Imaging controls for unmanned aerial vehicles

A system comprising one or more computers and one or more storage devices on which are stored instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:

• determining whether an object indicates a boundary between a first region that is being surveilled by a drone and a second region that does not need to be surveilled, both of a physical area;
• in response to detecting that the object indicates a boundary between the first region and the second region, determining a plurality of candidate viewing angles of a camera included in the drone;
• using the plurality of candidate viewing angles, dynamically computing, for the camera, one or more frame coverages of the physical area;
• identifying, for at least one of the one or more computed frame coverages for the camera, a predicted section of the physical area that would be depicted in an image using the corresponding computed frame coverage;
• determining an adjustment to an angle at which the drone performs surveillance of the physical area using the one or more computed frame coverages, the predicted section of the physical area, and data that identifies the first region that is being surveilled;
• generating, based on the adjustment to the angle, control signals that cause the drone to exclude the second region from the physical area being surveilled by the drone;
• and
• providing, to the drone, the control signals to cause the drone to exclude the second region from the physical area being surveilled.

One or more non-transitory computer storage media encoded with instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:

• determining whether an object indicates a boundary between a first region that is being surveilled by a drone and a second region that does not need to be surveilled, both of a physical area;
• in response to detecting that the object indicates a boundary between the first region and the second region, determining a plurality of candidate viewing angles of a camera included in the drone;
• using the plurality of candidate viewing angles, dynamically computing, for the camera, one or more frame coverages of the physical area;
• identifying, for at least one of the one or more computed frame coverages for the camera, a predicted section of the physical area that would be depicted in an image using the corresponding computed frame coverage;
• determining an adjustment to an angle at which the drone performs surveillance of the physical area using the one or more computed frame coverages, the predicted section of the physical area, and data that identifies the first region that is being surveilled;
• generating, based on the adjustment to the angle, control signals that cause the drone to exclude the second region from the physical area being surveilled by the drone;
• and
• providing, to the drone, the control signals to cause the drone to exclude the second region form the physical area being surveilled.