Embedded audio sensor system and methods
An embedded sensor can include an audio detector, a digital signal processor, a library, and a rules engine. The digital signal processor can be configured to receive signals from the audio detector and to identify the environment in which the embedded sensor is located. The library can store statistical models associated with specific environments, and the digital signal processor can be configured identify specific events based on detected sounds within the particular environment by utilizing the statistical model associated with the particular environment. The DSP can associate a probability of accuracy for the identified audible event. A rules engine can be configured to receive the probability and transmit a report of the detected audible event.
1 . A sensor comprising:
a camera;
a processor configured to receive signals from the camera, to create data from the received signals, and to detect an event in an image;
a privacy filter configured to obfuscate the data;
wherein the processor is configured to associate a probability with a detected event and to identify the detected event;
a watchdog function configured to determine whether the data is above a privacy threshold and, if so, to direct the processor to further obfuscate the data;
wherein the privacy filter is configured to obfuscate the data using a reduction in a signal-to-noise ratio; and
wherein the reduction in the signal-to-noise ratio is a result of at least one of down-sampling and pixel removal.
2 . The sensor of claim 1 , wherein the camera is a video camera.
3 . The sensor of claim 2 , wherein the video camera is configured to capture video in real time, and further comprising:
an audio detection device configured to capture environmental sounds;
a rules engine programmed to evaluate the captured environmental sounds and the captured video.
4 . The sensor of claim 1 , wherein the watchdog function is performed by the processor.
5 . The sensor of claim 1 , wherein the camera is an infrared camera.
6 . The sensor of claim 1 , wherein the processor is further configured to filter out background noise.
7 . The sensor of claim 3 , wherein the system sends alerts to a mobile device or a cloud upon detecting a combination of pre-specified audio and video events.
8 . The sensor of claim 7 , wherein the processor is further configured to analyze audio and video events in real time and store historical data for future analysis.
9 . The sensor of claim 3 , wherein the processor initiates video recording when a significant audible event is detected.
10 . A method of detecting an event using a sensor, the method comprising:
receiving signals from a camera;
creating data from the received signals using a processor;
detecting an event in an image using the processor;
obfuscating the data using a privacy filter;
associating a probability with the detected event using the processor;
identifying the detected event using the processor;
determining whether the data is above a privacy threshold using a watchdog function;
directing the processor to further obfuscate the data if the data is above the privacy threshold;
wherein reducing the signal-to-noise ratio comprises at least one of down-sampling or pixel removal, and further comprising; and
wherein obfuscating the data using the privacy filter comprises reducing a signal-to-noise ratio.
11 . The method of claim 10 , wherein the camera is a video camera.
12 . The method of claim 11 , further comprising:
capturing video in real time using the video camera;
capturing environmental sounds using an audio detection device; and
evaluating the captured environmental sounds and the video using a rules engine.
13 . The method of claim 10 , further comprising filtering out background noise using the processor.
14 . The method of claim 12 , further comprising sending alerts to a mobile device or a cloud upon detecting a combination of pre-specified audio and video events.
15 . The method of claim 14 , further comprising analyzing audio and video events in real time using the processor and storing historical data for future analysis.
16 . The method of claim 12 , further comprising initiating video recording when a significant audible event is detected using the processor.