Abstract
In this paper a solution is proposed for stabilizing the target in un-stabilized shaky videos by using the motion vector compensation technique mainly focusing on template-based approach for locating target in desired frames. Frames are extracted from the input video and are formatted for further processing. Noise filtration is then done to neutralize the affects of inherent noise in the input video. Dimensions and other parameters are extracted from the input frames and the target is then selected. The target is matched in successive frames using cross correlation matching. Center positions are then updated which are later used for motion vector calculation and offset updating. Finally, the effects of un-necessary target and camera movements are removed by linear translations. Modified frames are then sequentially stacked for video reconstruction and display. The proposed algorithm is useful in security applications and in research works like astrological studies and the study of heavenly bodies.