Fast block based local motion estimation for video stabilization

Today many people in the world without any (or with little) knowledge about video recording, thanks to the widespread use of mobile devices (PDAs, mobile phones, etc.) take videos. However the unwanted movements of their hands typically blur and introduce disturbing jerki-ness in the recorded sequences. Many video stabilization techniques have been hence developed with different performances but only fast strategies can be implemented on embedded devices. In this paper we propose a fast block matching local motion estimator for video stabilization purposes. Our contribution is twofold: the usage of gradient of integral projections (better performances in presence of illumination changes); complexity reduction through a series of optimizations based on mathematical inequalities. Experimental results confirm the effectiveness of the proposed approach.