Real-Time Video Stabilization Based on Smoothing Feature Trajectories

Abstract:

In this paper, a real-time video stabilization algorithm based on smoothing feature trajectories is proposed. For each input frame, our approach generates multiple feature trajectories by performing inter-frame template match and optical flow. A Kalman filter is then performed to smooth these feature trajectories. Finally, at the stage of image composition, the motion consistency of the feature trajectory is considered for achieving a visually plausible stabilized video. The proposed method can offer real-time video stabilization and its removed the delays for caching coming images. Experiments show that our approach can offer real-time stabilizing for videos with various complicated scenes.

• Periodical: Applied Mechanics and Materials (Volumes 519-520)
• Pages: 640-643
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.519-520.640
• Online since: February 2014
• Authors: Jing Dong*, Yang Xia
• Keywords: Computer Vision, Kalman Filter, Real-Time, Video Motion Analysis, Video Stabilization

References

[1] Lee K. Y., Chuang Y. Y., Chen B. Y., et al. Video stabilization using robust feature trajectories. Proceedings of 12th International Conference on Computer Vision, Kyoto, 1397 – 1404 (2009).

DOI: 10.1109/iccv.2009.5459297

[2] Matsushita Y., Ofek E., Tang X., et al. Full-frame video stabilization. IEEE Conference on Computer Vision and Pattern Recognition, San Diego, 50-57 (2005).

DOI: 10.1109/cvpr.2005.166

[3] Pan P., Minagawa A., Sun J., et al. A Dual Pass Video Stabilization System Using Iterative Motion Estimation and Adaptive Motion Smoothing. Proceedings of 20th International Conference on Pattern Recognition, Istanbul, 2298-2301 (2010).

DOI: 10.1109/icpr.2010.562

[4] Grundmann M., Kwatra V., Essa I. Auto-directed video stabilization with robust L1 optimal camera paths. IEEE Conference on Computer Vision and Pattern Recognition, Providence, 225-232 (2011).

DOI: 10.1109/cvpr.2011.5995525

[5] Zhang G., Hua W., Qin X., et al. Video stabilization based on a 3D perspective camera model. The Visual Computer, 25(11): 997-1008 (2009).

DOI: 10.1007/s00371-009-0310-z

[6] Liu F., Gleicher M., Jin H., et al. Content-preserving warps for 3D video stabilization. Transactions on Graphics, 28(3): 44 (2009).

DOI: 10.1145/1531326.1531350

[7] J. Shi and C. Tomasi, Good features to track. IEEE Conference on Computer Vision and Pattern Recognition, 593-600 (1994).

DOI: 10.1109/cvpr.1994.323794

[8] Liu C., Yuen J., Torralba A., et al. Sift flow: Dense correspondence across scenes and its applications. Transactions on Pattern Analysis and Machine Intelligence, 33(5): 978-994 (2011).

DOI: 10.1109/tpami.2010.147

[9] Lucas B. D., Kanade T. An iterative image registration technique with an application to stereo vision. International joint conference on Artificial intelligence, 674-679 (1981).

[10] Fischler M. A., Bolles R. C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6): 381-395 (1981).

DOI: 10.1145/358669.358692