Please wait a minute...
J4  2009, Vol. 43 Issue (6): 975-977    DOI: 10.3785/j.issn.1008-973X.2009.
计算机技术、自动化技术     
相机运动条件下的视频前景提取
陈成, 庄越挺, 肖俊
(浙江大学 人工智能研究所, 浙江 杭州 310027)
Video foreground segmentation with camera movement
 CHEN Cheng, PENG Huo-Ting, XIAO Dun
(Institute of Artificial Intelligence, Zhejiang University, Hangzhou 310027, China)
 全文: PDF(2460 KB)   HTML
摘要:

提出一种基于非参数化运动估计和图像配准的方法来进行相机运动条件下的前景提取.通过对视频帧和接近的训练背景图像进行非参数化运动估计,动态地构造出一幅和视频帧的视角完全相同的背景图像, 再通过背景减除提取前景. 为了解决运动估计的计算效率问题, 又提出一种基于流形的改进算法: 在离线阶段, 预先对训练背景图像进行非参数化运动估计, 并利用流形学习对训练背景图像进行建模; 在在线阶段, 通过在背景流形上进行运动插值来快速地估计新视频帧和训练背景图像之间的运动. 实验表明,改进的方法在基本保持像素提取准确率的同时获得了很高的效率.

Abstract:

A new approach based on non-parametric motion estimation and image registration was proposed for video foreground segmentation with camera movement.   First, non-parametric motion estimation was conducted between the video frame containing foreground and a similar training background image. Then, a new background image with exactly the same viewpoint as the video frame was constructed on the fly, and foreground pixels were segmented by classical background subtraction.  A manifold based extension was also proposed to alleviate the low efficiency of motion estimation. In the offline stage, motion estimation for training background images was pre-calculated, and a low-dimensional background manifold was discovered. In the online stage, motion estimation involving the new frame was conducted by fast interpolation on the manifold. Experimental results  show that the proposed method segments videos accurately and efficiently.

出版日期: 2009-06-01
:  TP391.41  
基金资助:

国家自然科学基金资助项目(60525108, 60533090); 国家科技支撑计划课题资助项目(2006BAH02A13-4);中国博士后科学基金资助项目(20080431327);浙江省教育厅科研计划资助项目(Y200803033).

通讯作者: 肖俊, 男, 博士, 讲师.     E-mail: junx@zju.edu.cn
作者简介: 陈成(1982-), 男, 安徽蚌埠人, 博士生, 从事计算机视觉与三维人体动画技术研究.
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  

引用本文:

陈成, 庄越挺, 肖俊. 相机运动条件下的视频前景提取[J]. J4, 2009, 43(6): 975-977.

CHEN Cheng, PENG Huo-Ting, XIAO Dun. Video foreground segmentation with camera movement. J4, 2009, 43(6): 975-977.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2009.        http://www.zjujournals.com/eng/CN/Y2009/V43/I6/975

[1] LEUNG M, YANG Y. Human body motion segmentation in a complex scene [J]. Pattern Recognition, 1987, 20(1): 5564.
[2] STAUFFER C, GRIMSON W. Adaptive background mixture models for realtime tracking [C]∥ Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 1999:246252.
[3] KATO J, WATANABE T, JOGA S, et al. An HMM based segmentation method for traffic monitoring movies [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24 (9): 12911296.
[4] RIDDER C, MUNKELT O, KIRCHNER H. Adaptive background estimation and foreground detection using kalman-filtering [C]∥ Proceedings of International Conference on Recent Advances in Mechatronics. Berlin: Springer, 1995:193199.
[5] WREN C, AZARBAYEJANI A, DARRELL T, et al. Pfinder: Real-time tracking of human body [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7): 780785.
[6] MITTALAND A, HUTTENLOCHER D. Scene modeling for wide area surveillance and image synthesis [C]∥ Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2000, 2: 160167.
[7] WIXSON L. Detecting salient motion by accumulating directionally-consistent flow [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 774780.
[8] HEUER J, KAUP A. Global motion estimation algorithm for video segmentation [C]∥ Proceedings of ACM Multimedia. New York: ACM, 1999:261264.
[9] SONG K, HUANG J. Fast optical flow estimation and its application to real-time obstacle avoidance [C]∥ Proceedings of IEEE International Conference on Robotics and Automation. New York: IEEE, 2001: 28912896.
[10] VERRI A, POGGIO T. Against quantitative optical flow [C]∥ Proceedings of IEEE International Conference on Computer Vision. New York: IEEE, 1987:171180.
[11] TENENBAUM J, SILVA V, LANGFORD J. A global geometric framework for nonlinear dimensionality reduction [J]. Science ,2000, 290(5500): 23192323.
[12] BENGIO Y, PAIEMENT J, VINCENT P. Out-of-sample extensions for LLE, Isomap, MDS, Eigenmaps, and spectral clustering [C]∥ Advances in Neural Information Processing Systems 16. Cambrige: MIT Press, 2004.

[1] 孙志海, 孔万增, 朱善安. 视频目标定位的减法聚类改进算法[J]. J4, 2010, 44(3): 458-462.
[2] 王宣银, 梁冬泰. 基于多元图像分析的表面缺陷检测算法[J]. J4, 2010, 44(3): 448-452.
[3] 范翔, 夏顺仁. 基于特征的显微图像全自动拼接[J]. J4, 2009, 43(7): 1182-1186.
[4] 张冬梅, 刘利刚. 基于角度滤波的平面图形光顺算法[J]. J4, 2009, 43(6): 1042-1046.