Weighted Feature Points Extraction based Video Stabilization
K. Madhavi1, B. Sreekanth Reddy2, Ch.Ganapathy Reddy3
1K.Madhavi, M.Tech Student, ECE Department, GNITS, Hyderabad, India.
2S.Satheesh, Asst. Professor, ECE Department, GNITS, Hyderabad, India.
3Ch.Ganapathy Reddy, Professor & HOD, ECE Department, GNITS, Hyderabad, India.
Manuscript received on September 05, 2013. | Revised Manuscript Received on September 23, 2013. | Manuscript published on September 20, 2013. | PP: 11-16 | Volume-1, Issue-10, September 2013. | Retrieval Number: J03070911013/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering & Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Camera global motion estimation is critical to the success of video stabilization. An extension of Video stabilization using principal component analysis (PCA) and scale invariant feature transform (SIFT) in particle filter framework is proposed. In the proposed method the feature points are collected from based on Speeded Up Robust Features (SURF). Random Samples Consensus (RANSAC) is used to remove local motion vectors and incorrect correspondences. A particle filter is used to estimate the weight of feature points, solving the issue of Different Depth of Field (DDOF) for feature points weighted least square (WLS) algorithm is applied in the global motion estimation. Finally, a Kalman filter estimates the intentional motion, and the unintentional motion is compensated to obtain stable video sequences. The algorithm has the characteristics of high precision and good robustness.
Keywords: particle filter, principal component analysis (PCA), scale invariant feature transform (SIFT), speeded up robust features (SURF).