Sonic sensing
A method for security and/or automation systems is described. In one embodiment, the method may include receiving image data associated with an area via an image sensor, receiving sound data associated with an object via an audio sensor, analyzing the image data in relation to the sound data, detecting an object's presence based at least in part on the analyzing, and identifying at least one characteristic relating to the object based at least in part on the detecting.
1. A method for security and/or automation systems at a premises, comprising:
receiving image data associated with an area of the premises via an image sensor located at the premises;
determining that the image data includes a partial image of an object;
receiving sound data associated with the object via an audio sensor located at the premises;
analyzing the sound data to determine a detected sound;
analyzing the image data in relation to the sound data;
estimating a size of the object based at least in part on a type of sound indicated by the sound data and analyzing the image data in relation to the sound data;
estimating a distance from the audio sensor to the detected sound based at least on the analysis of the sound data;
determining whether the estimated distance satisfies a distance threshold; and
adjusting a field of view and a focus of the image sensor based at least in part on the estimated size of the object, the partial image of the object, and whether the estimated distance satisfies the distance threshold.
2. The method of claim 1 , further comprising:
detecting a presence of the object within the area based at least in part on an analysis of the image data.
3. The method of claim 1 , further comprising:
determining whether the estimated distance satisfies a size threshold, wherein adjusting the field of view and the focus of the image sensor is further based at least in part on the whether the estimated distance satisfies the size threshold.
4. The method of claim 1 , further comprising:
detecting a sound within the sound data, wherein the detected sound includes one of a footstep, a voice, a horn of a vehicle, an engine of the vehicle, a knocking on a door, a ringing of a doorbell, an opening of the door, a rustling of clothing, a gunshot, a glass breaking, a rattling of keys, or a combination thereof.
5. The method of claim 4 , further comprising:
determining the type of sound based at least in part on detecting the sound within the sound data; and
estimating a distance from the audio sensor to the detected sound based at least in part on determining the type of sound.
6. The method of claim 5 , wherein estimating the size of the object further comprises:
estimating the size of the object relative to the field of view of the image sensor based at least in part on at least one of the estimated distance and the type of sound.
7. The method of claim 1 , further comprising:
capturing image data of the area after adjusting the field of view of the image sensor.
8. The method of claim 1 , further comprising:
analyzing the sound data to determine a detected sound; and
estimating a location of the detected sound.
9. The method of claim 8 , further comprising:
tracking a source of the detected sound based at least in part on a subsequent detected sound.
10. An apparatus for an automation system, comprising:
a processor;
memory in electronic communication with the processor; and
instructions stored in the memory, the instructions being executable by the processor to:
receive image data associated with an area of a premises via an image sensor located at the premises;
determine that the image data includes a partial image of an object;
receive sound data associated with the object via an audio sensor located at the premises;
analyze the sound data to determine a detected sound;
analyze the image data in relation to the sound data;
estimate a size of the object based at least in part on a type of sound indicated by the sound data and analyzing the image data in relation to the sound data;
estimate a distance from the audio sensor to the detected sound based at least on the analysis of the sound data;
determine whether the estimated distance satisfies a distance threshold; and
adjust a field of view and a focus of the image sensor based at least in part on the estimated size of the object, the partial image of the object, and whether the estimated distance satisfies a distance threshold.
11. The apparatus of claim 10 , the instructions being further executable by the processor to:
detect a presence of the object within the area based at least in part on an analysis of the image data.
12. The apparatus of claim 10 , the instructions being further executable by the processor to:
determine whether the estimated distance satisfies a size threshold, wherein adjusting the field of view and the focus of the image sensor is further based at least in part on the whether the estimated distance satisfies the size threshold.
13. The apparatus of claim 10 , the instructions being further executable by the processor to:
identify a false positive associated with a presence of the object within the area based at least in part on analyzing the image data and analyzing the sound data; and
determine whether to generate a notification based at least in part on analyzing the sound data, the identified false positive, and the presence of the object within the area.
14. A non-transitory computer-readable medium storing computer-executable code for an automation system, the code executable by a processor to:
receive image data associated with an area of a premises via an image sensor located at the premises;
determine that the image data includes a partial image of an object;
receive sound data associated with the object via an audio sensor located at the premises;
analyze the sound data to determine a detected sound;
analyze the image data in relation to the sound data;
estimate a size of the object based at least in part on a type of sound indicated by the sound data and analyzing the image data in relation to the sound data;
estimate a distance from the audio sensor to the detected sound based at least on the analysis of the sound data;
determine whether the estimated distance satisfies a distance threshold; and
adjust a field of view and a focus of the image sensor based at least in part on the estimated size of the object, the partial image of the object, and whether the estimated distance satisfies the distance threshold.
15. The method of claim 1 , further comprising:
identifying a false positive associated with a presence of the object within the area based at least in part on analyzing the image data and analyzing the sound data; and
determining whether to generate a notification based at least in part on analyzing the sound data, the identified false positive, and the presence of the object within the area.