Object-centered Fourier Motion Estimation and Segment-Transformation Prediction
The ability to anticipate the future is essential for ac-tion planning in autonomous systems. To this end, learning video pre-diction methods have been developed, but current systems often pro-duce blurred predictions. We address this issue by introducing an object-centered movement estimation, frame prediction, and correction frame-work using frequency-domain approaches. We transform single objectsbased on estimated translation and rotation speeds which we correct us-ing a learned encoding of the past. This results in clear predictions withfew parameters. Experimental evaluation shows that our approach is accurate and efficient.
PDF