Recovery Video Stabilization Using MRF-MAP Optimization

In this paper, we propose a novel approach for video stabilization using Markov random field (MRF) model-ing and maximum a posteriori (MAP) optimization. We build an MRF model describing a sequence of unsta-ble images and find joint pixel matchings over all im-age sequences with MAP optimization via Gibbs sam-pling. The resulting displacements of matched pixels in consecutive frames indicate the camera motion between frames and can be used to remove the camera motion to stabilize image sequences. The proposed method shows robust performance even when a scene has moving fore-ground objects and brings more accurate stabilization results. The performance of our algorithm is evaluated on outdoor scenes. 1