Feature point classification based global motion estimation for video stabilization

The performance of video stabilization is dependent on the accuracy of global motion estimation between two successive frames. In this paper, we propose a novel method to estimate the global motion accurately using the classified background (BG) feature points (FPs). In the proposed method, global motion estimation and FP classification are jointly performed using both the FP correspondences and the global motion parameters of the previous frame. The experimental results show that video stabilization using the proposed method outperforms the conventional stabilization methods, especially when the moving foreground (FG) objects occupy a large part of the image.