Digital Image Stabilization Using a Functional Neural Fuzzy Network
This study proposed a real-time video stabilization method to eliminate the unwanted shakes, preserve the intended panning of camera, and improve the stability of the captured video sequence. The proposed method uses a functional neuro-fuzzy network to learn the phenomena of different shakes and then it chooses adequate compensation weight for two different methods to calculate the compensated motion vector. Experimental results show that the proposed method has superior performance than other motion compensation methods.
KeywordsMotion Vector Current Frame Motion Compensation Smoothness Index Video Stabilization
Unable to display preview. Download preview PDF.
- 1.Chen, C.H., Kuo, Y.L., Chen, T.Y., Chen, J.R.: Real-time video stabilization based on motion compensation. In: Fourth Inter. Conf. on Innovative Computing, Information and Control, pp. 1495–1498 (2009)Google Scholar
- 5.Yang, J., Schonfeld, D., Mohamed, M.: Robust video stabilization based on particle filter tracking of projected camera motion. IEEE Trans. on Circuits and Systems for Video Technology 19(7) (July 2009)Google Scholar
- 9.Lin, C.J., Liu, Y.C., Lee, C.Y.: An efficient neural fuzzy network based on immune particle swarm optimization for prediction and control applications. Int. Journal of Innovative Computing, Information and Control 4(7), 1711–1721 (2008)Google Scholar