Video stabilization based on a 3D perspective camera model

Authors:
Guofeng Zhang;Wei Hua;Xueying Qin;Yuanlong Shao;Hujun Bao
Affiliations:
Zhejiang University, State Lab of CAD&CG, Zhejiang, People’’s Republic of China;Zhejiang University, State Lab of CAD&CG, Zhejiang, People’’s Republic of China;Zhejiang University, State Lab of CAD&CG, Zhejiang, People’’s Republic of China and Shandong University, School of Computer Science & Technology, Jinan, People’’s Repub ...;Zhejiang University, State Lab of CAD&CG, Zhejiang, People’’s Republic of China;Zhejiang University, State Lab of CAD&CG, Zhejiang, People’’s Republic of China
Venue:
The Visual Computer: International Journal of Computer Graphics
Year:
2009

Citing 0
Cited 4

Subspace video stabilization

ACM Transactions on Graphics (TOG)
Unsupervised learning for improving efficiency of dense three-dimensional scene recovery in corridor mapping

SCIA'11 Proceedings of the 17th Scandinavian conference on Image analysis
A hybrid method for video stabilization and retargeting

Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
An integrated new scheme for digital video stabilization

Advances in Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a novel approach to stabilize video sequences based on a 3D perspective camera model. Compared to previous methods which are based on simplified models, our stabilization system can work in situations where significant depth variations exist in the scenes and the camera undergoes large translational movement. We formulate the stabilization problem as a quadratic cost function on smoothness and similarity constraints. This allows us to precisely control the smoothness by solving a sparse linear system of equations. By taking advantage of the sparseness, our optimization process is very efficient. Instead of recovering dense depths, we use approximate geometry representation and analyze the resulting warping errors. We show that by appropriately constraining warping error, visually plausible results can be achieved even using planar structures. A variety of experiments have been implemented, which demonstrates the robustness and efficiency of our approach.