determining that the data signal correlates to at least one reference signal associated with the event.
7. The system recited in claim 6 , wherein the at least one reference signal comprises a spectral signature associated with the event.
8. The system recited in claim 6 , wherein the at least one reference signal comprises one of a plurality of reference signals each associated with a different event.
9. The system recited in claim 1 , wherein the event comprises an occurrence of at least one of: a doorbell sound, a smoke alarm sound, a carbon monoxide alarm sound, a security alarm sound, a door ajar alarm sound, a glass breaking sound, a door opening sound, a water flowing sound, or a collision sound.
10. The system recited in claim 1 , wherein the notification comprises at least one of an email sent to a user or a message sent to a device associated with the user.
11. A method comprising:
receiving, by a first processor, an electrical signal indicative of a sound; and
sending, by the first processor to a second processor and based on determining that the electrical signal indicates that the sound satisfies a threshold, a data signal based on the electrical signal, wherein the threshold is based at least in part on one or more electrical signals received during an ambient noise period.
12. The method recited in claim 11 , wherein the threshold is associated with at least one of an amplitude of the sound or a frequency of the sound.
13. The method recited in claim 11 , wherein the threshold is further based on a comparison of the one or more electrical signals received during the ambient noise period to one or more reference signals indicative of ambient noise.
14. The method recited in claim 11 , wherein the data signal is based on a spectral analysis of the electrical signal.
15. The method recited in claim 14 , wherein the spectral analysis comprises a Fourier transform.
16. The method recited in claim 11 , wherein the second processor is configured to receive the data signal and determine whether the data signal correlates to at least one of a plurality of reference signals associated with one or more events.
17. The method recited in claim 11 , wherein the sound comprises at least one of: a doorbell sound, a smoke alarm sound, a carbon monoxide alarm sound, a security alarm sound, a door ajar alarm sound, a glass breaking sound, a door opening sound, a water flowing sound, or a collision sound.
18. A device comprising:
one or more first processors; and
memory storing instructions that, when executed by the one or more first processors, cause the device to:
send, to a second processor and based on determining that an electrical signal associated with a sound satisfies a threshold, a data signal based on the electrical signal, wherein the threshold is based at least in part on one or more electrical signals received during an ambient noise period.
19. The device recited in claim 18 , wherein the threshold is associated with at least one of an amplitude of the sound or a frequency of the sound.
20. The device recited in claim 18 , wherein the threshold is further based on a comparison of the one or more electrical signals received during the ambient noise period to one or more reference signals indicative of ambient noise.
21. The device recited in claim 18 , wherein the data signal is based on a spectral analysis of the electrical signal.
22. The device recited in claim 21 , wherein the spectral analysis comprises a Fourier transform.
23. The device recited in claim 18 , wherein the second processor is configured to receive the data signal from the device and determine whether the data signal correlates to at least one of a plurality of reference signals associated with one or more events.
24. The device recited in claim 18 , wherein the sound comprises at least one of: a doorbell sound, a smoke alarm sound, a carbon monoxide alarm sound, a security alarm sound, a door ajar alarm sound, a glass breaking sound, a door opening sound, a water flowing sound, or a collision sound.
25. A non-transitory computer-readable medium storing instructions that, when executed, cause:
receiving, by a first processor, an electrical signal indicative of a sound; and
sending, by the first processor to a second processor and based on determining that the electrical signal indicates that the sound satisfies a threshold, a data signal based on the electrical signal, wherein the threshold is based at least in part on one or more electrical signals received during an ambient noise period.
26. The non-transitory computer-readable medium recited in claim 25 , wherein the threshold is associated with at least one of an amplitude of the sound or a frequency of the sound.
27. The non-transitory computer-readable medium recited in claim 25 , wherein the threshold is further based on a comparison of the one or more electrical signals received during the ambient noise period to one or more reference signals indicative of ambient noise.
28. The non-transitory computer-readable medium recited in claim 25 , wherein the data signal is based on a spectral analysis of the electrical signal.
29. The non-transitory computer-readable medium recited in claim 28 , wherein the spectral analysis comprises a Fourier transform.
30. The non-transitory computer-readable medium recited in claim 25 , wherein the second processor is configured to receive the data signal and determine whether the data signal correlates to at least one of a plurality of reference signals associated with one or more events.
31. The non-transitory computer-readable medium recited in claim 25 , wherein the sound comprises at least one of: a doorbell sound, a smoke alarm sound, a carbon monoxide alarm sound, a security alarm sound, a door ajar alarm sound, a glass breaking sound, a door opening sound, a water flowing sound, or a collision sound.