An affine-invariant active contour model (AI-snake) for model-based segmentation

被引:55
作者
Ip, HHS [1 ]
Shen, DG [1 ]
机构
[1] City Univ Hong Kong, Dept Comp Sci, Image Comp Grp, Kowloon, Peoples R China
关键词
active contour; affine invariant; correspondence matching; curvature; deformable model; model-based; object tracking; snake;
D O I
10.1016/S0262-8856(97)00051-6
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 show that existing shaped-based active contour models are not affine-invariant and we addressed the problem by presenting an affine-invariant snake model (AI-snake) such that its energy function are defined in terms local and global affine-invariant features. The main characteristic of the AI-snake is that, during the process of object extraction, the pose of the model contour is dynamically adjusted such that it is in alignment with the current snake contour by solving the snake-prototype correspondence problem and determining the required affine transformation. In addition, we formulate the correspondence matching between the snake and the object prototype as an error minimization process between two feature vectors which capture both local and global deformation information. We show that the technique is robust against object deformations and complex scenes. (C) 1998 Elsevier Science B.V.
引用
收藏
页码:135 / 146
页数:12
相关论文
共 35 条
[31]   GENERATION OF AFFINE INVARIANT LOCAL CONTOUR FEATURE DATA [J].
VAZ, RF ;
CYGANSKI, D .
PATTERN RECOGNITION LETTERS, 1990, 11 (07) :479-483
[32]   SURFACE RECONSTRUCTION USING DEFORMABLE MODELS WITH INTERIOR AND BOUNDARY CONSTRAINTS [J].
WANG, YF ;
WANG, JF .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1992, 14 (05) :572-579
[33]   A FAST ALGORITHM FOR ACTIVE CONTOURS AND CURVATURE ESTIMATION [J].
WILLIAMS, DJ ;
SHAH, M .
CVGIP-IMAGE UNDERSTANDING, 1992, 55 (01) :14-26
[34]   Parameterized feasible boundaries in gradient vector fields [J].
Worring, M ;
Smeulders, AWM ;
Staib, LH ;
Duncan, JS .
COMPUTER VISION AND IMAGE UNDERSTANDING, 1996, 63 (01) :135-144
[35]   ROBUST ACTIVE CONTOURS WITH INSENSITIVE PARAMETERS [J].
XU, G ;
SEGAWA, E ;
TSUJI, S .
PATTERN RECOGNITION, 1994, 27 (07) :879-884