A Two-Stage Algorithm for Motion Discontinuity-Preserving Optical Flow Estimation

Abstract

This paper proposes a two-stage optical flow estimation algorithm for video sequences based on feature-based matching and module-fusion. In the first stage, the algorithm computes initial translation and rotation parameters using a relaxation scheme at feature points and object-oriented anisotropic propagation in continuous and discontinuous regions. In the second stage, iterative-improvement optical flow estimation based on the strongly coupled recurrent module-fusion and adaptive smoothing is introduced. Computer simulation results of the proposed and conventional algorithms are shown.