What's NEXT? An interactive next best view approach

被引：15

作者：

Bottino, A ^{[1
]}

Laurentini, A ^{[1
]}

机构：

[1] Politecn Torino, Dipartimento Automat & Informat, I-10129 Turin, Italy

来源：

PATTERN RECOGNITION | 2006年 / 39卷 / 01期

关键词：

shape from silhouettes; visual hull; volume intersection; next best view problem; active vision; geometric probing;

D O I：

10.1016/j.patcog.2005.06.008

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Shape-from-silhouettes algorithms use either a surface or a volumetric approach. A problem with the volumetric approach is that in general we know neither the accuracy of the reconstruction, nor where to locate new viewpoints for improving the accuracy. In this paper we present a general approach to interactive, object-specific volumetric algorithms, based on a necessary condition for the best possible reconstruction to have been performed. The outlined approach can be applied to any class of objects. As an example of this approach, an interactive algorithm has been implemented for convex polyhedra. (c) 2005 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

引用

页码：126 / 132

页数：7

共 22 条

[1] GENERATING OCTREES FROM OBJECT SILHOUETTES IN ORTHOGRAPHIC VIEWS [J].

AHUJA, N ;

VEENSTRA, J .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1989, 11 (02) :137-149

[2]

[Anonymous], P 18 ANN ACM S THEOR

[3] The visual hull of smooth curved objects [J].

Bottino, A ;

Laurentini, A .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2004, 26 (12) :1622-1632

[4] 3D surface reconstruction using occluding contours [J].

Boyer, E ;

Berger, MO .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 1997, 22 (03) :219-233

[5] MODEL CONSTRUCTION AND SHAPE-RECOGNITION FROM OCCLUDING CONTOURS [J].

CHIEN, CH ;

AGGARWAL, JK .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1989, 11 (04) :372-389

[6] SURFACE SHAPE FROM THE DEFORMATION OF APPARENT CONTOURS [J].

CIPOLLA, R ;

BLAKE, A .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 1992, 9 (02) :83-112

[7] GLOBAL SURFACE RECONSTRUCTION BY PURPOSIVE CONTROL OF OBSERVER MOTION [J].

KUTULAKOS, KN ;

DYER, CR .

ARTIFICIAL INTELLIGENCE, 1995, 78 (1-2) :147-177

[8] How many 2D silhouettes does it take to reconstruct a 3D object? [J].

Laurentini, A .

COMPUTER VISION AND IMAGE UNDERSTANDING, 1997, 67 (01) :81-87

[9] HOW FAR 3D SHAPES CAN BE UNDERSTOOD FROM 2D SILHOUETTES [J].

LAURENTINI, A .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1995, 17 (02) :188-195

[10] THE VISUAL HULL CONCEPT FOR SILHOUETTE-BASED IMAGE UNDERSTANDING [J].

LAURENTINI, A .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1994, 16 (02) :150-162

← 1 2 3 →