Remoteless control of drone behavior
AssigneeSnap Inc.
InventorsDavid Meisenholder, Steven Horowitz
Life of this patent
Estimating the term…
Abstract
A drone system is configured to capture an audio stream that includes voice commands from an operator, to process the audio stream for identification of the voice commands, and to perform operations based on the identified voice commands. The drone system can identify a particular voice stream in the audio stream as an operator voice, and perform the command recognition with respect to the operator voice to the exclusion of other voice streams present in the audio stream. The drone can include a directional camera that is automatically and continuously focused on the operator to capture a video stream usable in disambiguation of different voice streams captured by the drone.
Claims19
A method of operating an aerial drone having an onboard camera system, the method comprising:
- via the onboard camera system, capturing a video stream of a scene that includes a human target subject;
- performing automated facial recognition on the video stream to identify one or more facial features of the human target subject;
- responsive to an operator command to capture an image of the scene, continuously monitoring a condition of one or more recognized facial features of the human target subject to determine satisfaction of one or more predefined image capture criteria by the one or more facial features of the human target subject;
- responsive to determining that the one or facial features fails to satisfy the one or more image capture criteria, delaying image capture until the monitored facial feature condition satisfies the one or more image capture criteria;
- and
- responsive to determining that the monitored condition of the one or more facial features satisfies the one or more predefined image capture criteria, automatically capturing a photographic image of the scene, thus providing autonomous timing of image capture based on the monitored facial feature condition of the target human subject.
A personal aerial drone comprising:
- a drone body carrying flight systems for controlled flight of the drone;
- an onboard camera system carried by the drone body;
- a controller comprising one or more computer processor devices configured to perform operations comprising:
- via the onboard camera system, capturing a video stream of a scene that includes a human target subject;
- performing automated facial recognition on the video stream to identify one or more facial features of the human target subject;
- responsive to an operator command to capture an image of the scene, continuously monitoring a condition of one or more recognized facial features of the human target subject to determine satisfaction of one or more predefined image capture criteria by the one or more facial features of the human target subject;
- responsive to determining that the one or facial features fails to satisfy the one or more image capture criteria, delaying image capture until the monitored facial feature condition satisfies the one or more image capture criteria;
- and
- responsive to determining that the monitored condition of the one or more facial features satisfies the one or more predefined image capture criteria, automatically capturing a photographic image of the scene, thus providing autonomous timing of image capture based on the monitored facial feature condition of the target human subject.
A non-transitory machine-readable storage medium having stored thereon instructions that cause one or more computer processor devices, when executing the instructions, to perform operations comprising:
- at an aerial drone having an onboard camera system, capturing a video stream of a scene that includes a human target subject;
- performing automated facial recognition on the video stream to identify one or more facial features of the human target subject;
- responsive to an operator command to capture an image of the scene, continuously monitoring a condition of one or more recognized facial features of the human target subject to determine satisfaction of one or more predefined image capture criteria by the one or more facial features of the human target subject;
- responsive to determining that the one or facial features fails to satisfy the one or more image capture criteria, delaying image capture until the monitored facial feature condition satisfies the one or more image capture criteria;
- and
- responsive to determining that the monitored condition of the one or more facial features satisfies the one or more predefined image capture criteria, automatically capturing a photographic image of the scene, thus providing autonomous timing of image capture based on the monitored facial feature condition of the target human subject.
Dependencies are inferred from the claim text.