Mohammad Javad Tanakian - Faculty of Electrical & Computer Engineering, University of Sistan and Baluchestan
Mehdi Rezaei۲, - Faculty of Electrical & Computer Engineering, University of Sistan and Baluchestan
Farahnaz Mohanna۳ - Faculty of Electrical & Computer Engineering, University of Sistan and Baluchestan

Digital video stabilization (DVS) allows acquiring video sequences without disturbing jerkiness, removing unwanted camera movements. In this paper, we propose a novel DVS algorithm that adaptively compensates the camera jitters utilizing an adaptive fuzzy filter on the global motion of video frames. The adaptive fuzzy filter is a Kalman filter which is tuned adaptively by a fuzzy system. The fuzzy system is also tuned adaptively during operation according to the characteristics of camera jitters. The global motion of video frames is estimated based on the block motion vectors which are resulted by video encoder during motion estimation operation. The proposed method also utilizes an adaptive criterion for validation of motion vectors. Experimental results have been indicated a good performance for the proposed DVS algorithm.

adaptive, digital video stabilization, fuzzy filter, motion estimation, motion vector, video coding, Kalman filter