Probabilistic Optical Flow Estimation for Large Pixel Displacements Utilizing Egomotion Flow Compensation

The pixel movements in an image sequence grabbed by a camera that is mounted on a mobile platform comprise the superposition of several mo- tion components. These motion components are caused by the egomotion of the camera and by the different movements of the objects seen by the cam- era. Utilizing sensory information from a calibrated stereo rig and egomotion measurements of the mobile platform we develop a probabilistic framework that estimates optical flow relative to the visual flow induced by the egomo- tion. Despite rapid egomotion changes and a large range of pixel movements the proposed Dynamic Bayesian Network allows to infer the optical flow in- duced by moving objects. This is used to segregate moving individuals from static background while the stereo rig is moving. We present optical flow and figure-background segmentation results by applying this general frame- work to image sequences captured by the humanoid robot ASIMO while he is walking and observing moving people