Please wait a minute...
J4  2009, Vol. 43 Issue (8): 1372-1376    DOI: 10.3785/j.issn.1008-973X.
计算机科学技术     
基于视频的微帧组合动态场景生成
余轶民,许端清,余轶军,等
(浙江大学 计算机科学与技术学院,浙江 杭州 310027)
5Videobased dynamic scenes generation with compound microframe
 YU Zhi-Min, XU Duan-Qing, YU Zhi-Jun, DENG
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
 全文: PDF(772 KB)   HTML
摘要:

针对基于视频的动态场景在时域上的不连续问题,提出了一种新的场景生成方法.以微帧为组成单元,以纹理合成特征匹配为基础,采用平滑过渡的方法达到时域的连续性,以获得具有真实感的视觉效果,同时应用无缝纹理混合方法保持视频帧的完整性和平滑性.实验结果表明,该算法具有良好的适应性,能够生成具有良好真实感的新动态场景,可以应用于三维仿真和虚拟现实等领域.

Abstract:

A novel approach was presented for solving discontinuity of video-based dynamic scenes in temporal scope. The micro-frame was introduced as the base of texture synthesis and was taken to make up of a whole frame as a unit. Smooth transition method was applied to ensure temporal continuity for visual effect with reality. The seamless texture mixing algorithm was used to faithfully keep the integrity and smoothness of the new synthesized video frames. Experimental results were encouraging and showed that this approach is well-performed on a wide range of video sequences and can be used to make realistic scenes. This approach can also be applied to a large area, such as 3D emulation and virtual reality etc.

出版日期: 2009-09-28
:  TP 391  
基金资助:

国家“973”重点基础研究发展规划资助项目(2002CB312106);国家“863”高技术研究发展计划资助项目(2002AA414070)

通讯作者: 许端清,男,教授.     E-mail: xdq@cs.zju.edu.cn
作者简介: 余轶民(1977-),男,浙江杭州人,博士生,从事计算机图形图像,视觉计算研究.
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:

余轶民, 许端清, 余轶军, 等. 基于视频的微帧组合动态场景生成[J]. J4, 2009, 43(8): 1372-1376.

YU Zhi-Min, XU Duan-Qing, YU Zhi-Jun, DENG. 5Videobased dynamic scenes generation with compound microframe. J4, 2009, 43(8): 1372-1376.

链接本文:

http://www.zjujournals.com/eng/CN/ 10.3785/j.issn.1008-973X.        http://www.zjujournals.com/eng/CN/Y2009/V43/I8/1372

[1] FOURNIER A, FUSSELL D, CARPENTER L. Computer rendering of stochastic models [J]. Communications of the ACM, 1982, 25(6): 371-384.

[2] SMITH A R. Plants, fractals and formal languages [J]. ACM SIGGRAPH Computer Graphics, 1984, 18(3): 1-10.

[3] CSURI C, HACKATHORN R, PARENT R, et al. Towards an interactive high visual complexity animation system [J]. ACM SIGGRAPH Computer Graphics, 1979, 13(2): 289-299.

[4] NORTON A. Generation and display of geometric fractals in 3-D [J]. ACM SIGGRAPH Computer Graphics, 1982, 16(3): 61-67.

[5] SZELISKI R. Shape from rotation [C]∥ IEEE Conference Computer Vision and Pattern Recognition. Maui: IEEE, 1991: 625-630.

[6] SZELISKI R. Rapid octree construction from image sequences [J]. CVGIP: Image Understanding, 1993, 58(1): 23-32.

[7] LAURENTINI A. The visual hull concept for silhouette-based image understanding [J]. IEEE Transactions on Pattern Analysis Machine Intelligence, 1994, 16(2): 150-162.

[8] MATUSIK W, BUEHLER C, RASKAR R, et al. Image-based visual hulls [C]∥ Computer Graphics Proceedings, Annual Conference Series. New Orleans: ACM, 2000: 369-376.

[9] LIPPMAN A. Movie-maps: an application of the optical videodisc to computer graphics [C]∥ Computer Graphics Proceedings, Annual Conference Series. Seattle: ACM, 1980: 32-43.

[10] CHEN S E, WILLIAMS L. View interpolation for image synthesis [C]∥ Computer Graphics Proceedings, Annual Conference Series. Anaheim: ACM, 1993: 279-288.

[11] SEITZ S M, DYER C R. View morphing [C]∥ Computer Graphics Proceedings, Annual Conference Series. New Orleans: ACM, 1996: 21-30.

