Methods and apparatus to operate a mobile camera for low-power usage

A mobile camera, comprising:

• a first state transitioner to transition the mobile camera from a motion feature detection state to an audio feature detection state in response to a motion feature in motion sensor data, a first power state of the motion feature detection state corresponding to lower power consumption than a second power state of the audio feature detection state;
• a second state transitioner to transition the mobile camera from the audio feature detection state to a low-resolution camera feature detection state in response to a first convolutional neural network recognizing an audio feature in audio data, the mobile camera to operate using higher power consumption in a third power state corresponding to the low-resolution camera feature detection state than in the second power state corresponding to the audio feature detection state;
• and
• a communications interface to send to an external device at least one of:
• (a) first metadata corresponding to the motion feature or the audio feature, or (b) second metadata corresponding to an image feature recognized in visual capture data by a second convolutional neural network when the mobile camera is in the low-resolution camera feature detection state.

An apparatus, comprising:

• first circuitry to transition a mobile camera from a motion feature detection state to an audio feature detection state in response to a motion feature in motion sensor data, a first power state of the motion feature detection state corresponding to lower power consumption than a second power state of the audio feature detection state;
• second circuitry to transition the mobile camera from the audio feature detection state to a first camera feature detection state in response to a first convolutional neural network recognizing an audio feature in audio data, the mobile camera to operate using higher power consumption in a third power state corresponding to the first camera feature detection state than in the second power state corresponding to the audio feature detection state;
• and
• communications circuitry to transmit at least one of:
• (a) first metadata corresponding to the motion feature or the audio feature, or (b) second metadata corresponding to an image feature recognized in visual capture data by a second convolutional neural network when the mobile camera is in the first camera feature detection state.

A non-transitory computer readable storage medium comprising instructions that, when executed, cause at least one processor to at least:

• transition a mobile camera from a motion feature detection state to an audio feature detection state in response to a motion feature in motion sensor data, a first power state of the motion feature detection state corresponding to lower power consumption than a second power state of the audio feature detection state;
• transition the mobile camera from the audio feature detection state to a low-resolution camera feature detection state in response to a first convolutional neural network recognizing an audio feature in audio data, the mobile camera to operate using higher power consumption in a third power state corresponding to the low-resolution camera feature detection state than in the second power state corresponding to the audio feature detection state;
• and
• send to an external device at least one of:
• (a) first metadata corresponding to the motion feature or the audio feature, or (b) second metadata corresponding to an image feature recognized in visual capture data by a second convolutional neural network when the mobile camera is in the low-resolution camera feature detection state.

A method to operate a mobile camera, the method comprising:

• transitioning the mobile camera from a motion feature detection state to an audio feature detection state in response to a motion feature in motion sensor data, a first power state of the motion feature detection state corresponding to lower power consumption than a second power state of the audio feature detection state;
• transitioning the mobile camera from the audio feature detection state to a low-resolution camera feature detection state in response to a first convolutional neural network recognizing an audio feature in audio data, the mobile camera to operate using higher power consumption in a third power state corresponding to the low-resolution camera feature detection state than in the second power state corresponding to the audio feature detection state;
• and
• sending to an external device at least one of:
• (a) first metadata corresponding to the motion feature or the audio feature, or (b) second metadata corresponding to an image feature recognized in visual capture data by a second convolutional neural network when the mobile camera is in the low-resolution camera feature detection state.