Abstract
Video stabilization is an important technique in present day digital cameras as most of the cameras are hand-held, mounted on moving platforms or subjected to atmospheric vibrations. In this paper we propose a novel video stabilization scheme based on estimating the camera motion using maximally stable extremal region features. These features traditionally used in wide baseline stereo problems were never explored for video stabilization purposes. Through our extensive experiments show we how some properties of these region features are suitable for the stabilization task. After estimating the global camera motion parameters using these region features, we smooth the motion parameters using a gaussian filter to retain the desired motion. Finally, motion compensation is carried out to obtain a stabilized video sequence. A number of examples on real and synthetic videos demonstrate the effectiveness of our proposed approach. We compare our results to existing techniques and show how our proposed approach compares favorably to them. Interframe Transformation Fidelity is used for objective evaluation of our proposed approach.
Similar content being viewed by others
References
Auberger S, Miro C (2005) Digital video stabilization architecture for low cost devices. In: Proc. of the 4th international symposium on image and signal processing and analysis, pp 474–479
Battiato S, Gallo G, Puglisi G, Scellato S (2007) SIFT features tracking for video stabilization. In: ICIAP 2007. Modena, Italy, pp 825–830
Battiato S, Puglisi G, Bruna A (2008) A robust video stabilization system by adaptive motion vectors filtering. In: ICME, pp 373–376
Censi A, Fusiello A, Roberto V (1999) Image stabilization by feature tracking. In: Proc. int. conf. anal. process, vol 2. Venice, Italy, pp 665–667
Chang J, Hu W, Cheng M, Chang B (2002) Digital image translation and rotation motion stabilization using optical flow technique. IEEE Trans Consum Electron 48(1):108–115
Chen B-Y, Lee K-Y, Huang W-T, Lin J-S (2008) Capturing intention-based full-frame video stabilization. In: Pacific graphics 2008 conference proceedings, vol 27, pp 1805–1814
Donoser M, Bischof H (2006) Efficient maximally stable extremal region tracking. In: IEEE conf. comput. vision pattern recognition, pp 553–560
Erturk S (2003) Digital image stabilization with sub-image phase correlation based global motion estimation. IEEE Trans Consum Electron 49(4):1320–1325
Erturk S, Dennis TJ (2000) Image sequence stabilization based on DFT filtering. IEE Proc Vis Image Signal Proc 147(2):95–102
Fischler MA, Bolles RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24(6):381–395
Fraundorfer F, Bischof H (2005) A novel performance evaluation method of local detectors on non-planar scenes. In: Workshop proceedings of CVPR
Hong W, Wei D, Batur AU (2010) Video stabilization and rolling shutter distortion reduction. In: Proceedings of the international conference on image processing, ICIP 2010, 26–29 Sept, Hong Kong, pp 3501–3504
Huang K-Y, Tsai Y-M, Tsai C-C, Chen L-G (2010) Video stabilization for vehicular applications using SURF-like descriptor and KD-tree. In: Proceedings of the international conference on image processing, ICIP 2010, 26–29 Sept, Hong Kong, pp 3517–3520
Jin J, Zhu Z, Xu G (2001) Digital video sequence stabilization based on 2.5-D motion estimation and inertial motion filtering. Real-Time Imaging 7(4):357–365
Ko S, Lee S, Jeon S, Kang E (1999) Fast digital image stabilizer based on gray-coded bit-plane matching. IEEE Trans Consum Electron 45(3):598–603
Kumar S, Azartash H, Biswas M, Nguyen T (2011) Real-time affine global motion estimation using phase correlation and its application for digital image stabilization. IEEE Trans Image Process 20(12):3406–3418
Lee K-Y, Chuang Y-Y, Chen B-Y, Ouhyoung M (2009) Video stabilization using robust feature trajectories. In: ICCV, pp 1397–1404
Liang Y-M, Tyan H-R, Chang S-L, Liao H-YM, Chen S-W (2004) Video stabilization for a camcorder mounted on a moving vehicle. IEEE Trans Veh Technol 53(6):1636–1648
