LINEAR AND INCREMENTAL ACQUISITION OF INVARIANT SHAPE MODELS FROM IMAGE SEQUENCES

被引：31

作者：

WEINSHALL, D ^{[1
]}

TOMASI, C ^{[1
]}

机构：

[1] STANFORD UNIV,DEPT COMP SCI,STANFORD,CA 94305

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1995年 / 17卷 / 05期

关键词：

STRUCTURE FROM MOTION; LINEAR RECONSTRUCTION; FACTORIZATION METHOD; AFFINE SHAPE; EUCLIDEAN SHAPE; WEAK PERSPECTIVE; GRAMIAN; AFFINE COORDINATES;

D O I：

10.1109/34.391392

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We show how to automatically acquire Euclidian shape representations of objects from noisy image sequences under weak perspective. The proposed method is linear and incremental, requiring no more than pseudoinverse. A nonlinear, but numerically sound preprocessing stage is added to improve the accuracy of the results even further. Experiments show that attention to noise and computational techniques improves the shape results substantially with respect to previous methods proposed for ideal images.

引用

页码：512 / 517

页数：6

共 16 条

[1] EPIPOLAR-PLANE IMAGE-ANALYSIS - AN APPROACH TO DETERMINING STRUCTURE FROM MOTION [J].