Gesture-recognition as basis for a human robot interface (HRI) on a AUV

An approach for gesture detection with a monocular camera on a moving vehicle is presented in this paper. The work consists of two parts. The first part deals with the video image processing. The main challenge here is the compensation of the ego-motion of the vehicle by image registration, which is required to facilitate the subsequent segmentation of relevant motions of the gestures. This is done with a spectral registration method, which proves to be useful for underwater scenarios. The second part deals with the recognition of gestures using motion trajectories. State machines where the different states are associated with the directions of movements are used for this purpose.