DocumentCode
3301851
Title
Notice of Violation of IEEE Publication Principles
Video Stabilization by Sparse and Low-Rank Matrix Decomposition
Author
Bo Gao ; Ziming Kou ; Zemin Jing
Author_Institution
Coll. of Mech. Eng., TaiYuan Univ. of Technol., Taiyuan, China
fYear
2011
fDate
19-21 May 2011
Firstpage
1
Lastpage
5
Abstract
Notice of Violation of IEEE Publication Principles
"Video Stabilization By Sparse and Low-rank Matrix Decomposition"
by Bo Gao, Ziming Kou, Zemin Jing
in the Proceedings of the 2011 International Conference on Computer and Management, May 2011, pp. 1-5
After careful and considered review of the content and authorship of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE\´s Publication Principles.
This paper contains substantial duplication of original text from the papers cited below. The original text was copied without attribution (including appropriate references to the original authors and/or paper titles) and without permission.
Due to the nature of this violation, reasonable effort should be made to remove all past references to this paper, and future references should be made to the following articles:
"RASL: Robust Alignment by Sparse and Low-rank Decomposition for Linearly Correlated Images"
by Yigang Peng, Arvind Ganesh, John Wright, Wenli Xu and Yi Ma
in the Proceedings of the 23rd IEEE Conference on Computer Vision and Pattern Recognition, June 2010, pp. 763–770
"Video Stabilization Based on a 3D Perspective Camera Model"
by Guofeng Zhang, Wei Hua, Xueying Qin, Yuanlong Shao, Hujun Bao
in The Visual Computer, Volume 25, Number 11, November 2009, pp. 997-1008
This paper presents a novel approach to stabilize video sequences based on low-rank matrix decomposition. 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 stabilized frames as a low-rank matrix. This allows us to precisely control the smoothness by decomposing low-rank matrix. By taking advantage of the sparseness, our optimization process is very efficient. Instead of recovering dens- depths, we use approximate geometry representation and analyse the resulting warping errors. We show that by appropriately constraint 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.
"Video Stabilization By Sparse and Low-rank Matrix Decomposition"
by Bo Gao, Ziming Kou, Zemin Jing
in the Proceedings of the 2011 International Conference on Computer and Management, May 2011, pp. 1-5
After careful and considered review of the content and authorship of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE\´s Publication Principles.
This paper contains substantial duplication of original text from the papers cited below. The original text was copied without attribution (including appropriate references to the original authors and/or paper titles) and without permission.
Due to the nature of this violation, reasonable effort should be made to remove all past references to this paper, and future references should be made to the following articles:
"RASL: Robust Alignment by Sparse and Low-rank Decomposition for Linearly Correlated Images"
by Yigang Peng, Arvind Ganesh, John Wright, Wenli Xu and Yi Ma
in the Proceedings of the 23rd IEEE Conference on Computer Vision and Pattern Recognition, June 2010, pp. 763–770
"Video Stabilization Based on a 3D Perspective Camera Model"
by Guofeng Zhang, Wei Hua, Xueying Qin, Yuanlong Shao, Hujun Bao
in The Visual Computer, Volume 25, Number 11, November 2009, pp. 997-1008
This paper presents a novel approach to stabilize video sequences based on low-rank matrix decomposition. 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 stabilized frames as a low-rank matrix. This allows us to precisely control the smoothness by decomposing low-rank matrix. By taking advantage of the sparseness, our optimization process is very efficient. Instead of recovering dens- depths, we use approximate geometry representation and analyse the resulting warping errors. We show that by appropriately constraint 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.
Keywords
image motion analysis; image representation; image sequences; matrix decomposition; optimisation; sparse matrices; stability; video signal processing; approximate geometry representation; camera; dense depth recovery; low-rank matrix decomposition; optimization; planar structure; sparse matrix decomposition; translational movement; video sequence stabilization; warping errors; Cameras; Convergence; Geometry; Matrix decomposition; Notice of Violation; Three dimensional displays; Transmission line matrix methods; Video sequences;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer and Management (CAMAN), 2011 International Conference on
Conference_Location
Wuhan
Print_ISBN
978-1-4244-9282-4
Type
conf
DOI
10.1109/CAMAN.2011.5778768
Filename
5778768
Link To Document