Video object cut and paste

被引:180
作者
Li, Y
Sun, J
Shum, HY
机构
来源
ACM TRANSACTIONS ON GRAPHICS | 2005年 / 24卷 / 03期
关键词
video segmentation; matting; tracking; graph cut;
D O I
10.1145/1073204.1073234
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
In this paper, we present a system for cutting a moving object out from a video clip. The cutout object sequence can be pasted onto another video or a background image. To achieve this, we first apply a new 3D graph cut based segmentation approach on the spatial-temporal video volume. Our algorithm partitions watershed presegmentation regions into foreground and background while preserving temporal coherence. Then, the initial segmentation result is refined locally. Given two frames in the video sequence, we specify two respective windows of interest which are then tracked using a bi-directional feature tracking algorithm. For each frame in between these two given frames, the segmentation in each tracked window is refined using a 2D graph cut that utilizes a local color model. Moreover, we provide brush tools for the user to control the object boundary precisely wherever needed. Based on the accurate binary segmentation result, we apply coherent matting to extract the alpha mattes and foreground colors of the object.
引用
收藏
页码:595 / 600
页数:6
相关论文
共 19 条
  • [1] Keyframe-based tracking for rotoscoping and animation
    Agarwala, A
    Hertzmann, A
    Salesin, DH
    Seitz, SM
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2004, 23 (03): : 584 - 591
  • [2] [Anonymous], P SIGGRAPH 2002
  • [3] [Anonymous], P ACM SIGGRAPH AUG
  • [4] APOSTOLOFF N, 2004, P CVPR, V1, P407
  • [5] Bellman R., 1957, DYNAMIC PROGRAMMING
  • [6] The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields
    Black, MJ
    Anandan, P
    [J]. COMPUTER VISION AND IMAGE UNDERSTANDING, 1996, 63 (01) : 75 - 104
  • [7] BLAKE A., 1998, Active Contours
  • [8] BLAKE A, 2004, P ECCV, V1, P428
  • [9] Boykov Y.Y., 2001, ICCV, V1, P105, DOI DOI 10.1109/ICCV.2001.937505
  • [10] Chuang YY, 2001, PROC CVPR IEEE, P264