Abstract:In this paper a new video stabilization technique is proposed based on the Hilbert Huang Transform (HHT). HHT is a Decomposes the video into Intrinsic Mode Functions (IMFs). The proposed video stabilizer deals with vertical or horizontal displacements meaning that translational motions are corrected. First, LMVs from a certain image region of the sequence are defined by applying a motion estimation algorithm. Second, the resulting signal is separated into a finite number of IMFs through the process of EMD. The proposed HHTbased DIS method can be beneficial in a variety of applications including handheld cameras and mobile phones as a post-processing method, as well as for stabilizing image sequences acquired from cameras mounted on vehicles.
Keywords: Video Stabilization, Motion Estimation, HHT, IMFS, SSIM
[1]. C. Caraffi, S. Cattani, and P. Grisleri, "Off-road path and obstacle detection using decision networks and stereo vision," IEEE
Trans. Intell. Transp. Syst., vol. 8, no. 4, pp. 607–618, Dec. 2007.
[2]. A. A. Amanatiadis and I. Andreadis, "Digital image stabilization by independent component analysis," IEEE Trans. Instrum. Meas.,
vol. 59, no. 7,pp. 1755–1763, Jul. 2010.
[3]. A. Bosco, A. Bruna, S. Battiato, G. Bella, and G. Puglisi, "Digital video stabilization through curve warping techniques," IEEE
Trans. Consum. Electron., vol. 54, no. 2, pp. 220–224, May 2008.
[4]. A.-O. Boudraa and J.C. Cexus, "EMD-based signal filtering," IEEE Trans. Instrum. Meas., vol. 56, no. 6, pp. 2196–2202, Dec.
2007.
[5]. S. Battiato, A. R. Bruna, and G. Puglisi, "A robust block based image/video registration approach for mobile imaging d evices,"
IEEE Trans. Multimedia, vol. 12, no. 7, pp. 622–635, Nov. 2010.