Audio sensors for controlling surveillance video data capture

1. A system, comprising:

a video camera configured for a plurality of video capture rates;

an audio sensor, wherein:

the audio sensor is configured to collect audio data from an audio field; and

the audio field is at least partially outside a field of view of the video camera; and

a controller configured to:

receive audio data from the audio sensor;

determine, from the audio data, an audio event;

select, responsive to the audio event, a first video capture rate from the plurality of video capture rates;

modify, responsive to the audio event, a video capture operation of the video camera using the first video capture rate during a first operating period; and

capture, using the video camera, video data based on the modified video capture operation.

2. The system of claim 1 , wherein the controller is further configured to select a second video capture rate from the plurality of video capture rates during a second operating period.

3. The system of claim 1 , wherein the controller is further configured to:

suspend video capture during a second operating period; and

initiate, responsive to the audio event, video capture at the first video capture rate to modify the video capture operation during the first operating period.

4. The system of claim 1 , wherein:

the audio event is associated with a video object of interest; and

the audio event precedes the video object being detectable in the field of view of the video camera.

5. The system of claim 1 , wherein:

the audio sensor comprises at least one directional microphone configured with a direction and an audio range to detect sound sources outside the field of view of the video camera; and

the controller is further configured to determine, based on the audio data, a direction of movement of a sound source that intercepts the field of view of the video camera.

6. The system of claim 5 , wherein the at least one directional microphone is configured as an audio tripwire for the sound source approaching the field of view of the video camera.

7. The system of claim 1 , further comprising:

an analytics engine configured to:

receive the audio data from the audio sensor;

determine, in the audio data, the audio event, wherein determining the audio event is based on:

an audio recognition value meeting an audio recognition threshold; and

an audio duration value meeting an audio duration threshold; and

return the audio event for use by the controller.

8. The system of claim 7 , wherein:

the analytics engine is further configured to use an audio recognition model to determine the audio recognition value;

the audio recognition model is configured to classify the audio data using at least one audio source type identifier; and

the controller is further configured to use the at least one audio source type identifier to determine a modification of the video capture operation of the video camera.

9. The system of claim 7 , wherein:

the analytics engine is further configured to use an audio recognition model to determine the audio recognition value;

the audio recognition model is configured to determine a location and a direction of movement of a sound source; and

the controller is further configured to send, responsive to the location and the direction of movement of the sound source, a pan-tilt-zoom position control signal to the video camera to adjust the field of view of the video camera.

10. The system of claim 7 , wherein:

the analytics engine is further configured to use an audio recognition model to determine the audio recognition value;

the audio recognition model is a machine learning model trained with audio reference data corresponding to known sound sources;

the controller is further configured to:

detect, using the video data, at least one data object in the field of view of the video camera; and

determine, based on correlations of the audio event and detecting at least one data object, additional audio reference data; and

the analytics engine is further configured to retrain the machine learning model using the additional audio reference data.

11. A computer-implemented method, comprising:

collecting, by an audio sensor, audio data from an audio field, wherein the audio field is at least partially outside a field of view of a video camera;

receiving the audio data from the audio sensor;

determining, based on the audio data, an audio recognition value;

determining, from the audio data, an audio event based on the audio recognition value meeting an audio recognition threshold;

modifying, responsive to the audio event, a video capture operation of the video camera; and

capturing, using the video camera, video data based on the modified video capture operation.

12. The computer-implemented method of claim 11 , further comprising:

selecting a first video capture rate from a plurality of video capture rates for the video camera during a first operating period; and

selecting, responsive to the audio event, a second video capture rate to modify the video capture operation during a second operating period.

13. The computer-implemented method of claim 11 , further comprising:

suspending video capture during a first operating period; and

initiating, responsive to the audio event, video capture at a selected video capture rate to modify the video capture operation during a second operating period.

14. The computer-implemented method of claim 11 , wherein:

the audio event is associated with a video object of interest; and

the audio event precedes the video object being detectable in the field of view of the video camera.

15. The computer-implemented method of claim 11 , further comprising:

determining, based on the audio data, a direction of movement of a sound source that intercepts the field of view of the video camera, wherein the audio sensor comprises at least one directional microphone configured with a direction and an audio range to detect sound sources outside the field of view of the video camera.

16. The computer-implemented method of claim 15 , further comprising configuring the at least one directional microphone as an audio tripwire for the sound source approaching the field of view of the video camera.

17. The computer-implemented method of claim 11 , further comprising:

determining the audio recognition value using an audio recognition model;

classifying, using the audio recognition model, the audio data using at least one audio source type identifier; and

determining, using the at least one audio source type identifier, a modification of the video capture operation of the video camera.

18. The computer-implemented method of claim 11 , further comprising:

determining the audio recognition value using an audio recognition model;

determining, using the audio recognition model, a location and a direction of movement of a sound source; and

adjusting, responsive to the location and the direction of movement of the sound source, the field of view of the video camera using a pan-tilt-zoom position control signal.

19. The computer-implemented method of claim 11 , further comprising:

determining the audio recognition value using an audio recognition model;

training, using a machine learning model and audio reference data corresponding to known sound sources, the audio recognition model;

detecting, using the video data, at least one data object in the field of view of the video camera;

determining, based on correlations of the audio event and detecting at least one data object, additional audio reference data; and

retraining, using the machine learning model and the additional audio reference data, the audio recognition model.

20. A storage system, comprising:

a video camera;

an audio sensor, wherein:

the audio sensor is configured to collect audio data from an audio field;

the audio field is at least partially outside a field of view of the video camera; and

the audio sensor comprises at least one directional microphone configured with a direction and an audio range to detect sound sources outside the field of view of the video camera;

a processor;

a memory;

means for collecting, by the audio sensor, audio data from the audio field;

means for determining, from the audio data, an audio event based on determining a direction of movement of a sound source that intercepts the field of view of the video camera;

means for modifying, responsive to the audio event, a video capture operation of the video camera; and

means for capturing, using the video camera, video data based on the modified video capture operation.