Unmanned Aerial Vehicles (UAV) are finding their way to a wide range of safety-critical missions. Our collaborative research team of computer scientists and aerospace engineers has worked on developing hardware and software of UAV. One of vital components in software used in UAV is image stabilization. The constantly-shaking images taken from the UAV, resulted from the vehicle's motion, need to be stabilized to perform its mission. In this paper, we present our implementation of image stabilization software. Our research is focused on using state-of-the-art Graphic Processing Unit (GPU) to improve the performance of the image stabilization software. The stabilizer estimates motion of the vehicle by calculating optical flow between successive two frames. In this study, we parallelized the calculation of the optical flow, which is identified as a computational bottleneck of the entire image stabilization process. Using the massive parallelism of NVIDIA C2060 GPU with 448 cores, we could improve the overall performance of image stabilizer.