Electronic image stabilization still exists some problems, such as high time-consuming，low accuracy, high eror matching probability and so on. The paper takes appropriate measures to solove these problems from two aspects: feature points extraction and matching. Firstly, the FAST algorithm is adpoted to extracte the feature points, and positional precision of the feature points is improved to the level of sub-pixel. Then the RANSAC algorithm is used to eliminate the error matched points, avoid the interference of relative movement, and the global motion parameters calculated is more accurate. Experimental results show that a more higher precision and faster speed is obtained, which can also be applied for the complex shaking video containing translation, rotation shake and relative movement.