A video stabilization method based on sub-block gray projection

A video stabilization method based on sub-block gray projection algorithm is proposed. Firstly, each image is divided into sub-blocks which are filtered according to their gray gradients. After the sub-blocks of which gray gradients are lower than a threshold are removed, the calculation amount of projection is reduced and the motion estimation accuracy is improved. Then gray projection is done in the remained sub-blocks, and the global motion vector is calculated according to the local motion vectors and the interframe motion model. Finally, the trembling image is compensated to stabilize the image sequence according to motion compensating vector. The problems of that the global motion estimation accuracy is reduced by the local motion and the rotation motion of camera could not be estimated by traditional gray projection algorithm are effectively resolved by the sub-block gray projection algorithm. The experiment results show that the algorithm is more accurate and efficient than the traditional gray projection algorithm.