Digital Image Stabilization Based on Harmony Filter

A digital image stabilization algorithm based on a harmony filter is presented in this paper. The corner points are extracted from the reference image. A new motion estimation method based on diamond search (DS) and partial distortion elimination (PDE) algorithm is proposed in the feature block matching. The global motion parameters are obtained based on the affine transformation model and the least square solution. Then a new filter algorithm named harmony filter is adopted to smooth the global motion by separating the active scanning movement from random jitter of camera. Finally, the original jitter sequences are compensated by the correction vectors. Experimental results show that our method can eliminate the high frequency tremble, keep active motion of camera and realize real-time image stabilization.