Abstract: Introduced herein are techniques for improving media content production and consumption by utilizing metadata associated with the relevant media content. More specifically, systems and techniques are introduced herein for automatically producing media content (e.g., a video composition) using several inputs uploaded by a filming device (e.g., an unmanned aerial vehicle (UAV) copter or action camera), an operator device, and/or some other computing device. Some or all of these devices may include non-visual sensors that generate sensor data. Interesting segments of raw video recorded by the filming device can be formed into a video composition based on events detected within the non-visual sensor data that are indicative of interesting real world events. For example, substantial variations or significant absolute values in elevation, pressure, acceleration, etc., may be used to identify segments of raw video that are likely to be of interest to a viewer.

Abstract: Introduced herein are systems and techniques for automatically producing media content (e.g., a video composition) using several inputs uploaded by an unmanned aerial vehicle (UAV) copter, an operator device, and/or some other computing device. More specifically, production and modification techniques based on sensor-driven events are described herein that allow videos to be created on behalf of a user of the UAV copter. Interesting segments of raw video recorded by the UAV copter can be formed into a video composition based on sensor events that are indicative of interesting real world events. The sensors responsible for detecting the events may be connected to (or housed within) the UAV copter, the operator device, and/or some other computing device. Sensor measurements can also be used to modify the positioning, movement pattern, focus level/point, etc., of the UAV copter responsible for generating the raw video.