Fast and robust photomapping with an Unmanned Aerial Vehicle (UAV)

— A fast and robust method for visual odometry based on the Fourier-Mellin Invariant (FMI) descriptor is presented. It extends previous FMI based approaches in two ways. First, a logarithmic representation of the spectral magnitude of the FMI descriptor is used. Second, a filter on the frequency where the shift is supposed to appear is applied. It is shown with experiments with an Unmanned Aerial Vehicle that this improved Fourier-Mellin Invariant (iFMI) method is is indeed an advancement and well suited for online visual odometry to generate large photo maps.

• Type: Conference
• Year: 2009
• Where: IROS
• Authors: Heikow Bülow, Andreas Birk
• Keywords: FMI Based Approaches, FMI Descriptor, IROS 2009, Robotics, Visual Odometry