 We developed a real-time method for detecting and tracking moving objects from unmanned aerial vehicles, UAVs. This method uses a single camera to estimate the camera's motion between two consecutive frames, which is compared to the real optical flow directly calculated from the video feed. This comparison allows us to identify dynamic pixels and group them into dynamic objects. These objects are then tracked over time and space, allowing us to filter out false detections and misdetections. Our algorithm was tested on a quad-rotor platform using a commercial camera, demonstrating its effectiveness. This article was authored by Bruce McDonald, Antonio Barrientos, Jamie Del Cerro, and others.