Fast motion estimation algorithm of video stabilization system

A real-time electronic image stabilization motion estimation method based on fast sub-block gray projection algorithm is proposed. In the method, each image is divided into a number of sub-blocks, and sub-blocks are sifted with their gray gradients. After removing sub-blocks whose gray gradients are lower than the given threshold, the calculation amount of projection is reduced and the motion estimation accuracy is improved. Then gray projection is done in each remained sub-block, and global motion vector of the image is calculated according to the local motion vectors of sub-blocks and the affine motion model. The drawbacks as the local motions reducing the global motion estimation accuracy and traditional gray projection algorithm could not deal with rotation are resolved well by this algorithm. The experiment results show that the algorithm is more accurate and efficient than the gray projection algorithm.