Video Stabilization Using Scale-Invariant Features

Authors:
Rong Hu;Rongjie Shi;I-fan Shen;Wenbin Chen
Affiliations:
Fudan University;Fudan University;Fudan University;Fudan University
Venue:
IV '07 Proceedings of the 11th International Conference Information Visualization
Year:
2007

Citing 0
Cited 7

Dynamic Selection of Characteristics for Feature Based Image Sequence Stabilization

ACIVS '08 Proceedings of the 10th International Conference on Advanced Concepts for Intelligent Vision Systems
Automatic Feature-Based Stabilization of Video with Intentional Motion through a Particle Filter

ACIVS '08 Proceedings of the 10th International Conference on Advanced Concepts for Intelligent Vision Systems
A New Global Alignment Method for Feature Based Image Mosaicing

ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing, Part II
Robust video stabilization to outlier motion using adaptive RANSAC

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Digital image stabilization for humanoid eyes inspired by human VOR system

ROBIO'09 Proceedings of the 2009 international conference on Robotics and biomimetics
A robust global motion estimation for digital video stabilization

AI'12 Proceedings of the 25th Australasian joint conference on Advances in Artificial Intelligence
Lagrangian based mathematical modeling and experimental validation of a planar stabilized platform for mobile systems

Journal of Computational and Applied Mathematics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Video Stabilization is one of those important video processing techniques to remove the unwanted camera vibration in a video sequence. In this paper, we present a practical method to remove the annoying shaky motion and reconstruct a stabilized video sequence with good visual quality. Here, the scale invariant(SIFT) features, proved to be invariant to image scale and rotation, is applied to estimate the camera motion. The unwanted vibrations are separated from the intentional camera motion with the combination of Gaussian kernel filtering and parabolic fitting. It is demonstrated that our method effectively removes the high frequency "noise' motion, but also minimize the missing area as much as possible. To reconstruct the undefined areas, resulting from motion compensation, we adopt the mosaicing method with Dynamic Programming . The proposed method has been confirmed to be effective over a widely variety of videos.