Using iFMI spectral registration for video stabilization and motion detection by an Unmanned Aerial Vehicle (UAV)

Unmanned Aerial Vehicles (UAV), especially in the form of Micro Aerial Vehicles (MAV) are useful tools for reconnaissance, surveillance, and general situation assessment in safety, security, and rescue missions. Many UAV have meanwhile good autonomous flight capabilities, especially by tracking pre-planned routes via GPS or for station-keeping. Here it is shown how the video stream from an UAV can be analyzed to automatically detect motion in the scene while the vehicle is moving itself. Concretely, it is shown how a spectral image registration method, the improved Fourier Mellin Invariant method (iFMI), can be used for video stabilization and motion segmentation. The method is first analyzed with scenes containing artificial markers for ground truth evaluation. Furthermore, results from aerial video data from a quadcopter platform are presented.