A Motion Edge Extraction Method under the Condition of Camera Swing

Xiao Qing Wu; Xiang  Long; Xiong Yang

doi:10.4028/www.scientific.net/AMM.513-517.3878

Paper Titles

Improving Workflow Management System Implementation with Workflow Localization Method
p.3859

Monitoring on Mode Selection for Technology Transfer Based on Regional Sustainable Development
p.3864

Parametric Foot Trajectory Planning for a Hexapod Robot
p.3868

Comparing Study on Approaches of Identifying Indicators' Benchmark for Sustainable Development
p.3874

A Motion Edge Extraction Method under the Condition of Camera Swing
p.3878

A Correction Method for Non-Vertical View Angle Three-Dimensional Display
p.3882

Experiment and Analysis System without Modulation Locked Fiber Grating System
p.3886

A Novel Method to Automatically Generate Depth Maps Based on Trace Points
p.3890

The Application of Fuzzy PID Controller in Wrecker Uprighting System
p.3895

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 513-517A Motion Edge Extraction Method under the...

A Motion Edge Extraction Method under the Condition of Camera Swing

Abstract:

Motion edge extraction is the object of most motion segmentation methods. We have proposed a motion edge extraction method in our previous work. However, if the camera swings, a number of background edges are classified into foreground edges. In order to solve this problem, we propose a background pixel relating method to modify the motion model and to remove those misclassified edges. At the end of this paper, we use the CAVIAR project test sequence to test our method. The result is satisfactory.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 513-517)

Pages:

3878-3881

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.513-517.3878

Citation:

Cite this paper

Online since:

February 2014

Authors:

Xiao Qing Wu*, Xiang Long, Xiong Yang

Keywords:

Background Pixel Relating, Canny Operator, Motion Edge Extraction, Motion Model, Motion Vector

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] D. Cremers and S. Soatto, Motion competition: A variational approach to piecewise parametric motion segmentation, International Journal of Computer Vision, vol. 62, no. 3, p.249–265, May (2005).

DOI: 10.1007/s11263-005-4882-4

Google Scholar

[2] H. Shen, L. Zhang, B. Huang, and P. Li, A map approach for joint motion estimation, segmentation, and super resolution, IEEE Transactions on Image Processing, vol. 16, no. 2, p.479–490, (2007).

DOI: 10.1109/tip.2006.888334

Google Scholar

[3] J. Zhang, F. Shi, J. Wang, and Y. Liu, 3d motion segmentation from straight-line optical flow, in Multimedia Content Analysis and Mining, 2007, p.85–94.

DOI: 10.1007/978-3-540-73417-8_15

Google Scholar

[4] Long Xiang，Wu Xiaoqing，Yang Xiong, Remaining edges linking method of motion segmentation based on edge detection. Proceedings of 9th International Conference on Fuzzy System and Knowledge Discovery (FSKD 2012). Vol. 4, p.1909-(1914).

DOI: 10.1109/fskd.2012.6233808

Google Scholar

[5] B. K. P. Horn and B. Schunck, Determining optical flow: A retrospective, Artif. Intell. 59, 1993, 81–87.

Google Scholar

[6] M. Proesmans, L. Van Gool, E. Pauwels, and A. Oosterlinck, Determination of optical flow and its discontinuities using non-linear diffusion, in 3rd European Conference on Computer Vision, ECCV'94, 1994, Vol. 2, p.295–304.

DOI: 10.1007/bfb0028362

Google Scholar