Abstract
In this paper, a video stabilization technique based on optimized dynamic time warping (DTW) has been proposed. The method uses integral frame projection warping (IFPW) for the relative motion estimation between consecutive frames. Implementation of DTW is done using dynamic programming, to give a significant reduction in terms of memory and processing time. Most of the motion estimation techniques are adversely affected due to blurring, low intensity and large displacements. The proposed method gives accurate results under these conditions and proves to be a robust for various applications such as moving platform and night shooting, over existing intensity-based motion estimation techniques. Efficiency of the proposed IFPW technique, for dark video and blurry frames, is measured using motion estimation error analysis. Overall performance evaluation of the stabilization system is done using interframe transformation fidelity and processing time.
Similar content being viewed by others
References
Oshima, M., Hayashi, T., Fujioka, S., Inaji, T., Mitani, H., Kajino, J., Ikeda, K., Komoda, K.: VHS camcorder with electronic image stabilizer. Proc. IEEE Trans. Consum. Electron. 35(4), 749–758 (1989)
Sato, K., Ishizuka, S., Nikami, A., Sato, M.: Control techniques for optical image stabilizing system. Proc. IEEE Trans. Consum. Electron. 39(3), 461–466 (1993)
Kinugasa, T., Yamamoto, N., Komatsu, H., Takase, S., Imaide, T.: Electronic image stabilizer for video camera use. Proc. IEEE Trans. Consum. Electron. 36(3), 520–525 (1990)
Vella, F., Castorina, A., Mancuso, M., Messina, G.: Digital image stabilization by adaptive block motion vectors filtering. Proc. IEEE Trans. Consum. Electron. 48(3), 796–801 (2002)
Ko, S.-J., Lee, S.-H., Lee, K.-H.: Digital image stabilizing algorithms based on bit-plane matching. Proc. IEEE Trans. Consum. Electron. 44(3), 617–622 (1998)
Ko, S.-J., Lee, S.-H., Jeon, S.-W., Kang, E.-S.: Fast digital image stabilizer based on gray-coded bit-plane matching. Proc. IEEE Trans. Consum. Electron. 45(3), 598–603 (1999)
Kim, J.-S., Park, R.-H.: A fast feature-based block matching algorithm using integral projections. Proc. IEEE J. Sel. Areas Commun. 10(5), 968–971 (1992)
Piva, S., Zara, M., Gera, G., Regazzoni, C.S.: Color-based video stabilization for real-time onboard object detection on high-speed trains. In: Proceedings of the IEEE Conference on Advantage Video and Signal Based Surveillance, pp. 299–304. Miami, FL, USA (2003)
Bosco, A., Bruna, A., Battiato, S., Bella, G., Puglisi, G.: Digital video stabilization through curve warping techniques. Proc. IEEE Trans. Consum. Electron. 54(2), 220–224 (2008)
Muller, M.: Information Retrieval for Music and Motion, Ch. 4. Springer, Berlin, pp. 69–84 (2007)
Keogh, E., Pazzani, M.: Derivative dynamic time warping. In: Proceeding of the First SIAM International Conference on Data Mining, pp. 1–11. Chicago, IL USA (2001)
Xu, J., Chang, H.-W., Yang, S., Wang, M.: Fast feature-based video stabilization without accumulative global motion estimation. Proc. IEEE Trans. Consum. Electron. 58(3), 993–999 (2012)
Matsushita, Y., Ofek, E., Ge, W., Tang, X., Shum, H.-Y.: Full-frame video stabilization with motion inpainting. Proc. IEEE Trans. Pattern Anal. Mach. Intell. 28(7), 1150–1163 (2006)
Ertürk, S.: Real-time digital image stabilization using Kalman filters. Proc. Real-Time Imaging 8(4), 317–328 (2002)
Tsai, T.-H., Fang, C.-L., Chuang, H.-M.: Design and implementation of efficient video stabilization engine using maximum a posteriori estimation and motion energy smoothing approach. Proc. IEEE Trans. Circuits Syst. Video Technol. 22(6), 817–830 (2012)
Ertürk, S., Dennis, T.J.: Image sequence stabilization based on DFT filtering. Proc. IEE Proc. Vis. Image Signal Process. 147(2), 95–102 (2000)
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Shukla, D., Jha, R.K. A robust video stabilization technique using integral frame projection warping. SIViP 9, 1287–1297 (2015). https://doi.org/10.1007/s11760-013-0584-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-013-0584-5