Conference paper
Gyroscope Aided Video Stabilization Using Nonlinear Regression on Special Orthogonal Group
This paper presents a novel approach for gyroscope aided video stabilization. With the raw 3D rotational motion captured by a gyroscope, it is then smoothed through nonlinear regression directly on the Special Orthogonal Group. Instead of solving a variational problem, the regression problem is discretized with finite forward difference, which makes it an optimization problem on manifold.
We derive a quadratic approximation of the objective function using Lie algebra. To address the black border problem caused by smoothing, we model it as linear inequality constraints. The resulting quadratic programming problem can be efficiently solved. Experiments on synthetic data and real video sequences demonstrate that our method performs better than the compared method in terms of motion smoothing and video stabilization.
Language: | English |
---|---|
Publisher: | IEEE |
Year: | 2020 |
Pages: | 2707-2711 |
Proceedings: | 2020 IEEE International Conference on Acoustics, Speech, and Signal ProcessingIEEE International Conference on Acoustics, Speech and Signal Processing |
Series: | Proceedings of the Ieee International Conference on Acoustics, Speech, and Signal Processing |
ISBN: | 1509066314 , 1509066322 , 9781509066315 and 9781509066322 |
ISSN: | 2379190x and 15206149 |
Types: | Conference paper |
DOI: | 10.1109/ICASSP40776.2020.9054373 |
ORCIDs: | Hu, Xiao , Olesen, Daniel and Knudsen, Per |
Algebra Gyroscopes Lie algebra Lie algebras Linear programming Manifolds Quadratic programming Smoothing methods Video sequences black border problem gyroscope aided video stabilization gyroscopes image sequences motion smoothing nonlinear regression optimization problem quadratic programming quadratic programming problem raw 3D rotational motion regression analysis regression problem special orthogonal group variational problem video sequences video signal processing