[12] ADELSON E H, BERGEN J R. The plenoptic function and the elements of early vision [M]∥ Computational Models of Visual Processing. Cambridge: The MIT Press, 1991.

[13] DEBEVEC P E, TAYLOR C J, MALIK J. Modeling and rendering architecture from photographs: a hybrid geometry and image-based approach [C]∥ Computer Graphics Proceedings, Annual Conference Series. New Orleans: ACM, 1996: 11-20.

[14] SHUM H Y, HE L W. Rendering with concentric mosaics [C]∥ Computer Graphics (SIGGRAPH’99). Los Angeles: ACM, 1999.

[15] BREGLER C, COVELL M, SLANEY M. Video rewrite: driving visual speech with audio [C]∥ Computer Graphics (SIGGRAPH’97). Los Angeles: ACM, 1997: 353360.

[16] POLLARD S, PILU M, HAYES S, et al. View synthesis by trinocular edge matching and transfer [C]∥ British Machine Vision Conference (BMVC98). Southampton: BMVA, 1998.

[17] BAR-JOSEPH Z. Statistical learning of multi-dimensional textures [D]. Jerusalem: The Hebrew University of Jerusalem, 1999.

[18] SCHDL A, SZELISKI R, SALESIN D H, et al. Video textures [C]∥ Proceedings of ACM SIGGRAPH 2000, Computer Graphics Proceedings, Annual Conference Series. New York: ACM, 2000: 489-498.

[19] HASTIE T, TIBSHIRANI R, FRIEDMAN J. The elements of statistical learning: data mining, inference, and prediction [M]. Berlin: Springer-Verlag, 2002.

[20] ZOU Lin-can, LI Da-bin, GUAN Yu, et al. A new video texture based fluid modeling approach [J]. Journal of Image and Graphics, 2006, 6(Suppl.): 155-160.

[21] ASHIKHMIN M. Synthesizing natural textures [C]∥ Proceedings of ACM Symposium on Interactive 3D Graphics. Los Angeles: ACM, 2001: 217-226.

[1] 赵建军,王毅,杨利斌. 基于时间序列预测的威胁估计方法[J]. J4, 2014, 48(3): 398-403.
[2] 崔光茫, 赵巨峰, 冯华君, 徐之海, 李奇, 陈跃庭. 非均匀介质退化图像快速仿真模型的建立[J]. J4, 2014, 48(2): 303-311.
[3] 张天煜, 冯华君, 徐之海, 李奇, 陈跃庭. 基于强边缘宽度直方图的图像清晰度指标[J]. J4, 2014, 48(2): 312-320.
[4] 刘中, 陈伟海, 吴星明, 邹宇华, 王建华. 基于双目视觉的显著性区域检测[J]. J4, 2014, 48(2): 354-359.
[5] 王相兵,童水光,钟崴,张健. 基于可拓重用的液压挖掘机结构性能方案设计[J]. J4, 2013, 47(11): 1992-2002.
[6] 王进, 陆国栋, 张云龙. 基于数量化一类分析的IGA算法及应用[J]. J4, 2013, 47(10): 1697-1704.
[7] 刘羽, 王国瑾. 以已知曲线为渐进线的可展曲面束的设计[J]. J4, 2013, 47(7): 1246-1252.
[8] 胡根生,鲍文霞,梁栋,张为. 基于SVR和贝叶斯方法的全色与多光谱图像融合[J]. J4, 2013, 47(7): 1258-1266.
[9] 吴金亮, 黄海斌, 刘利刚. 保持纹理细节的无缝图像合成[J]. J4, 2013, 47(6): 951-956.
[10] 陈潇红,王维东. 基于时空联合滤波的高清视频降噪算法[J]. J4, 2013, 47(5): 853-859.
[11] 朱凡,李悦,蒋 凯,叶树明,郑筱祥. 基于偏最小二乘的大鼠初级运动皮层解码[J]. J4, 2013, 47(5): 901-905.
[12] 吴宁, 陈秋晓, 周玲, 万丽. 遥感影像矢量化图形的多层次优化方法[J]. J4, 2013, 47(4): 581-587.
[13] 计瑜,沈继忠,施锦河. 一种基于盲源分离的眼电伪迹自动去除方法[J]. J4, 2013, 47(3): 415-421.
[14] 王翔,丁勇. 基于Gabor滤波器的全参考图像质量评价方法[J]. J4, 2013, 47(3): 422-430.
[15] 童水光, 王相兵, 钟崴, 张健. 基于BP-HGA的起重机刚性支腿动态优化设计[J]. J4, 2013, 47(1): 122-130.