期刊文献+

基于单应轨迹的视频实时稳像算法 被引量:3

A real-time video stabilization algorithm based on homography trajectory
下载PDF
导出
摘要 针对视频稳像中实时任务的需求特点,提出一种基于单应轨迹的视频稳像算法。估计序列图像帧间的单应变换,并将该变换作用于图像窗口的4个角点,从而对每帧图像产生4个短的单应轨迹以代表视频短时间内的运动。利用关联卡尔曼滤波器以一种连续方式对不同帧的单应轨迹进行平滑。对图像合成采用包括性和相似约束以提高结果视频的可观性质量。该算法以在线方式工作,消除了缓存输入图像帧导致的延迟,具备不依赖于复杂的3D重建和长距离特征跟踪的优点,并有效避免了单应模型表达视频运动模型的误差积累问题。实验表明该算法能够有效对包含2D和较复杂3D场景的视频进行稳像,并且能够达到实时处理速度。 Motivated by the demands of real-time video stabilization,a real-time video stabilization algorithm based on homography trajectory is proposed. For each input frame,our approach regenerates four short homography trajectories by applying inter-frame homography transformations to the four corners of image rectangle. An associate Kalman filter is then performed to smooth these transformational trajectories. Finally,at the stage of image composition,constraints of inclusion and similarity are considered for selecting a visually plausible stabilized video. The proposed method can offer real-time video stabilization and it can remove the delays for caching coming images. In addition,our method does not rely on sophisticated 3D reconstruction or long-range feature tracking and it can effectively relieve the errors introduced by using homography to model the video motion. Experiments show that our approach can offer real-time stabilizing for videos with 2D scenes or the 3D scenes with moderate depth variation.
出处 《国防科技大学学报》 EI CAS CSCD 北大核心 2014年第2期99-104,共6页 Journal of National University of Defense Technology
基金 国家自然科学基金资助项目(11002156) 国家部委资助项目
关键词 实时算法 视频稳像 卡尔曼滤波 视频运动分析 单应变换 real-time algorithm video stabilization Kalman filer video motion analysis homography
  • 相关文献

参考文献17

  • 1Liu C, Yuen J, Torralba A. Sift flow: Dense correspondence across scenes and its applications [ J ]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011,33 (5) :978 -994.
  • 2Kumar S, Azartash H, Biswas M, et al. Real-time affine global motion estimation using phase correlation and its application for digital image stabilization [ J ]. IEEE Transactions on Image Processing, 2011, 20 ( 12 ) :3406 - 3418.
  • 3Wang C T, Kim J H, Byun K Y, et al. Robust digital image stabilization using the Kalman filter [ J ]. Transactions on Consumer Electronics, 2009, 55 ( 1 ) :6 - 14.
  • 4Ryu Y G, Roh H C, Chung M J, et al. Long-time video stabilization using point-feature trajectory smoothing [ C ]// Proceeding of IEEE International Conference on Consumer Electronics, 2011:189 - 190.
  • 5Morimoto C, Chellappa R. Evaluation of image stabilization algorithms[ C ]//Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, 1998,5:2789 - 2792.
  • 6Fischler M A, Bolles R C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography [ J ]. Communications of the ACM, 1981, 24(6) :381 -395.
  • 7Kurazume R, Hirose S. Development of image stabilization system for remote operation of walking robots [ C ]//Proceedings of IEEE International Conference on Robotics and Automation, 2000,2 : 1856 - 1861.
  • 8Lucas B D, Kanade T. An iterative image registration technique with an application to stereo vision [ C ]// Proceedings of International Joint Conference on Artificial Intelligence, 1981,2 : 674 - 679.
  • 9Lee K Y, Chuang Y Y, Chen B Y, et al. Video stabilization using robust feature trajectories [ C ]//Proceedings of 12th International Conference on Computer Vision, 2009:1397 - 1404.
  • 10Pang D, Chen H, Halawa S. Efficient video stabilization with dual-tree complex wavelet transform [ R ]. San Francisco: Stanford University Press, 2010.

同被引文献26

  • 1时永刚,周渝斌,赵跃进.实时电子数字稳像系统并行处理的快速实现[J].电子与信息学报,2006,28(7):1174-1178. 被引量:4
  • 2Liu F, Gleicher M, Jin H, et al. Content-preserving warps for 3d video stabilization[J].ACM Transac- tions on Graphics, 2009,28(3) : 255-231.
  • 3Shi J, Malik J. Motion segmentation and tracking using normalized[C].In IEEE International Conder- ence on Computer Vision(ICCV), 1998:1154-1160.
  • 4Gunnar Farnebtck. Two-Frame Motion Estimation Based on Polynomial Expansion[A]. SCIA'03 Pro- ceedings of the 13th Scandinavian conference on Image analysis Pages.Berlin:Springer,2003:363-370.
  • 5Baker Simon, Scharstein Daniel, Lewis J P. A data- base and evaluation methodology for optical flow[J]. Intemational Journal of Computer Vision,2011 92(1):1-31.
  • 6Hartley R, Zisserman A. computer vision[M].New ty Press, 2004:159-176.
  • 7Multiple view geometry in York:Cambridge Universi- Hartley R I. In defense of the eight-point algorithm [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997,19(6) :580-593.
  • 8ZHANG Haolong, WU Qiang, LIU Tianqi, et al. Design and implementation of electronic image stabilization system based on dual-core DSP[C]. International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Beijing, 2013: 117-120. doi: 10.1109/IIH-MSP. 2013.38.
  • 9HAQUE M N, BISWAS M, PICKERING M R, et al. A low-complexity image registration algorithm for global motion estimation[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2012, 22(3): 426-433. doi: 10.1109/TCSVT.2011.2163983.
  • 10KIM S W, YIN S, YUN K, et al. Spatio-temporal weighting in local patches for direct estimation of camera motion in video stabilization[J]. Elsevier Computer Vision and Image Understanding, 2014, 118: 71-83. doi: 10.1016/j.cviu. 2013.09.005.

引证文献3

二级引证文献5

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部