Electronic Image Stabilization Alogrithm Based on Adaptive Motion Filter

An electronic image stabilization algorithm is proposed based on improved Sage-Husa adaptive visual smoothing. It uses visual attention features to smooth inter-frame global motions, thus resulting in stabilized sequences. Firstly, corners are detected from reference frame as feature points. Through matching features in current frame, deleting mismatched points and solving motion equations, global motion vectors are generated. Then Sage-Husa adaptive filtering method is described in detail, which corrects the process and observation noise by estimating their statistical property in real time. So, it can improve the filter accuracy greatly and remove camera jitter but retain camera scan simultaneously. Finally each current frame is warped by fast motion compensation in consideration of the linear storage of the image. The experimental results illustrate that the proposed algorithm can stabilize the inter-frame jitter and track the real scene with smooth vision.