Segmentation framework based on label field fusion

被引:22
作者
Jodoin, Pierre-Marc [1 ]
Mignotte, Max
Rosenberger, Christophe
机构
[1] Univ Sherbrooke, Dept Informat, Sherbrooke, PQ J1K 2R1, Canada
[2] Univ Montreal, Dept Informat & Rech Operat, Montreal, PQ H2L 2W5, Canada
[3] Univ Orleans, Lab Vis & Robot, F-18020 Bourges, France
关键词
color segmentation; label fusion; motion estimation; motion segmentation; occlusion;
D O I
10.1109/TIP.2007.903841
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we put forward a novel fusion framework that mixes together label fields instead of observation data as is usually the case. Our framework takes as input two label fields: a quickly estimated and to-be-refined segmentation map and a spatial region map that exhibits the shape of the main objects of the scene. These two label fields are fused together with a global energy function that is minimized with a deterministic iterative conditional mode algorithm. As explained in the paper, the energy function may implement a pure fusion strategy or a fusion-reaction function. In the latter case, a data-related term is used to make the optimization problem well posed. We believe that the conceptual simplicity, the small number of parameters, the use of a simple and fast deterministic optimizer that admits a natural implementation on a parallel architecture are among the main advantages of our approach. Our fusion framework is adapted to various computer vision applications among which are motion segmentation, motion estimation and occlusion detection.
引用
收藏
页码:2535 / 2550
页数:16
相关论文
共 88 条
[1]   Region-based parametric motion segmentation using color information [J].
Altunbasak, Y ;
Eren, PE ;
Tekalp, AM .
GRAPHICAL MODELS AND IMAGE PROCESSING, 1998, 60 (01) :13-23
[2]  
Alvarez L, 2002, LECT NOTES COMPUT SC, V2350, P721
[3]   Reliable estimation of dense optical flow fields with large displacements [J].
Alvarez, L ;
Weickert, J ;
Sánchez, J .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2000, 39 (01) :41-56
[4]   A COMPUTATIONAL FRAMEWORK AND AN ALGORITHM FOR THE MEASUREMENT OF VISUAL-MOTION [J].
ANANDAN, P .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1989, 2 (03) :283-310
[5]  
[Anonymous], 2005, NEURAL NETWORKS PATT
[6]  
[Anonymous], P IEEE INT C AC SPEE
[7]   Computing optical flow via variational techniques [J].
Aubert, G ;
Deriche, R ;
Kornprobst, P .
SIAM JOURNAL ON APPLIED MATHEMATICS, 1999, 60 (01) :156-182
[8]   PERFORMANCE OF OPTICAL-FLOW TECHNIQUES [J].
BARRON, JL ;
FLEET, DJ ;
BEAUCHEMIN, SS .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1994, 12 (01) :43-77
[9]   Multisensor image segmentation using Dempster-Shafer fusion in Markov fields context [J].
Bendjebbour, A ;
Delignon, Y ;
Fouque, L ;
Samson, V ;
Pieczynski, W .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2001, 39 (08) :1789-1798
[10]  
Bergen L, 2000, PROC CVPR IEEE, P536, DOI 10.1109/CVPR.2000.854907