Diver detection by motion-segmentation and shape-analysis from a moving vehicle

The operation of Autonomous Underwater Vehicles (AUV) in scenarios where also human divers are working, e.g., during archaeological missions or during inspection and service tasks, bears an interesting application potential. But according scenarios also require the detection of the divers for at least safety reasons. Diver detection is also of interest for other applications, e.g., within the context of harbor security scenarios. In this paper, an approach for diver detection with a monocular camera on a moving vehicle is presented. The main challenge is the motion compensation in the video stream, which is achieved here by a spectral registration method in form of the improved Fourier Mellin Invariant (iFMI) registration.