Region-based parametric motion segmentation using color information

被引:65
作者
Altunbasak, Y
Eren, PE
Tekalp, AM
机构
[1] Univ Rochester, Dept Elect Engn, Rochester, NY 14627 USA
[2] Univ Rochester, Ctr Elect Imaging Syst, Rochester, NY 14627 USA
来源
GRAPHICAL MODELS AND IMAGE PROCESSING | 1998年 / 60卷 / 01期
关键词
D O I
10.1006/gmip.1997.0453
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
This paper presents pixel-based and region-based parametric motion segmentation methods for robust motion segmentation with the goal of aligning motion boundaries with those of real objects in a scene. We first describe a two-step iterative procedure for parametric motion segmentation by either motion-vector or motion-compensated intensity matching. We next present a region-based extension of this method, whereby all pixels within a predefined spatial region are assigned the same motion label. These predefined regions may be fixed-or variable-size blocks or arbitrary-shaped areas defined by color or texture uniformity. A particular combination of these pixel-based and region-based methods is then proposed as a complete algorithm to obtain the best possible segmentation results on a variety of image sequences. Experimental results showing the benefits of the proposed scheme are provided. (C) 1998 Academic Press.
引用
收藏
页码:13 / 23
页数:11
相关论文
共 23 条
[1]   STATISTICAL MODEL-BASED CHANGE DETECTION IN MOVING VIDEO [J].
AACH, T ;
KAUP, A ;
MESTER, R .
SIGNAL PROCESSING, 1993, 31 (02) :165-180
[3]  
ALTUNBASAK Y, 1996, S MULT COMM VID COD
[4]  
Bergen J. R., 1992, ARTIF INTELL, P147
[5]  
BORSHUKOV GD, 1996, P SPIE IS T EL IM SC
[6]  
BOVER M, 1995, P 2 AS C COMP VIS AC
[7]  
CHANG MM, 1994, P IEEE INT C AC SPEE
[8]  
Dufaux F., 1995, Proceedings. International Conference on Image Processing (Cat. No.95CB35819), P306, DOI 10.1109/ICIP.1995.529707
[9]  
GU C, 1995, P INT S MULT COMM VI
[10]   DETERMINING OPTICAL-FLOW [J].
HORN, BKP ;
SCHUNCK, BG .
ARTIFICIAL INTELLIGENCE, 1981, 17 (1-3) :185-203