In this paper, we study various video stabilization techniques and develop an algorithm which can perform video stabilization under strict time constraints. To do this, an optimized version of block matching in a restricted search space is utilized to minimize the use of computational resources. We also develop an experimental setup to do real-time video stabilization under various vibrating conditions. In this study, we have also compared our algorithm with an existing stabilization algorithm and looked at how the two techniques perform under different circumstances. © 2017 IEEE.