Litvin A, Konrad J, Karl W (2003) Probabilistic video stabilization using kalman filtering and mosaicking. In: Proc. image video commun. IST/SPIE symp. electron. imaging. Santa Clara, CA, pp 663–674
Liu F, Gleicher M, Jin H, Agarwala A (2009) Content-preserving warps for 3D video stabilization. ACM Trans Graph 28(3):44:1–44:9
Liu F, Gleicher M, Wang J, Jin H, Agarwala A (2011) Subspace video stabilization. ACM Trans Graph 30(1):4:1–4:10
Lowe D (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110
Luo Q, Khoshgoftaar TM (2007) An empirical study on estimating motions in video stabilization. In: Proc. of the IEEE international conference on information reuse and integration. Las Vegas, Nevada, USA, pp 360–366
Matas J, Chum O, Urban M, Pajdla T (2002) Robust wide baseline stereo from maximally stable extremal regions. In: Proc. BMVC, pp 384–393
Matsushita Y, Ofek E, Ge W, Tang X, Shum H-Y (2006) Full-frame video stabilization with motion inpainting. IEEE Trans Pattern Anal Mach Intell 28(7):1150–1163
Mikolajczyk K, Tuytelaars T, Schmid C, Zisserman A, Matas J, Schaffalitzky F, Kadir T, Van Gool L (2005) A comparison of affine region detectors. Int J Comput Vis 65(1–2):43–72
Morimoto C, Chellappa R (1998) Evaluation of image stabilization algorithms. In: Proc. of IEEE international conference on acoustics, speech, and signal processing (ICASSP’98), pp 2789–2792
Morimoto C, Chellappa R (1996) Fast electronic digital image stabilization for off-road navigation. Real-Time Imaging 2(5):285–296
Morimoto C, Chellappa R (1997) Fast 3-D stabilization and mosaic construction. In: IEEE conf. comput. vision pattern recognition. San Juan, Puerto Rico, pp 660–665
Obdrzálek S, Matas J (2002) Object recognition using local affine frames on distinguished regions. In: BMVC, pp 113–122
Okade M, Biswas PK (2011) Improving video stabilization in the presence of motion blur. In: Third national conference on computer vision, pattern recognition, image processing and graphics (NCVPRIPG), 15-17, Dec pp 78–81
Pail J, Park Y, Kim D (1992) An adaptive motion decision system for digital image stabilizer based on edge pattern matching. IEEE Trans Consum Electron 38(3):607–615
Pang D, Chen H, Halawa S (2010) Efficient video stabilization with dual-tree complex wavelet transform. In: EE368 Stanford spring project report
Piva S, Zara M, Gera G, Regazzoni C (2003) Color-based video stabilization for real-time on-board object detection on high-speed trains. In: Proc. IEEE conf. advanced video signal based surveillance, pp 299–304, Miami, FL
Puglisi G, Battiato S (2011) A robust image alignment algorithm for video stabilization purposes. IEEE Trans Circuits Syst Video Technol 21(10):1390–1400
Qin C, Wang S, Zhang X (2012) Simultaneous inpainting for image structure and texture using anisotropic heat transfer model. Multimed Tools Appl 56:469–483
Sivic J, Zisserman A (2003) Video google: a text retrieval approach to object matching in videos. In: ICCV, pp 1470–1477
Tuytelaars T, Van Gool L (2004) Matching widely separated views based on affine invariant regions. Int J Comput Vis 59(1):61–85
Uomori K, Morimura A, Ishii H (1992) Electronic image stabilization systems for video cameras and VCRs. J Soc Motion Pict Telev 101(2):66–75
Yang J, Schonfeld D, Mohamed M (2009) Robust video stabilization based on particle filter tracking of projected camera motion. IEEE Trans Circuits Syst Video Technol 19(7):945–954
Yu G, Morel J-M (2009) A fully affine invariant image comparison method. In: IEEE international conference on acoustics, speech and signal processing, pp 1597–1600
Zhou J, Hu H, Wan D (2011) Video stabilization and completion using two cameras. IEEE Trans Circuits Syst Video Technol 21(12):1879–1889
Acknowledgements
We would like to thank the anonymous reviewers for their review comments which helped us immensely to improve the quality of our work.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Okade, M., Biswas, P.K. Video stabilization using maximally stable extremal region features. Multimed Tools Appl 68, 947–968 (2014). https://doi.org/10.1007/s11042-012-1095-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-012-1095-z