Digital video stabilization based on hybrid filtering

The algorithm based on SIFT feature matching and Kalman filter has been used for digital video stabilization, it is efficient in many applications. However, video obtained by the method is still not stable. An improved scheme in motion filtering is proposed in this paper. The scheme is that global motion vector estimated by Kalman filter is filtered by an ideal low-pass filter with the Hanning window, here the process is called hybrid filtering. For the jitter video, the global motion vector obtained by SIFT feature matching with RANSAC is filtered by the hybrid filtering, and then the video image is compensated, finally, the stable video image sequence is obtained. The experimental results show that the method can eliminate jitter component more effective than one that only use SIFT feature matching and Kalman filter. The stable video image sequence will be obtained.