Affiliations: Faculty of Electrical & Computer Engineering, University of Sistan and Baluchestan, Daneshgah Blvd, Zahedan, Iran
Correspondence:
[*]
Corresponding author. Mehdi Rezaei, Faculty of Electrical & Computer Engineering, University of Sistan and Baluchestan, Zahedan, Iran. Tel.: +98 543116546, Fax: +98 5433447908, mehdi.rezaei@ece.usb.ac.ir
Abstract: Digital video stabilization (DVS) allows acquiring video sequences without disturbing jerkiness, removing unwanted camera movements. A good DVS should remove the unwanted camera movements while maintains the intentional camera movements. In this article, we propose a novel real-time DVS algorithm with a short-delay. The proposed DVS compensates the camera jitters applying an adaptive fuzzy filter on the global motion of video frames. The adaptive filter is an infinite impulse response (IIR) non-causal filter which is tuned by a fuzzy system adaptively to the camera motion characteristics. The fuzzy system itself is also tuned during operation according to the amount of camera jitters. The fuzzy system uses two inputs which are quantitative representations of the unwanted and the intentional camera movements. The global motion of video frames is estimated based on the block motion vectors which resulted by video encoder during motion estimation operation. Experimental results indicate a good performance for the proposed algorithm.
Keywords: Adaptive, delay, digital video stabilization, fuzzy filter, motion vector, video coding, numerical assessment
