In this paper a new video stabilization algorithm for unmanned aerial vehicles (UAV) has been presented which is used to stabilize the video being transmitted from UAV to the ground station. First, the corner points are extracted using Good Features to Track corner detection algorithm and the extracted points are used to compute the optical flow between two consecutive frames. Next, the points detected from optical flow are used to estimate the motion parameters using an affine transform model. Subsequently, a hybrid filter consisting of Kalman and low pass filter is used to smooth the estimated motion parameters and the frames are warped using the smoothed parameters to obtain a stabilized video sequence. The experimental results show that the algorithm can remove the unwanted vibration more effectively than the one that only uses either a Kalman Filter or a low pass filter.
Kejriwal, L., & Singh, I. (2016). A Hybrid Filtering Approach of Digital Video Stabilization for UAV Using Kalman and Low Pass Filter. In Procedia Computer Science (Vol. 93, pp. 359–366). Elsevier B.V. https://doi.org/10.1016/j.procs.2016.07.221